diff --git "a/data/json/OR-github_discussions.txt" "b/data/json/OR-github_discussions.txt" new file mode 100644--- /dev/null +++ "b/data/json/OR-github_discussions.txt" @@ -0,0 +1,258 @@ +{"messages": [{"user": "I place cells manually using tcl scripting but when I run detailed placements they do move.\r\n\r\nIs there any atribute i can set to prevent this and lock the cell to defined location? "}, {"assistant": " $inst setPlacementStatus LOCKED"}]} +{"messages": [{"user": "Hello, \r\n\r\nCould you help me figuring out how to add and place some cell through command line to specific coords? \r\n\r\nThanks"}, {"assistant": "By 'add' do you mean create new instances and connect them? In general you'll have to use odb scripting for this. https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/cts/test/array.tcl creates and places instances along with other operations."}]} +{"messages": [{"user": "Is the \"rebuffer\" buffer superfluous here?\r\n\r\nThe \"rebuffer\" buffer does not exist in placement, only after CTS.\r\n\r\n`make DESIGN_CONFIG=designs/asap7/mock-array/Element/config.mk gui_final`:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/7a197d43-9270-4233-bebd-620b9cfd5fc8)\r\n\r\n\r\n`make DESIGN_CONFIG=designs/asap7/mock-array/Element/config.mk gui_place`:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/7d45e527-9062-4a14-b4d3-24125d3c0f46)\r\n"}, {"assistant": "It is there for timing optimization as the path has negative slack which is addressed post-CTS. Is there a reason to think it superfluous?"}, {"user": "No extra buffers after removing `set_load -pin_load 10 [all_outputs]`:\r\n\r\nUntar [cts-nobuffer.tar.gz](https://github.com/The-OpenROAD-Project/OpenROAD/files/14554686/cts-nobuffer.tar.gz)\r\n\r\n```\r\n$ ./run-me-mock-array_Element-asap7-base.sh\r\nOpenROAD v2.0-12488-g85f541bb6\r\nopenroad> report_checks -to io_lsbOuts_7\r\nStartpoint: _755_ (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: io_lsbOuts_7 (output port clocked by clock_vir)\r\nPath Group: clock_vir\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 74.98 74.98 clock network delay (propagated)\r\n 0.00 74.98 ^ _755_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 45.97 120.95 v _755_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 13.06 134.01 ^ _435_/Y (INVx4_ASAP7_75t_R)\r\n 18.04 152.05 ^ output265/Y (BUFx2_ASAP7_75t_R)\r\n 0.01 152.06 ^ io_lsbOuts_7 (out)\r\n 152.06 data arrival time\r\n\r\n 300.00 300.00 clock clock_vir (rise edge)\r\n 70.00 370.00 clock network delay (ideal)\r\n -20.00 350.00 clock uncertainty\r\n 0.00 350.00 clock reconvergence pessimism\r\n-240.00 110.00 output external delay\r\n 110.00 data required time\r\n---------------------------------------------------------\r\n 110.00 data required time\r\n -152.06 data arrival time\r\n---------------------------------------------------------\r\n -42.06 slack (VIOLATED)\r\n```\r\n"}, {"assistant": "> How do I stop \"don't touch\" from removing the output buffer so I get the comparison I'm after?\r\n\r\nSet don't touch after the output buffer is created.\r\n\r\n> If I delete set_load -pin_load 10 [all_outputs], the extra buffer goes away.\r\n\r\nProbably the timing improves and the net no longer needs repair. Similarly with the set_driving_cell changing the timing."}]} +{"messages": [{"user": "In issue #4692:\r\n\r\n> If you use `db = odb.dbDatabase.create()` then you get a db with no Logger that can't issue messages. I suggest you just use the API that works.\r\n\r\nThe problem with that is while `odb.dbDatabase.create()` allows multiple DBs to exist simultaneously, the new API does not. We do have a number of scripts that operate on two databases simultaneously. Problem is, now we have three ways of doing this, none of which are ideal:\r\n\r\n1. This fails with \"No logger is installed in odb.\"\r\n\r\n\t```python3\r\n\tdef _2r1w_db_old(db1_in, db2_in, db_out):\r\n\t db1 = odb.dbDatabase.create()\r\n\t db1 = odb.read_db(db1, db1_in)\r\n\t db2 = odb.dbDatabase.create()\r\n\t db2 = odb.read_db(db2, db2_in)\r\n\t odb.write_db(db1, db_out)\r\n\t```\r\n\r\n2. This fails with \"You can't load a new db file as the db is already populated\"\r\n\r\n\t```python3\r\n\tdef _2r1w_db_new(db1_in, db2_in, db_out):\r\n\t ord_tech1 = Tech()\r\n\t design1 = Design(ord_tech1)\r\n\t design1.readDb(db1_in)\r\n\t \r\n\t ord_tech2 = Tech()\r\n\t design2 = Design(ord_tech2)\r\n\t design2.readDb(db2_in)\r\n\t \r\n\t design1.writeDb(db_out)\r\n\t```\r\n\r\n3. This works, but is horrifying and is likely to fail for multiple reasons in the future.\r\n\r\n\t```python3\r\n\tdef _2r1w_db_mix(db1_in, db2_in, db_out):\r\n\t ord_tech1 = Tech()\r\n\t design1 = Design(ord_tech1)\r\n\t design1.readDb(db1_in)\r\n\t \r\n\t db2 = odb.dbDatabase.create()\r\n\t db2.setLogger(design1.getLogger())\r\n\t db2 = odb.read_db(db2, db2_in)\r\n\t\r\n\t design1.writeDb(db_out)\r\n\t```\r\n\r\nAdvice?"}, {"assistant": "I'm curious what your use case is for multiple dbs. I guess you are only use odb APIs as nothing else in OR is likely to work in such a scenario. \r\n\r\nWe could add an API to setup the logger."}, {"assistant": "Does this satisfy your needs\r\n```\r\nfrom openroad import Design, Tech\r\nimport odb\r\n\r\nord_tech1 = Tech()\r\ndesign1 = Design(ord_tech1)\r\ndesign1.readDb('odb/test/data/design.odb')\r\n\r\ndb2 = Design.createDetachedDb()\r\ndb2 = odb.read_db(db2, 'odb/test/data/design.odb')\r\n\r\ndesign1.writeDb('db1.odb')\r\nodb.write_db(db2, 'db2.odb')\r\n```"}, {"assistant": "Done #4749 \r\n\r\nThe odb APIs should be fine."}]} +{"messages": [{"user": "Hello all,\r\n\r\nis there a way in the GUI to highlight all standard cells that belong to a given module within the hierarchy?"}, {"assistant": "You can use the 'Hierarchy Browser' from the 'Windows' menu. If you see \r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/979243d1-d259-41ed-b50f-7403f9fbffa6)\r\n\r\nclick it to the on the highlighting. An example:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/5e659e20-c91f-4a76-8c99-544abd423c63)\r\n"}, {"assistant": "Are you using ORFS? If so set SYNTH_HIERARCHICAL=1 in your config"}]} +{"messages": [{"user": "Hi,\r\n\r\nI am using TritonPart in a personal project and my application closely resembled the following application mentioned in the TritonPart paper. [Here](https://vlsicad.ucsd.edu/Publications/Conferences/401/c401.pdf):\r\n\r\n> In other words, the standard balance constraint must be satisfied\r\nalong each dimension of weights. A practical example of this\r\nconstraint is partitioning a netlist across multiple FPGAs, where\r\nresources such as flip-flops (FFs), digital signal processing blocks\r\n(DSPs), and look-up tables (LUTs) are all limited. This is a hard\r\nconstraint\r\n\r\n1. In my application, I had three different types of vertices, denoted as t1, t2, and t3. My main concern was to ensure that no more than four crossings were allowed between any partitions. I believe to achieve this functionality; I need to set `-balance_constraint` to `3`.\r\n2. In each individual partition or block, I could only have a maximum of `four t1 cells, 16 t2 cells, and four t3 cells`. This was the maximum condition. However, I was unsure about how to implement this constraint. I have read the OpenROAD paper and documentation, but any related reference would be very helpful for my application.\r\n\r\nThank you, let me know if you need any more information.\r\n"}, {"assistant": "Please check https://github.com/The-OpenROAD-Project/OpenROAD/issues/4724"}]} +{"messages": [{"user": "With latest OpenROAD GUI, Leaf Instance > Combinational not showing any instance list.\r\n![Missing_leaf_instance_list](https://github.com/The-OpenROAD-Project/OpenROAD/assets/85787913/825e771d-7eef-42c7-9779-89bb23263e48)\r\n\r\nBut previous OpenROAD had this feature to trace all leaf instance list.\r\n![with_instance_list](https://github.com/The-OpenROAD-Project/OpenROAD/assets/85787913/4253f57c-7360-4978-babf-f773ecc310b7)\r\n\r\nIs that feature moved under some other options or removed it?\r\n\r\n@maliberty @vvbandeira "}, {"assistant": "The listing of instances was removed as for large designs it becomes far too slow and isn't that helpful. See https://github.com/The-OpenROAD-Project/OpenROAD/issues/4629 What is your use case?"}]} +{"messages": [{"user": "I'm seeing high congestion at global place for a design using asap7 libraries on Openroad. I tried using cell padding with 8 cell sites on the left and right. It helped reduce the congestion a bit, but not enough. I have set a max fanout and tightened the max capacitance in addition to the previous changes, and congestion is still there. I also changed the flow to congestion-driven instead of timing-driven and used the routability check overflow option but still see the congestion although it has decreased slightly. Any suggestions?\u00a0"}, {"assistant": "Can you provide a test case or at least some images of the problem?"}, {"user": "The RTL was generated through [OpenASIP ](http://openasip.org/)\r\nBy testcase do you mean odb file ? If not, how do I generate one ?\r\n\"new_Cong\"\r\nThe image shows estimated congestion and is captured after detailed placement. \r\n"}, {"assistant": "`make global_place_issue` should package the test case. Do not post if you are using any confidential data."}, {"user": "Here is the testcase : https://tuni-my.sharepoint.com/:u:/g/personal/pooja_mudbhatkal_tuni_fi/EVDGc1VOxIZNhEfmDVLf1JcB56kh2ipprLFusncKTGhAWA?e=NnEMJh \r\nPlease let me know if you have access issues"}, {"assistant": "This design does have an very unusual distribution of cell types. I think you will need to enlarge the block and lower the placement density to compensate for it.\r\n\r\n@gudeh this could be an interesting case to test your routability improvements on."}, {"assistant": "Btw, what sort of block is this?"}, {"assistant": "Hi @Mudbhatkal, I noticed from the log files in the make issue you uploaded that you used yosys version 0.33. Have you tried other Yosys versions? ORFS is currently using 0.38 from a recent update. If you have a local installation of ORFS you can use the 'build_openroad.sh' script. I usually use the following: `./build_openroad.sh --local`.\r\n\r\nMaybe this would provide a different set of logic gates and a different routing scenario. For some reason I was not able to run Yosys on my end with your files."}, {"assistant": "Have you tried lowering PLACE_DENSITY as I suggested earlier?"}, {"assistant": "vliw cores I\u2019ve seen in the past had wide and deep muxes around the registers. If these are not isolated in a separate rtl hierarchy, synthesis tools tend to ignore mux levels and generate ao/oa spagetti netlists that no R&R tool can untangle.\r\nPhysical synthesis tools are supposed to be able to give you a better netlist, but since yosys isn\u2019t one of them, you\u2019ll have to rewrite the rtl of the muxes to get a P&R friendly netlist.\r\nPut each mux level in a separate rtl hierarchy and make sure that synthesis doesn\u2019t flatten them. Separate enables per level of muxing. You should be able to identify mux structures in your netlist.\r\nP&R tools are usually bad at visualizing cone connectivity, but OR has timing critically color coded cone viewing as part of the timing debug. Use it after placement to look at your muxes."}, {"user": "[big_tta_fixed.zip](https://github.com/The-OpenROAD-Project/OpenROAD/files/14486076/big_tta_fixed.zip)\r\nThis RTL has some fixes but I still see congestion issues. Also tried with synth_hierarchial set to 1. Attaching it here in case someone finds it useful."}]} +{"messages": [{"user": "I thought inverters were good at amplifying signals? So is an inverter + buffer on output superfluous?\r\n\r\nI'm not suggesting a change, I'm just trying to learn what is possible/common vs. what OpenROAD is doing.\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/65b87224-0bb8-497a-bf34-b89ca348d8c7)\r\n\r\nThe buffer is added in resizing.\r\n\r\n1. untar [resize.tar.gz](https://github.com/The-OpenROAD-Project/OpenROAD/files/14265925/resize.tar.gz)\r\n2. `./run-me-mock-array_Element-asap7-base.sh`\r\n3. Enter `report_checks -to io_lsbOuts_7`\r\n\r\n```\r\n$ ./run-me-mock-array_Element-asap7-base.sh \r\nOpenROAD v2.0-12176-g735d54b79 \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\nWarning: There are 7 input ports missing set_input_delay.\r\nWarning: There are 6 output ports missing set_output_delay.\r\nWarning: There is 1 unconstrained endpoint.\r\n\r\n==========================================================================\r\nresizer pre report_design_area\r\n--------------------------------------------------------------------------\r\nDesign area 105 u^2 6% utilization.\r\n\r\n==========================================================================\r\ninstance_count\r\n--------------------------------------------------------------------------\r\n902\r\n\r\n==========================================================================\r\npin_count\r\n--------------------------------------------------------------------------\r\n1299\r\n\r\nPerform port buffering...\r\n[INFO RSZ-0027] Inserted 257 input buffers.\r\n[INFO RSZ-0028] Inserted 264 output buffers.\r\nPerform buffer insertion...\r\n[INFO RSZ-0058] Using max wire length 162um.\r\n[INFO RSZ-0039] Resized 526 instances.\r\nRepair tie lo fanout...\r\nRepair tie hi fanout...\r\n\r\n==========================================================================\r\nreport_floating_nets\r\n--------------------------------------------------------------------------\r\nWarning: There are 7 input ports missing set_input_delay.\r\nWarning: There are 6 output ports missing set_output_delay.\r\nWarning: There is 1 unconstrained endpoint.\r\n\r\n==========================================================================\r\nresizer report_design_area\r\n--------------------------------------------------------------------------\r\nDesign area 159 u^2 9% utilization.\r\n\r\n==========================================================================\r\ninstance_count\r\n--------------------------------------------------------------------------\r\n1423\r\n\r\n==========================================================================\r\npin_count\r\n--------------------------------------------------------------------------\r\n2341\r\n\r\nopenroad> report_checks -to io_lsbOuts_7\r\nStartpoint: _755_ (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: io_lsbOuts_7 (output port clocked by clock_vir)\r\nPath Group: clock_vir\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (ideal)\r\n 0.00 0.00 ^ _755_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 40.03 40.03 v _755_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 11.28 51.31 ^ _435_/Y (INVx3_ASAP7_75t_R)\r\n 22.51 73.82 ^ output265/Y (BUFx4f_ASAP7_75t_R)\r\n 0.27 74.09 ^ io_lsbOuts_7 (out)\r\n 74.09 data arrival time\r\n\r\n 300.00 300.00 clock clock_vir (rise edge)\r\n 0.00 300.00 clock network delay (ideal)\r\n -20.00 280.00 clock uncertainty\r\n 0.00 280.00 clock reconvergence pessimism\r\n -60.00 220.00 output external delay\r\n 220.00 data required time\r\n---------------------------------------------------------\r\n 220.00 data required time\r\n -74.09 data arrival time\r\n---------------------------------------------------------\r\n 145.91 slack (MET)\r\n\r\n\r\nopenroad> \r\n```\r\n\r\n\r\nChecking that this buffer isn't there before resizing:\r\n\r\n```\r\n$ . vars-mock-array_Element-asap7-base.sh \r\n$ ODB_FILE=results/asap7/mock-array_Element/base/3_3_place_gp.odb openroad -no_init -gui scripts/gui.tcl\r\nOpenROAD v2.0-12176-g735d54b79 \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\nEstimating parasitics\r\n>>> report_checks -to io_lsbOuts_7\r\nStartpoint: _755_ (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: io_lsbOuts_7 (output port clocked by clock_vir)\r\nPath Group: clock_vir\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (ideal)\r\n 0.00 0.00 ^ _755_/CLK (DFFHQNx1_ASAP7_75t_R)\r\n 36.60 36.60 v _755_/QN (DFFHQNx1_ASAP7_75t_R)\r\n 17.65 54.25 ^ _435_/Y (INVx3_ASAP7_75t_R)\r\n 7.12 61.38 ^ io_lsbOuts_7 (out)\r\n 61.38 data arrival time\r\n\r\n 300.00 300.00 clock clock_vir (rise edge)\r\n 0.00 300.00 clock network delay (ideal)\r\n -20.00 280.00 clock uncertainty\r\n 0.00 280.00 clock reconvergence pessimism\r\n -60.00 220.00 output external delay\r\n 220.00 data required time\r\n---------------------------------------------------------\r\n 220.00 data required time\r\n -61.38 data arrival time\r\n---------------------------------------------------------\r\n 158.62 slack (MET)\r\n```\r\n"}, {"user": "There is an option not to buffer ports, but I don't see it used anywhere, nor documented. `buffer_ports` is documented.\r\n\r\n```\r\n$ DONT_BUFFER_PORTS=1 ./run-me-mock-array_Element-asap7-base.sh \r\nOpenROAD v2.0-12176-g735d54b79 \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\nWarning: There are 7 input ports missing set_input_delay.\r\nWarning: There are 6 output ports missing set_output_delay.\r\nWarning: There is 1 unconstrained endpoint.\r\n\r\n==========================================================================\r\nresizer pre report_design_area\r\n--------------------------------------------------------------------------\r\nDesign area 105 u^2 6% utilization.\r\n\r\n==========================================================================\r\ninstance_count\r\n--------------------------------------------------------------------------\r\n902\r\n\r\n==========================================================================\r\npin_count\r\n--------------------------------------------------------------------------\r\n1299\r\n\r\nPerform buffer insertion...\r\n[INFO RSZ-0058] Using max wire length 162um.\r\n[INFO RSZ-0039] Resized 521 instances.\r\nRepair tie lo fanout...\r\nRepair tie hi fanout...\r\n\r\n==========================================================================\r\nreport_floating_nets\r\n--------------------------------------------------------------------------\r\nWarning: There are 7 input ports missing set_input_delay.\r\nWarning: There are 6 output ports missing set_output_delay.\r\nWarning: There is 1 unconstrained endpoint.\r\n\r\n==========================================================================\r\nresizer report_design_area\r\n--------------------------------------------------------------------------\r\nDesign area 155 u^2 9% utilization.\r\n\r\n==========================================================================\r\ninstance_count\r\n--------------------------------------------------------------------------\r\n902\r\n\r\n==========================================================================\r\npin_count\r\n--------------------------------------------------------------------------\r\n1299\r\n\r\nopenroad> report_checks -to io_lsbOuts_7\r\nStartpoint: _755_ (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: io_lsbOuts_7 (output port clocked by clock_vir)\r\nPath Group: clock_vir\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (ideal)\r\n 0.00 0.00 ^ _755_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 48.38 48.38 v _755_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 12.54 60.92 ^ _435_/Y (CKINVDCx8_ASAP7_75t_R)\r\n 6.63 67.55 ^ io_lsbOuts_7 (out)\r\n 67.55 data arrival time\r\n\r\n 300.00 300.00 clock clock_vir (rise edge)\r\n 0.00 300.00 clock network delay (ideal)\r\n -20.00 280.00 clock uncertainty\r\n 0.00 280.00 clock reconvergence pessimism\r\n -60.00 220.00 output external delay\r\n 220.00 data required time\r\n---------------------------------------------------------\r\n 220.00 data required time\r\n -67.55 data arrival time\r\n---------------------------------------------------------\r\n 152.45 slack (MET)\r\n\r\n\r\nopenroad> \r\n```\r\n"}, {"assistant": "That option comes from https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1431 and I don't really remember why we needed it at all. Tom said \"I think that the need for this variable should go away when we improve the automatic code.\" but I don't know what improvement was needed and there is no issue referenced. I don't think it is a good option to have. Do you remember more?"}]} +{"messages": [{"user": "I installed openroad on RHEL8 using the documentation from GitHub. After launching openroad -gui, I noticed that it mentions QtCharts is not installed. So I built and compiled it (from source qtcharts-everywhere-src-5.15.0.zip), and and it appears to have installed in /usr/include/qt5/QtCharts ..but when I launch openroad -gui again , it STILL says \"QtCharts not installed\" ..(see attachment) Any ideas on what to do ?? This doesn't appear to be very straightforward\r\n\r\n![openroad_QtCharts_missing](https://github.com/The-OpenROAD-Project/OpenROAD/assets/47336735/70f5288c-1aa8-447b-ac35-0c0cfb27bee0)\r\n"}, {"assistant": "Cmake does some caching so I suggest removing your build directory and re-running cmake to see if it then finds it."}, {"assistant": "Is the rest of Qt installed in the same area?"}]} +{"messages": [{"user": "I'm building MegaBoom and global placement takes hours. Is this a known issue where it is known what is needed to mitigate the slowdown?\r\n\r\n```\r\n[NesterovSolve] Iter: 460 overflow: 0.205059 HPWL: 19290468260\r\n[INFO GPL-0100] worst slack -3.76e-07\r\n[INFO GPL-0103] Weighted 176557 nets.\r\n[INFO GPL-0075] Routability numCall: 1 inflationIterCnt: 1 bloatIterCnt: 0\r\n[long pause]\r\n```\r\n\r\nSuspend and resume a few times shows this stack-trace:\r\n\r\n```\r\ngrt::GlobalRouter::mergeSegments(std::vector> const&, std::vector>&) (@grt::GlobalRouter::mergeSegments(std::vector> const&, std::vector>&):296)\r\ngrt::GlobalRouter::findRouting(std::vector>&, int, int) (@grt::GlobalRouter::findRouting(std::vector>&, int, int):140)\r\ngrt::GlobalRouter::globalRoute(bool, bool, bool) (@grt::GlobalRouter::globalRoute(bool, bool, bool):121)\r\ngpl::RouteBase::getGlobalRouterResult() (@gpl::RouteBase::getGlobalRouterResult():22)\r\ngpl::RouteBase::routability() (@gpl::RouteBase::routability():54)\r\ngpl::NesterovPlace::doNesterovPlace(int) (@gpl::NesterovPlace::doNesterovPlace(int):924)\r\n_wrap_replace_nesterov_place_cmd (@_wrap_replace_nesterov_place_cmd:17)\r\nTclNRRunCallbacks (@TclNRRunCallbacks:37)\r\n___lldb_unnamed_symbol1497 (@___lldb_unnamed_symbol1497:339)\r\nTcl_EvalEx (@Tcl_EvalEx:9)\r\nTcl_Eval (@Tcl_Eval:11)\r\nsta::sourceTclFile(char const*, bool, bool, Tcl_Interp*) (@sta::sourceTclFile(char const*, bool, bool, Tcl_Interp*):32)\r\nord::tclAppInit(Tcl_Interp*) (@ord::tclAppInit(Tcl_Interp*):131)\r\nTcl_MainEx (@Tcl_MainEx:111)\r\nmain (@main:727)\r\n__libc_start_call_main (@__libc_start_call_main:29)\r\n__libc_start_main_impl (@__libc_start_main@@GLIBC_2.34:44)\r\n_start (@_start:15)\r\n```\r\n\r\nA tiny method...\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/88404674f2a35c7fd2d3bea51b4088fde81f0586/src/grt/src/GlobalRouter.cpp#L2126\r\n\r\nNaiively rewriting to avoid O(n^2) https://github.com/The-OpenROAD-Project/OpenROAD/pull/4627\r\n"}, {"assistant": "> Is this a known issue where it is known what is needed to mitigate the slowdown?\r\n\r\nRoutability, which calls grt, can take a while but I don't know of a specific mitigation. You might try vtune for performance profiling."}]} +{"messages": [{"user": "Once I have updated the clock tree viewer, how do I deselect the clock tree(orange and red) that is now hiding everything in the chip view?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/3abf5fae-24ca-4a84-b00d-d7d30d74ab5a)\r\n\r\n\r\n"}, {"assistant": "Right click in the widget and you can turn off the display."}]} +{"messages": [{"user": "Hi,\r\n\r\nI am trying to save my LEF and Liberty files to .odb file using write_db to speed up the library reading time. \r\nBut it seems like only LEF files can be saved to the database. Is there any way to save the lib files as well?\r\n\r\nThanks!"}, {"assistant": "Not currently. "}]} +{"messages": [{"user": "Using https://github.com/The-OpenROAD-Project/OpenROAD/pull/4615 I see that the gcell data takes a lot of space in the .odb file. The current structure is:\r\n\r\n```\r\n struct GCellData\r\n {\r\n uint horizontal_usage = 0;\r\n uint vertical_usage = 0;\r\n uint up_usage = 0;\r\n uint horizontal_capacity = 0;\r\n uint vertical_capacity = 0;\r\n uint up_capacity = 0;\r\n uint horizontal_blockage = 0;\r\n uint vertical_blockage = 0;\r\n uint up_blockage = 0;\r\n };\r\n```\r\n\r\nThis is 9 4-byte ints which is a lot of space. A large design can easily have a matrix with 10M entries for each of 10 routing layers.\r\n\r\n Oddly we don't actually write out the blockage fields:\r\n\r\n```\r\ndbOStream& operator<<(dbOStream& stream, const dbGCellGrid::GCellData& obj)\r\n{\r\n stream << obj.horizontal_usage;\r\n stream << obj.vertical_usage;\r\n stream << obj.up_usage;\r\n stream << obj.horizontal_capacity;\r\n stream << obj.vertical_capacity;\r\n stream << obj.up_capacity;\r\n return stream;\r\n}\r\n```\r\n\r\nwhich seems like a bug. So the on disk size is a smaller than the in memory size. I think there are two ways to reduce the size:\r\n\r\n1. Use uint8_5 (1-byte) as you generally have ~15 tracks per gcell so four bytes is wasteful\r\n2. Reduce horizontal/vertical to just preferred. There is no need to store the non-preferred direction values as the global router will never route in the non-preferred direction.\r\n\r\nA third possibility is to drop 'blockage'. This is only used in one spot in gpl's routability. Can we just reduce the capacity accordingly and check for low capacity gcells instead? (@eder-matheus ?)"}, {"user": "In bp_single/gf12 the gcell data is 2011.7MB of 3615.1MB = 55% of the total size"}]} +{"messages": [{"user": "Is there any way to route logical constant 1 & 0 to Vdd & Vss power rails instead of using tie cells? Right now I'm using a cell with short circuit between output and power pins, which is really bad in terms of area."}, {"assistant": "No there is no facility for that. The supply rails are often noisy and the tie cell provides a more stable output. What is the issue with using a tie cell?"}, {"assistant": "Constant propagation should be able to remove all constants unless they're connected to ram/rom/pad/analog macro's, no ?\r\nWhich synthesis tool has been used to create the netlist ?\r\nCan yosys do constant propagation ? If so, is it on by default or does it need to be enabled ?"}]} +{"messages": [{"user": "If I read this correctly, then the run of 1st iteration elapsed(wallclock) time was 10 hours, 46 minutes and 46 seconds. \r\n\r\n4h47mn was spent up to and including completing 100%.\r\n\r\nQ: what happens in the 6 hours between 100% and fully completing 1st iteration?\r\n\r\nUsually very little time passes at this stage, is it expected that a lot of time can pass here?\r\n\r\nThis run is from thethe MegaBoom design I'm working on.\r\n\r\n\r\n```\r\n[INFO DRT-0195] Start 1st optimization iteration.\r\n Completing 10% with 1076101 violations.\r\n elapsed time = 00:24:49, memory = 60012.99 (MB).\r\n Completing 20% with 873473 violations.\r\n elapsed time = 01:04:14, memory = 60329.16 (MB).\r\n Completing 30% with 805447 violations.\r\n elapsed time = 01:20:27, memory = 59897.90 (MB).\r\n Completing 40% with 667422 violations.\r\n elapsed time = 01:58:03, memory = 60366.77 (MB).\r\n Completing 50% with 559526 violations.\r\n elapsed time = 02:24:50, memory = 59460.91 (MB).\r\n Completing 60% with 474370 violations.\r\n elapsed time = 02:49:13, memory = 60126.98 (MB).\r\n Completing 70% with 320252 violations.\r\n elapsed time = 03:28:15, memory = 60227.41 (MB).\r\n Completing 80% with 270693 violations.\r\n elapsed time = 03:44:28, memory = 59310.96 (MB).\r\n Completing 90% with 163044 violations.\r\n elapsed time = 04:21:50, memory = 60829.58 (MB).\r\n Completing 100% with 79991 violations.\r\n elapsed time = 04:47:55, memory = 59083.30 (MB).\r\n[INFO DRT-0199] Number of violations = 87967.\r\nViol/Layer M1 M2 V2 M3 V3 M4 V4 M5 V5 M6 V6 M7 V7 M8\r\nCorner Spacing 0 13 0 0 0 1 0 0 0 0 0 0 0 0\r\nCut Spacing 0 0 0 0 0 0 0 0 0 0 0 0 32 0\r\nCutSpcTbl 0 0 0 0 870 0 714 0 45 0 79 0 0 0\r\nEOL 0 11018 0 243 0 100 0 47 0 29 0 42 0 0\r\nMetal Spacing 1896 2198 0 1705 0 126 0 48 0 27 0 57 0 54\r\nMin Step 0 0 0 0 0 0 0 0 0 0 0 0 0 255\r\nNS Metal 0 0 0 0 0 0 0 0 0 0 0 1 0 27\r\nRecheck 123 4568 0 3242 0 351 0 1 0 0 0 0 0 0\r\nRect Only 0 0 0 0 0 0 0 0 0 0 0 83 0 0\r\nShort 11 6274 19 681 4 157 1 110 1 132 24 5 14 15\r\neolKeepOut 0 50499 0 971 0 615 0 169 0 87 0 183 0 0\r\n[INFO DRT-0267] cpu time = 77:23:47, elapsed time = 10:14:46, memory = 56657.25 (MB), peak = 61275.99 (MB)\r\n```"}, {"user": "I attached to the process during the \"mystery processing\", paused and looked at stack traces:\r\n\r\n```\r\n___lldb_unnamed_symbol837 (@___lldb_unnamed_symbol837:56)\r\n___lldb_unnamed_symbol816 (@___lldb_unnamed_symbol816:16)\r\nfr::FlexDRConnectivityChecker::check(int) (@fr::FlexDRConnectivityChecker::check(int):1143)\r\nfr::FlexDR::searchRepair(fr::FlexDR::SearchRepairArgs const&) (@fr::FlexDR::searchRepair(fr::FlexDR::SearchRepairArgs const&):1714)\r\nfr::FlexDR::main() (@fr::FlexDR::main():51)\r\ntriton_route::TritonRoute::main() (@triton_route::TritonRoute::main():175)\r\ndetailed_route_cmd(char const*, char const*, char const*, char const*, char const*, bool, int, char const*, char const*, int, double, char const*, char const*, int, bool, bool, bool, int, bool, char const*, int) (@detailed_route_cmd(char const*, char const*, char const*, char const*, char const*, bool, int, char const*, char const*, int, double, char const*, char const*, int, bool, bool, bool, int, bool, char const*, int):304)\r\n_wrap_detailed_route_cmd (@_wrap_detailed_route_cmd:263)\r\nTclNRRunCallbacks (@TclNRRunCallbacks:37)\r\n___lldb_unnamed_symbol1497 (@___lldb_unnamed_symbol1497:339)\r\nTcl_EvalEx (@Tcl_EvalEx:9)\r\nTcl_Eval (@Tcl_Eval:11)\r\nsta::sourceTclFile(char const*, bool, bool, Tcl_Interp*) (@sta::sourceTclFile(char const*, bool, bool, Tcl_Interp*):32)\r\nord::tclAppInit(Tcl_Interp*) (@ord::tclAppInit(Tcl_Interp*):131)\r\nTcl_MainEx (@Tcl_MainEx:111)\r\nmain (@main:727)\r\n__libc_start_call_main (@__libc_start_call_main:29)\r\n__libc_start_main_impl (@__libc_start_main@@GLIBC_2.34:44)\r\n_start (@_start:15)\r\n```\r\n\r\nThen there are a number of, what I believe are, paused threads.\r\n\r\n```\r\nfr::FlexDRConnectivityChecker::astar(fr::frNet const*, std::vector>&, std::vector>&, std::map, std::set, std::allocator>, std::less>, std::allocator const, std::set, std::allocator>>>> const&, std::vector> const&, int, int) (@fr::FlexDRConnectivityChecker::astar(fr::frNet const*, std::vector>&, std::vector>&, std::map, std::set, std::allocator>, std::less>, std::allocator const, std::set, std::allocator>>>> const&, std::vector> const&, int, int):645)\r\nfr::FlexDRConnectivityChecker::check(int) (._omp_fn.1) (@fr::FlexDRConnectivityChecker::check(int) (._omp_fn.1):162)\r\n___lldb_unnamed_symbol813 (@___lldb_unnamed_symbol813:87)\r\nstart_thread (@start_thread:164)\r\n__clone3 (@__clone3:19)\r\n```\r\n\r\nHmm.... I wonder if it is stuck, I'll let it run today. In \"top\" there's no openroad binary that is using CPU... In the example above, it did continue after the long \"mystery processing\" stage."}]} +{"messages": [{"user": "This is just an observation that puzzled me for a bit that I thought I'd share.\r\n\r\nFirst I thought something was wrong, but having thought about it for a bit, it's obvious: the endpoint slack diagram counts only endpoints, whereas the timing report has all the start and end point combinations. This means that the timing report has many more rows than there are endpoints in the slack diagram.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/b44d56b6-1c12-45e7-a06f-f3238dbb420d)\r\n\r\nAt least 9999(maximum in GUI) rows here:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/dad6dfa1-8350-460e-9976-341d365f8d85)\r\n\r\nOf course this is nothing new, there is a feature to display only one row per endpoint:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/fec8e633-03df-4aaf-82f9-a67802050942)\r\n\r\nHmm... is that the worst slack per end-point?\r\n"}, {"assistant": "Yes it should be the worst slack path to that endpoint. Total paths is exponential in design size."}]} +{"messages": [{"user": "Why are these used in combination?\r\n\r\nWhat happens if I don't?\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/discussions/4529 has an fMax of 125, which isn't enormously impressive. There are 79 levels of logic in the longest path, which indicates to me that something isn't being optimized in synthesis...\r\n\r\nBOOMv documents that it relies heavily on [register retiming](https://docs.boom-core.org/en/latest/sections/physical-realization.html#physical-realization) and I've also observed that it needs [register cloning](https://github.com/The-OpenROAD-Project/OpenROAD/discussions/4522#discussioncomment-8106429) for synchronous reset.\r\n\r\nHence, I want to try disabling hierarchical synthesis on MegaBoom, but given the long turnaround times, 40 hours, it would be nice to know a little bit about what I'm doing and what I should expect..."}, {"assistant": "I believe that RTLMP requires hierarchy in the netlist to work at all. If the netlist is flat, RTLMP won't work."}, {"user": "> At least no public tests. We would have to run the private ones as well.\r\n\r\n"}, {"assistant": "@oharboe the retiming doesn't work in Yosys (and not in OpenROAD), so that is going to be a limitation. We ran into this as well with something else from the Chisel team folks and there isn't a good solution at the moment "}]} +{"messages": [{"user": "Based on https://github.com/The-OpenROAD-Project/megaboom/commit/a8e07eab7d4848057ac8e7993d5fee93b3d8653d\r\n\r\nAfter understanding the design better and a best effort to [generating Verilog](https://groups.google.com/g/chipyard/c/XPmGRK_CtZA) for the core with an asynchronous FIFO from the core to the surrounding memory system and buses such that the depth of the clock tree in the core isn't such an enormous issue + I have a report from yosys to list all RAMs and ROMs in the design such that I can be sure that I mock all ROM/RAMs larger than 1024 bits, it was time to try [MegaBoom flattened](https://github.com/The-OpenROAD-Project/megaboom/blob/1cce55c772d823ebca0bf8368f1d363a2e546044/BUILD.bazel#L1153)...\r\n\r\nThe core here is MegaBoom up to and including L1 data/instruction cache. L2 & peripherals are excluded.\r\n\r\nSynthesis times are tolerable and not that far off non-flattened where I break out some macros for the larger parts of the core: ICache, DCache, branch predictor and floating point pipeline.\r\n\r\n```\r\nLog Elapsed seconds\r\n1_1_yosys 4057\r\n1_1_yosys_hier_report 4063\r\nTotal 8120\r\n```\r\n\r\nFrom `make gui_synth`, I can see that the core is ca. 98% of the design measured in instances. The rest are buses and asynchronous bridges.\r\n\r\n`make memory` reports the table of roms and rams in the design. This report uses yosys and takes ca. 5 minutes to run, very acceptable. It would be *great* if synthesis could be run without optimizations quicky and then to view the results in the hierarchy view...\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/05c5ded4-19e6-417f-ba74-31c5c64aa6ea)\r\n\r\nThe area of the instances is 250000um^2. I have been having trouble with 30% placement density, so I'm going to try 20% placement density. What is the relationship with CORE_UTILIZATION and placement density here...?\r\n\r\nMake that CORE_UTILIZATION=15\r\n\r\nsqrt(2500000/0.15) => 1300um * 1300um\r\n\r\nMacro placement and estimated routing congestion for 2000um x 2000um. The macros seem to be pushed out to the corners, let's see how that works out in placement and routing...\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/03f9e101-6a6b-4362-a4f9-f93e142c11dc)\r\n\r\nRouting congestion in `make gui_place`. Why is the empty area yellow? Is power considered part of routing congestion?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/cdef90ba-9366-4046-b86d-7cac7a1d476f)\r\n\r\nEstimated routing congestion RUDY. I guess RUDY excludes power?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/203b5a86-3cd4-4c04-bf80-a0b204e98692)\r\n\r\nClock tree looks good:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/2363f35c-d12e-44b4-bbbb-5773d25b3426)\r\n\r\n\r\nGlobal routing has taken 40000s so far, but it seems to have succeeded:\r\n\r\n```\r\n[INFO GRT-0101] Running extra iterations to remove overflow.\r\n[INFO GRT-0197] Via related to pin nodes: 10765900\r\n[INFO GRT-0198] Via related Steiner nodes: 1028317\r\n[INFO GRT-0199] Via filling finished.\r\n[INFO GRT-0111] Final number of vias: 14831285\r\n[INFO GRT-0112] Final usage 3D: 118911097\r\n\r\n[INFO GRT-0096] Final congestion report:\r\nLayer Resource Demand Usage (%) Max H / Max V / Total Overflow\r\n---------------------------------------------------------------------------------------\r\nM1 0 0 0.00% 0 / 0 / 0\r\nM2 65189536 19765924 30.32% 0 / 0 / 0\r\nM3 88394705 29035790 32.85% 0 / 0 / 0\r\nM4 65419606 14163760 21.65% 0 / 0 / 0\r\nM5 58863583 8001905 13.59% 0 / 0 / 0\r\nM6 42524107 2674369 6.29% 0 / 0 / 0\r\nM7 52346733 775494 1.48% 0 / 0 / 0\r\n---------------------------------------------------------------------------------------\r\nTotal 372738270 74417242 19.97% 0 / 0 / 0\r\n\r\n[INFO GRT-0018] Total wirelength: 44969527 um\r\n[INFO GRT-0014] Routed nets: 2043518\r\nWarning: There are 10 input ports missing set_input_delay.\r\nWarning: There are 7 output ports missing set_output_delay.\r\nWarning: There are 323 unclocked register/latch pins.\r\nWarning: There are 4128 unconstrained endpoints.\r\n\r\n==========================================================================\r\nglobal route pre repair design report_design_area\r\n--------------------------------------------------------------------------\r\nDesign area 523197 u^2 13% utilization.\r\nPerform buffer insertion...\r\n[INFO RSZ-0058] Using max wire length 162um.\r\n```\r\n\r\n\r\nGlobal route heat map:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/504a1b08-d095-41f1-a8be-6392437eeaf5)\r\n\r\n\r\nDetailed routing without power:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/97c26702-6d81-472a-a79d-e15eb6cf1a9e)\r\n\r\n\r\nRegarding the long global routing times, I set SKIP_INCREMENTAL_REPAIR=1 in detailed routing, whereas it is a global routing argument. I believe that will take care of the pathologically slow global routing...\r\n\r\n```\r\n- 'route': ['SKIP_INCREMENTAL_REPAIR=1'],\r\n+ 'grt': ['SKIP_INCREMENTAL_REPAIR=1']\r\n```\r\n\r\n\r\n```\r\n>>> report_checks -path_delay max\r\nStartpoint: system/prci_ctrl_domain/_853_\r\n (rising edge-triggered flip-flop clocked by clock_uncore)\r\nEndpoint: system/_185_ (recovery check against rising-edge clock clock_uncore)\r\nPath Group: asynchronous\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock_uncore (rise edge)\r\n1973.50 1973.50 clock network delay (propagated)\r\n 0.00 1973.50 ^ system/prci_ctrl_domain/_853_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 87.72 2061.22 v system/prci_ctrl_domain/_853_/QN (DFFASRHQNx1_ASAP7_75t_R)\r\n 41.86 2103.08 v load_slew185637/Y (BUFx16f_ASAP7_75t_R)\r\n 37.04 2140.12 v max_cap185634/Y (BUFx16f_ASAP7_75t_R)\r\n 36.83 2176.95 v wire185631/Y (BUFx16f_ASAP7_75t_R)\r\n 41.48 2218.44 v wire185630/Y (BUFx16f_ASAP7_75t_R)\r\n 47.39 2265.83 v max_length185629/Y (BUFx16f_ASAP7_75t_R)\r\n 39.69 2305.52 v wire185628/Y (BUFx16f_ASAP7_75t_R)\r\n 81.35 2386.87 v max_length185627/Y (BUFx16f_ASAP7_75t_R)\r\n 29.27 2416.13 v load_slew185625/Y (BUFx16f_ASAP7_75t_R)\r\n 52.11 2468.25 v load_slew185624/Y (BUFx12f_ASAP7_75t_R)\r\n 43.24 2511.49 v load_slew185618/Y (BUFx16f_ASAP7_75t_R)\r\n 50.84 2562.32 v load_slew185615/Y (BUFx16f_ASAP7_75t_R)\r\n 34.35 2596.68 v load_slew185559/Y (BUFx16f_ASAP7_75t_R)\r\n 34.56 2631.24 v load_slew185558/Y (BUFx16f_ASAP7_75t_R)\r\n 26.61 2657.85 v load_slew185557/Y (BUFx16f_ASAP7_75t_R)\r\n 46.26 2704.11 v load_slew185556/Y (BUFx16f_ASAP7_75t_R)\r\n 51.34 2755.46 v max_length185555/Y (BUFx12f_ASAP7_75t_R)\r\n 41.44 2796.90 v wire185553/Y (BUFx16f_ASAP7_75t_R)\r\n 51.64 2848.53 v load_slew185552/Y (BUFx16f_ASAP7_75t_R)\r\n 34.46 2882.99 v wire185550/Y (BUFx16f_ASAP7_75t_R)\r\n 51.12 2934.11 v wire185547/Y (BUFx16f_ASAP7_75t_R)\r\n 64.89 2999.00 v load_slew185546/Y (BUFx16f_ASAP7_75t_R)\r\n 37.84 3036.83 v wire185534/Y (BUFx16f_ASAP7_75t_R)\r\n 88.57 3125.41 v wire185533/Y (BUFx3_ASAP7_75t_R)\r\n 17.20 3142.60 v wire23908/Y (BUFx16f_ASAP7_75t_R)\r\n 103.84 3246.44 v wire185532/Y (BUFx16f_ASAP7_75t_R)\r\n 53.90 3300.35 v load_slew185531/Y (BUFx16f_ASAP7_75t_R)\r\n 35.37 3335.71 v load_slew185522/Y (BUFx16f_ASAP7_75t_R)\r\n 31.13 3366.84 v load_slew185507/Y (BUFx16f_ASAP7_75t_R)\r\n 32.21 3399.06 v wire185505/Y (BUFx16f_ASAP7_75t_R)\r\n 37.17 3436.23 v load_slew185504/Y (BUFx16f_ASAP7_75t_R)\r\n 25.45 3461.69 v load_slew185494/Y (BUFx16f_ASAP7_75t_R)\r\n 25.36 3487.04 v wire185486/Y (BUFx16f_ASAP7_75t_R)\r\n 47.14 3534.18 v wire185485/Y (BUFx16f_ASAP7_75t_R)\r\n 24.87 3559.05 v max_cap185484/Y (BUFx16f_ASAP7_75t_R)\r\n 27.89 3586.94 v wire185483/Y (BUFx3_ASAP7_75t_R)\r\n 16.61 3603.56 v wire19831/Y (BUFx16f_ASAP7_75t_R)\r\n 105.13 3708.69 v wire185481/Y (BUFx3_ASAP7_75t_R)\r\n 18.09 3726.78 v wire19408/Y (BUFx16f_ASAP7_75t_R)\r\n 112.70 3839.48 ^ system/_107_/Y (INVx1_ASAP7_75t_R)\r\n 0.03 3839.51 ^ system/_185_/SETN (DFFASRHQNx1_ASAP7_75t_R)\r\n 3839.51 data arrival time\r\n\r\n8500.00 8500.00 clock clock_uncore (rise edge)\r\n1969.03 10469.03 clock network delay (propagated)\r\n -10.00 10459.03 clock uncertainty\r\n 0.00 10459.03 clock reconvergence pessimism\r\n 10459.03 ^ system/_185_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 0.82 10459.85 library recovery time\r\n 10459.85 data required time\r\n---------------------------------------------------------\r\n 10459.85 data required time\r\n -3839.51 data arrival time\r\n---------------------------------------------------------\r\n 6620.34 slack (MET)\r\n\r\n\r\nStartpoint: _32_ (negative level-sensitive latch clocked by clock_uncore)\r\nEndpoint: _10_ (rising clock gating-check end-point clocked by clock_uncore)\r\nPath Group: gated clock\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n4250.00 4250.00 clock clock_uncore (fall edge)\r\n2156.12 6406.12 clock network delay (propagated)\r\n 0.00 6406.12 v _32_/CLK (DLLx1_ASAP7_75t_R)\r\n 32.10 6438.22 v _32_/Q (DLLx1_ASAP7_75t_R)\r\n 0.01 6438.23 v _10_/B (AND2x4_ASAP7_75t_R)\r\n 6438.23 data arrival time\r\n\r\n8500.00 8500.00 clock clock_uncore (rise edge)\r\n1955.45 10455.45 clock network delay (propagated)\r\n -10.00 10445.45 clock uncertainty\r\n 0.00 10445.45 clock reconvergence pessimism\r\n 10445.45 ^ _10_/A (AND2x4_ASAP7_75t_R)\r\n 0.00 10445.45 clock gating setup time\r\n 10445.45 data required time\r\n---------------------------------------------------------\r\n 10445.45 data required time\r\n -6438.23 data arrival time\r\n---------------------------------------------------------\r\n 4007.22 slack (MET)\r\n\r\n\r\nStartpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100862_\r\n (rising edge-triggered flip-flop clocked by clock_uncore)\r\nEndpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_719555_\r\n (rising edge-triggered flip-flop clocked by clock_uncore)\r\nPath Group: clock_uncore\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock_uncore (rise edge)\r\n1977.51 1977.51 clock network delay (propagated)\r\n 0.00 1977.51 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100862_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 97.74 2075.25 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100862_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 26.79 2102.04 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055781_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 123.43 2225.47 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100818_/CON (HAxp5_ASAP7_75t_R)\r\n 36.21 2261.68 ^ wire155277/Y (BUFx12f_ASAP7_75t_R)\r\n 45.28 2306.96 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055932_/Y (NOR2x2_ASAP7_75t_R)\r\n 28.25 2335.21 v max_length142580/Y (BUFx16f_ASAP7_75t_R)\r\n 104.72 2439.93 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055933_/Y (NAND2x2_ASAP7_75t_R)\r\n 59.96 2499.89 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055934_/Y (OA22x2_ASAP7_75t_R)\r\n 36.00 2535.89 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055951_/Y (AND4x2_ASAP7_75t_R)\r\n 12.14 2548.03 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055963_/Y (NAND3x2_ASAP7_75t_R)\r\n 70.12 2618.15 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055964_/Y (AOI211x1_ASAP7_75t_R)\r\n 55.95 2674.10 ^ load_slew117489/Y (BUFx12f_ASAP7_75t_R)\r\n 53.80 2727.90 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056077_/Y (AND3x4_ASAP7_75t_R)\r\n 25.58 2753.48 ^ max_length114043/Y (BUFx16f_ASAP7_75t_R)\r\n 32.81 2786.29 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056130_/Y (AND2x6_ASAP7_75t_R)\r\n 14.23 2800.52 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056131_/Y (NAND2x1_ASAP7_75t_R)\r\n 15.55 2816.06 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056132_/Y (INVx1_ASAP7_75t_R)\r\n 16.14 2832.21 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09390_/Y (NAND2x2_ASAP7_75t_R)\r\n 28.51 2860.72 v wire99845/Y (BUFx16f_ASAP7_75t_R)\r\n 70.62 2931.33 v wire99844/Y (BUFx16f_ASAP7_75t_R)\r\n 56.99 2988.32 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09404_/Y (OAI21x1_ASAP7_75t_R)\r\n 11.35 2999.67 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09407_/Y (NAND2x1_ASAP7_75t_R)\r\n 44.90 3044.57 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09408_/Y (OR4x2_ASAP7_75t_R)\r\n 57.29 3101.86 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09409_/Y (OR5x2_ASAP7_75t_R)\r\n 39.18 3141.05 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_11025_/Y (NOR2x2_ASAP7_75t_R)\r\n 25.42 3166.47 ^ wire85735/Y (BUFx3_ASAP7_75t_R)\r\n 16.09 3182.56 ^ wire22108/Y (BUFx16f_ASAP7_75t_R)\r\n 96.00 3278.56 ^ max_length85734/Y (BUFx12f_ASAP7_75t_R)\r\n 59.41 3337.98 ^ wire85733/Y (BUFx3_ASAP7_75t_R)\r\n 15.95 3353.92 ^ wire21265/Y (BUFx16f_ASAP7_75t_R)\r\n 93.06 3446.99 ^ max_length85732/Y (BUFx16f_ASAP7_75t_R)\r\n 52.88 3499.86 ^ wire85731/Y (BUFx12f_ASAP7_75t_R)\r\n 61.48 3561.34 ^ wire85730/Y (BUFx12f_ASAP7_75t_R)\r\n 94.55 3655.89 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374889_/Y (AND3x4_ASAP7_75t_R)\r\n 93.17 3749.07 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374891_/Y (XNOR2x2_ASAP7_75t_R)\r\n 33.79 3782.85 v max_length80723/Y (BUFx16f_ASAP7_75t_R)\r\n 73.46 3856.31 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715616_/CON (HAxp5_ASAP7_75t_R)\r\n 16.66 3872.97 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374906_/Y (INVx4_ASAP7_75t_R)\r\n 24.46 3897.43 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715614_/CON (HAxp5_ASAP7_75t_R)\r\n 13.62 3911.05 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715583_/Y (INVx1_ASAP7_75t_R)\r\n 101.30 4012.35 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715612_/SN (HAxp5_ASAP7_75t_R)\r\n 45.01 4057.36 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384513_/Y (XNOR2x1_ASAP7_75t_R)\r\n 28.70 4086.05 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384518_/Y (AND5x2_ASAP7_75t_R)\r\n 31.22 4117.28 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09414_/Y (AO22x2_ASAP7_75t_R)\r\n 32.81 4150.08 v wire55436/Y (BUFx12f_ASAP7_75t_R)\r\n 66.68 4216.77 v wire55435/Y (BUFx12f_ASAP7_75t_R)\r\n 67.25 4284.01 v wire55434/Y (BUFx12f_ASAP7_75t_R)\r\n 66.32 4350.34 v wire55433/Y (BUFx12f_ASAP7_75t_R)\r\n 67.31 4417.65 v wire55432/Y (BUFx12f_ASAP7_75t_R)\r\n 71.71 4489.36 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09415_/Y (OR4x1_ASAP7_75t_R)\r\n 50.77 4540.13 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09416_/Y (OR5x2_ASAP7_75t_R)\r\n 50.72 4590.86 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09417_/Y (OR5x2_ASAP7_75t_R)\r\n 33.49 4624.35 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_11022_/Y (AOI22x1_ASAP7_75t_R)\r\n 26.99 4651.33 ^ load_slew51767/Y (BUFx16f_ASAP7_75t_R)\r\n 59.33 4710.67 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_11023_/Y (AND2x6_ASAP7_75t_R)\r\n 32.05 4742.72 ^ wire50793/Y (BUFx16f_ASAP7_75t_R)\r\n 70.46 4813.18 ^ wire50792/Y (BUFx16f_ASAP7_75t_R)\r\n 57.14 4870.32 ^ max_length50791/Y (BUFx12f_ASAP7_75t_R)\r\n 57.90 4928.22 ^ wire50790/Y (BUFx16f_ASAP7_75t_R)\r\n 89.00 5017.21 ^ wire50789/Y (BUFx16f_ASAP7_75t_R)\r\n 65.37 5082.59 ^ wire50788/Y (BUFx12f_ASAP7_75t_R)\r\n 62.25 5144.84 ^ wire50787/Y (BUFx12f_ASAP7_75t_R)\r\n 73.66 5218.50 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374879_/Y (AND2x2_ASAP7_75t_R)\r\n 30.04 5248.54 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374909_/Y (NAND2x2_ASAP7_75t_R)\r\n 75.54 5324.08 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374941_/Y (XNOR2x2_ASAP7_75t_R)\r\n 47.25 5371.33 v wire46725/Y (BUFx3_ASAP7_75t_R)\r\n 16.83 5388.16 v wire7813/Y (BUFx16f_ASAP7_75t_R)\r\n 77.75 5465.91 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715634_/CON (HAxp5_ASAP7_75t_R)\r\n 20.02 5485.92 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_374961_/Y (INVx4_ASAP7_75t_R)\r\n 27.92 5513.84 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715636_/CON (HAxp5_ASAP7_75t_R)\r\n 14.52 5528.36 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715578_/Y (INVx1_ASAP7_75t_R)\r\n 110.73 5639.08 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715638_/SN (HAxp5_ASAP7_75t_R)\r\n 46.55 5685.64 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384519_/Y (XNOR2x1_ASAP7_75t_R)\r\n 41.02 5726.65 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384524_/Y (AND5x2_ASAP7_75t_R)\r\n 63.15 5789.80 v wire30208/Y (BUFx12f_ASAP7_75t_R)\r\n 83.85 5873.65 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09398_/Y (AO221x2_ASAP7_75t_R)\r\n 31.18 5904.83 v wire29780/Y (BUFx12f_ASAP7_75t_R)\r\n 67.42 5972.25 v wire29779/Y (BUFx12f_ASAP7_75t_R)\r\n 66.73 6038.98 v wire29778/Y (BUFx12f_ASAP7_75t_R)\r\n 66.08 6105.06 v wire29777/Y (BUFx12f_ASAP7_75t_R)\r\n 99.39 6204.45 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09399_/Y (OR4x2_ASAP7_75t_R)\r\n 52.91 6257.36 v wire29446/Y (BUFx12f_ASAP7_75t_R)\r\n 74.94 6332.30 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09400_/Y (OR3x2_ASAP7_75t_R)\r\n 11.77 6344.06 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13817_/Y (NOR2x1_ASAP7_75t_R)\r\n 36.79 6380.86 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13818_/Y (AND3x4_ASAP7_75t_R)\r\n 22.16 6403.01 ^ wire29198/Y (BUFx3_ASAP7_75t_R)\r\n 16.12 6419.13 ^ wire4813/Y (BUFx16f_ASAP7_75t_R)\r\n 79.70 6498.83 ^ wire29197/Y (BUFx3_ASAP7_75t_R)\r\n 17.06 6515.89 ^ wire4798/Y (BUFx16f_ASAP7_75t_R)\r\n 110.37 6626.27 ^ wire29196/Y (BUFx3_ASAP7_75t_R)\r\n 17.81 6644.08 ^ wire4769/Y (BUFx16f_ASAP7_75t_R)\r\n 71.73 6715.81 ^ wire29195/Y (BUFx12f_ASAP7_75t_R)\r\n 63.73 6779.54 ^ wire29194/Y (BUFx16f_ASAP7_75t_R)\r\n 82.80 6862.34 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_380843_/Y (AND3x4_ASAP7_75t_R)\r\n 80.15 6942.49 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_380845_/Y (XNOR2x2_ASAP7_75t_R)\r\n 40.14 6982.63 v wire24381/Y (BUFx3_ASAP7_75t_R)\r\n 16.96 6999.59 v wire4637/Y (BUFx16f_ASAP7_75t_R)\r\n 169.90 7169.49 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715676_/CON (HAxp5_ASAP7_75t_R)\r\n 22.93 7192.41 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_380978_/Y (INVx5_ASAP7_75t_R)\r\n 39.12 7231.53 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715678_/CON (HAxp5_ASAP7_75t_R)\r\n 17.36 7248.89 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715581_/Y (INVx1_ASAP7_75t_R)\r\n 139.72 7388.61 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_715680_/SN (HAxp5_ASAP7_75t_R)\r\n 46.63 7435.24 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384526_/Y (XNOR2x1_ASAP7_75t_R)\r\n 43.35 7478.59 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_384530_/Y (AND5x2_ASAP7_75t_R)\r\n 21.89 7500.48 ^ wire14553/Y (BUFx16f_ASAP7_75t_R)\r\n 60.38 7560.86 ^ wire14552/Y (BUFx12f_ASAP7_75t_R)\r\n 78.29 7639.15 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09424_/Y (AO221x2_ASAP7_75t_R)\r\n 46.92 7686.07 ^ wire14505/Y (BUFx12f_ASAP7_75t_R)\r\n 61.68 7747.74 ^ wire14504/Y (BUFx12f_ASAP7_75t_R)\r\n 63.66 7811.41 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09425_/Y (OR4x2_ASAP7_75t_R)\r\n 18.88 7830.29 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09426_/Y (OA21x2_ASAP7_75t_R)\r\n 9.19 7839.48 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13964_/Y (NOR2x1_ASAP7_75t_R)\r\n 32.41 7871.89 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13965_/Y (AND3x4_ASAP7_75t_R)\r\n 21.83 7893.72 v wire14423/Y (BUFx3_ASAP7_75t_R)\r\n 16.60 7910.32 v wire2687/Y (BUFx16f_ASAP7_75t_R)\r\n 76.26 7986.58 v wire14422/Y (BUFx3_ASAP7_75t_R)\r\n 17.63 8004.21 v wire2673/Y (BUFx16f_ASAP7_75t_R)\r\n 92.08 8096.29 v max_length14421/Y (BUFx16f_ASAP7_75t_R)\r\n 48.26 8144.55 v wire14420/Y (BUFx12f_ASAP7_75t_R)\r\n 65.64 8210.20 v wire14419/Y (BUFx12f_ASAP7_75t_R)\r\n 78.20 8288.39 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_462481_/Y (AND2x2_ASAP7_75t_R)\r\n 32.72 8321.11 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_462482_/Y (NAND2x2_ASAP7_75t_R)\r\n 51.65 8372.77 ^ wire13868/Y (BUFx16f_ASAP7_75t_R)\r\n 93.74 8466.51 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_463033_/Y (OR2x6_ASAP7_75t_R)\r\n 66.52 8533.02 ^ wire13185/Y (BUFx16f_ASAP7_75t_R)\r\n 125.00 8658.02 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_469024_/Y (NOR2x2_ASAP7_75t_R)\r\n 73.88 8731.90 v wire7777/Y (BUFx16f_ASAP7_75t_R)\r\n 117.54 8849.44 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_477305_/Y (OR3x4_ASAP7_75t_R)\r\n 46.53 8895.97 v wire2121/Y (BUFx3_ASAP7_75t_R)\r\n 16.26 8912.24 v wire1767/Y (BUFx16f_ASAP7_75t_R)\r\n 100.49 9012.73 v max_length2120/Y (BUFx16f_ASAP7_75t_R)\r\n 62.86 9075.59 v max_length2119/Y (BUFx16f_ASAP7_75t_R)\r\n 21.06 9096.65 v wire2118/Y (BUFx16f_ASAP7_75t_R)\r\n 76.88 9173.53 v max_length2117/Y (BUFx16f_ASAP7_75t_R)\r\n 36.80 9210.33 v wire2116/Y (BUFx16f_ASAP7_75t_R)\r\n 83.84 9294.17 v wire2115/Y (BUFx16f_ASAP7_75t_R)\r\n 105.13 9399.30 v wire2101/Y (BUFx16f_ASAP7_75t_R)\r\n 95.85 9495.16 v wire2100/Y (BUFx16f_ASAP7_75t_R)\r\n 52.35 9547.50 v max_length2099/Y (BUFx16f_ASAP7_75t_R)\r\n 38.11 9585.61 v wire2098/Y (BUFx3_ASAP7_75t_R)\r\n 16.02 9601.62 v wire113/Y (BUFx16f_ASAP7_75t_R)\r\n 127.64 9729.27 v max_length2096/Y (BUFx16f_ASAP7_75t_R)\r\n 47.57 9776.84 v wire2094/Y (BUFx3_ASAP7_75t_R)\r\n 16.12 9792.96 v wire70/Y (BUFx16f_ASAP7_75t_R)\r\n 103.02 9895.98 v max_length2093/Y (BUFx16f_ASAP7_75t_R)\r\n 51.33 9947.30 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_521833_/Y (NOR2x1_ASAP7_75t_R)\r\n 14.62 9961.93 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_521834_/Y (AO21x1_ASAP7_75t_R)\r\n 0.01 9961.94 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_719555_/D (DFFHQNx2_ASAP7_75t_R)\r\n 9961.94 data arrival time\r\n\r\n8500.00 8500.00 clock clock_uncore (rise edge)\r\n1952.03 10452.03 clock network delay (propagated)\r\n -10.00 10442.03 clock uncertainty\r\n 0.00 10442.03 clock reconvergence pessimism\r\n 10442.03 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_719555_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -6.09 10435.94 library setup time\r\n 10435.94 data required time\r\n---------------------------------------------------------\r\n 10435.94 data required time\r\n -9961.94 data arrival time\r\n---------------------------------------------------------\r\n 474.00 slack (MET)\r\n\r\n\r\nStartpoint: system/serial_tl_domain/_1267_\r\n (rising edge-triggered flip-flop clocked by serial_tl_0_clock)\r\nEndpoint: system/serial_tl_domain/_1188_\r\n (rising edge-triggered flip-flop clocked by serial_tl_0_clock)\r\nPath Group: serial_tl_0_clock\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock serial_tl_0_clock (rise edge)\r\n 48.42 48.42 clock network delay (propagated)\r\n 0.00 48.42 ^ system/serial_tl_domain/_1267_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 130.15 178.57 ^ system/serial_tl_domain/_1267_/QN (DFFASRHQNx1_ASAP7_75t_R)\r\n 69.41 247.98 v system/serial_tl_domain/_0676_/Y (NOR2x2_ASAP7_75t_R)\r\n 39.09 287.06 v system/serial_tl_domain/_0823_/Y (AND2x4_ASAP7_75t_R)\r\n 22.08 309.14 ^ system/serial_tl_domain/_1128_/CON (HAxp5_ASAP7_75t_R)\r\n 9.17 318.32 v system/serial_tl_domain/_1125_/Y (INVx1_ASAP7_75t_R)\r\n 13.54 331.85 ^ system/serial_tl_domain/_1129_/CON (HAxp5_ASAP7_75t_R)\r\n 8.88 340.73 v system/serial_tl_domain/_1123_/Y (INVx1_ASAP7_75t_R)\r\n 83.77 424.51 v system/serial_tl_domain/_1130_/SN (HAxp5_ASAP7_75t_R)\r\n 41.84 466.35 v load_slew119094/Y (BUFx10_ASAP7_75t_R)\r\n 24.78 491.13 v system/serial_tl_domain/_0863_/Y (AND2x2_ASAP7_75t_R)\r\n 19.53 510.67 v system/serial_tl_domain/_0864_/Y (AND2x2_ASAP7_75t_R)\r\n 23.33 534.00 v system/serial_tl_domain/_0866_/Y (AO32x1_ASAP7_75t_R)\r\n 49.05 583.05 v system/serial_tl_domain/_0870_/Y (OR5x2_ASAP7_75t_R)\r\n 22.11 605.16 v system/serial_tl_domain/_0872_/Y (OA22x2_ASAP7_75t_R)\r\n 0.01 605.17 v system/serial_tl_domain/_1188_/D (DFFHQNx2_ASAP7_75t_R)\r\n 605.17 data arrival time\r\n\r\n8500.00 8500.00 clock serial_tl_0_clock (rise edge)\r\n 47.57 8547.57 clock network delay (propagated)\r\n -10.00 8537.57 clock uncertainty\r\n 0.00 8537.57 clock reconvergence pessimism\r\n 8537.57 ^ system/serial_tl_domain/_1188_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -4.26 8533.31 library setup time\r\n 8533.31 data required time\r\n---------------------------------------------------------\r\n 8533.31 data required time\r\n -605.17 data arrival time\r\n---------------------------------------------------------\r\n 7928.14 slack (MET)\r\n\r\n```\r\n\r\n```\r\n>>> report_clock_min_period\r\nclock_uncore period_min = 8026.00 fmax = 124.60\r\nserial_tl_0_clock period_min = 571.86 fmax = 1748.67\r\n```\r\n\r\n```\r\n$ ./orfs make FLOW_VARIANT=flat elapsed\r\nLog Elapsed seconds\r\n1_1_yosys 4057\r\n1_1_yosys_hier_report 4063\r\n2_1_floorplan 393\r\n2_2_floorplan_io 12\r\nNo elapsed time found in bazel-bin/logs/asap7/ChipTop/flat/2_3_floorplan_tdms.log\r\n2_4_floorplan_macro 1817\r\n2_5_floorplan_tapcell 678\r\n2_6_floorplan_pdn 580\r\n3_1_place_gp_skip_io 877\r\n3_2_place_iop 38\r\n3_3_place_gp 7678\r\n3_4_place_resized 1341\r\n3_5_place_dp 1934\r\n4_1_cts 12699\r\n5_1_grt 68906\r\n5_2_fillcell 143\r\n5_3_route 20911\r\n6_1_merge 556\r\n6_report 7928\r\ngenerate_abstract 1166\r\nTotal 135777\r\n```\r\n"}, {"user": "@gudeh Any idea why the colors are so different for estimated and actual routing congestion? The estimate appears to give a very similar looking image, but why is the actual estimated congestion different?"}, {"assistant": "@oharboe Just a thought, have you properly constrained the async FIFO in SDC? I found this line https://github.com/The-OpenROAD-Project/megaboom/blob/1cce55c772d823ebca0bf8368f1d363a2e546044/constraints-chiptop.sdc#L13. I'm not sure if this covers the async FIFO or not. This would be okay for design space exploration, but for a real implementation it isn't sufficient. See [this very good guide](https://gist.github.com/brabect1/7695ead3d79be47576890bbcd61fe426)."}, {"user": "Regarding the very long global routing times. The global routing is actually fast, it is incremental repair and [reporting times](https://github.com/The-OpenROAD-Project/OpenROAD/issues/4533) that are slow."}]} +{"messages": [{"user": "Does RTLMP rotate macros?\r\n\r\nI have purposely created macros with all pins (except clock) on the left side so that there is an asymmetry to be exploited.\r\n\r\nLooking at the register file, highlighted in the screenshot below, it looks like rotating it 90 degrees counterclockwise would have resulted in much reduced routing congestion compared to the MY (mirrored about the Y axis) orientation.\r\n\r\nI have seen R180, but I don't recall R90... Does RTLMP try R90?\r\n\r\nIt is incredibly nice to get an estimated routing congestion at the floorplan stage. Thanks @ApeachM!\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/fffc3384-833f-4141-ab8d-b5dbc4be1d47)\r\n\r\nThis was using https://github.com/The-OpenROAD-Project/megaboom/commits/pins-on-left/\r\n\r\nStandalone reproduction case:\r\n\r\n1. Compile #4519\r\n1. untar https://drive.google.com/file/d/1bzlI2F004DV0dn4uvH0ajKE7l7bl9yW2/view?usp=sharing\r\n2. run `run-me-ChipTop-asap7-base.sh`"}, {"assistant": "No we don't do 90 degree turns. In most advanced processes that is illegal as there is a required poly direction."}]} +{"messages": [{"user": "How can I tell if clock skew is increasing the minimum clock period for a design?\r\n\r\nHere is my current understanding:\r\n\r\nIf two flip flops are not connected, then the clock skew between the clocks that drive those two flip flops doesn't matter because there is no timing path between these two flip flops.\r\n\r\nSkew can be good and it can be bad. If there is a long timing path between two flip flops, then a negative skew for the starting flip flops or postivive skew for the capturing flip flop would make it easier to meet timing.\r\n\r\nAs a first order approximation though, the CTS will try to minimize clock skew, because in the end a very large clock skew will catch up with you and increase the minimum clock period.\r\n\r\nLatest MegaBoom update:\r\n\r\nI have [modified MegaBoom](https://github.com/The-OpenROAD-Project/megaboom/pull/18) so that it no longer has a PLL, but a clock for the TileLink (top level memory/peripheral interface) and for the RISC-V core.\r\n\r\nAs I understand, though I don't know the code very well, the RISC-V core is connected to the TileLink via an asynchronous FIFO(or equivalent thereof).\r\n\r\nTherefore there are no ChipTop inputs/outputs that have an insertion point relative to the clock for the RISC-V core. This seems like a clever way of doing things, because then the insertion latency of the RISC-V clock doesn't matter(though clock uncertainty which I would expect to grow with a long clock insertation latency) for the clock period.\r\n\r\n```\r\n>>> report_clock_skew\r\nClock clock_uncore\r\nLatency CRPR Skew\r\nsystem/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_728430_/CLK ^\r\n 882.50\r\nsystem/tile_prci_domain/tile_reset_domain_boom_tile/core/int_issue_unit/slots_32/_3607_/CLK ^\r\n1008.42 0.00 -125.92\r\n\r\nClock serial_tl_0_clock\r\nLatency CRPR Skew\r\nsystem/serial_tl_domain/_1154_/CLK ^\r\n 67.76\r\nsystem/serial_tl_domain/_1275_/CLK ^\r\n 64.77 0.00 2.99\r\n```\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/1df082cd-b853-44f7-8b5e-7ebeb9e1409b)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/e1288f3f-c699-4fa5-9148-40a2b85e5d43)\r\n\r\nSome notes:\r\n\r\n- The area of some of those macros are mocked to be smaller than they really are so as to fit this into 1000um x 1000um and have reasonable turnaround times in builds. The L2 is *tiny* in area...\r\n- The longest timing path is part of the top level design(macros are not involved), so nothing material should be lost by ignoring what is inside the macros for now. The macros are abstracts from floorplan, so completely unrealistic.\r\n- A quick test the other day put a flattened design at ca. 3mm^2 and 3 million instances(big caveat, as I write this from my flawed memory, I'm not currently studying a flattened design). To be revisited later maybe.\r\n- W.r.t. the global placement congestion, macro placement has a fix coming up, so I don't think there's anything interesting to study w.r.t. macro placement and global routing congestion until a new build has been done after that fix. https://github.com/The-OpenROAD-Project/OpenROAD/pull/4519\r\n- almost no hold cells, 20, there used to be thousands or even tens of thousands. . :exploding_head: \r\n- running time for CTS is now much more reasonable, 5000s down from 30000s. This is not entirely suprising: now that the clock tree is not pathologically formed, the repair job is probably quick.\r\n\r\n\r\n```\r\nLog Elapsed seconds\r\n1_0_mem 173\r\n1_1_yosys 3606\r\n1_1_yosys_hier_report 3542\r\n2_1_floorplan 277\r\n2_2_floorplan_io 8\r\nNo elapsed time found in bazel-bin/logs/asap7/ChipTop/base/2_3_floorplan_tdms.log\r\n2_4_floorplan_macro 496\r\n2_5_floorplan_tapcell 130\r\n2_6_floorplan_pdn 206\r\n3_1_place_gp_skip_io 448\r\n3_2_place_iop 14\r\n3_3_place_gp 4564\r\n3_4_place_resized 863\r\n3_5_place_dp 1033\r\n4_1_cts 5069\r\n5_1_grt 14525\r\nTotal 34954\r\n```\r\n"}, {"assistant": "> If two flip flops are not connected, then the clock skew between the clocks that drive those two flip flops doesn't matter because there is no timing path between these two flip flops.\r\n\r\nCorrect\r\n\r\n> Skew can be good and it can be bad. If there is a long timing path between two flip flops, then a negative skew for the starting flip flops or postivive skew for the capturing flip flop would make it easier to meet timing.\r\n\r\nCorrect\r\n\r\n> As a first order approximation though, the CTS will try to minimize clock skew, because in the end a very large clock skew will catch up with you and increase the minimum clock period.\r\n\r\nThe OR CTS engine tries to minimize skew because it is algorithmically simpler, but not necessarily the most optimal. Commercial engines use a technique called \"concurrent clock optimization\" which will look at the timing paths and purposefully skew certain registers if it makes timing better.\r\n\r\nConcurrent clock optimization has a similar effect to register retiming - the former shifts the clock so it borrows setup time from one stage to give to another stage. The latter shifts logic from one stage to another stage and therefore also shifts setup time.\r\n\r\n> As I understand, though I don't know the code very well, the RISC-V core is connected to the TileLink via an asynchronous FIFO(or equivalent thereof).\r\n\r\nYes, async FIFOs or other clock domain crossings (CDCs) are convenient ways to break up and decouple clock trees. Clock trees cannot become too large, because the larger they are, the more power they consume and the more difficult it is to minimize skew/jitter/uncertainty. A clock tree can become so large that the jitter becomes larger than the clock period, in which case timing is impossible to meet. There is a design tradeoff between how many clock domains there are and data latency because the CDCs add one or more cycles when transmitting data across the interface.\r\n\r\n> How can I tell if clock skew is increasing the minimum clock period for a design?\r\n\r\nI might rephrase the question more simply as \"How can I tell if clock skew is bad for a design?\" because clock skew always impacts the clock period, as alluded above. This is one of the areas where it takes a lot of intuition, experimentation, and heuristics to evaluate because the answer is rarely clear. A soft and perhaps unuseful rule of thumb would be \"when the clock skew/jitter/uncertainty becomes a significant fraction of the clock period\". There are no hard rules of thumb, because sometimes high skew can be tolerated in order to keep the design fully synchronous. I personally start to get suspicious if the skew is eating more than 20-40% of the clock period. But the size of the clock tree also matters and how much skew you would _expect_ from a clock tree of that size.\r\n\r\nThere are some red flags, though, to identify purely suboptimal results. One is if there are many, many hold buffers being inserted. This is usually due to bad timing constraints, but it could also be due to bad skew in the clock tree.\r\n\r\nAnother red flag is if a path is failing both setup time _and_ hold time. This most often happens not because of skew but because of jitter caused by on-chip variation. Jitter can cause clock edges to be both early and late, which means that if a path is failing both then the jitter is too high."}, {"user": "This is the [asynchronous connection](https://github.com/The-OpenROAD-Project/megaboom/blob/9d9d44d90545dd747f38f23d1f4c37045edb5d57/rtl/ClockSinkDomain_2.sv#L163C3-L163C3) between TileLink and the rest of the system is in the Verilog code.\r\n\r\nHere is [the expected gray counter](https://github.com/The-OpenROAD-Project/megaboom/blob/9d9d44d90545dd747f38f23d1f4c37045edb5d57/rtl/AsyncQueueSink_3.sv#L56C14-L56C34) and the corresponding [Chisel code](https://github.com/chipsalliance/rocket-chip/blob/50adbdb3e4e18c2b3de57693323f4174b60f9767/src/main/scala/util/AsyncQueue.scala#L145). \r\n\r\n"}, {"user": "I chased down the synchronous reset although it doesn't show up in the most critical path at the ChipTop level.\r\n\r\nFor now, I have created a macro out of the BranchPredictor to rein in build times. In that macro the synchronous reset has a very large fanout, which obviously is a disaster for timing.\r\n\r\nAfter some investigation at the top level, I have found out that MegaBoom, [as documented](https://docs.boom-core.org/en/latest/sections/physical-realization.html#register-retiming), is relying heavily on register retiming and that the synchronous reset [is in fact pipelined](https://github.com/The-OpenROAD-Project/megaboom/blob/9d9d44d90545dd747f38f23d1f4c37045edb5d57/rtl/AsyncResetSynchronizerPrimitiveShiftReg_d3_i0.sv#L40).\r\n\r\nHowever, since the design is hierarchical and not flattened, the design won't be able to take advantage of these three pipeline stages. Also, yosys does not support retiming.\r\n\r\nRetiming in OpenROAD/yosys has been discussed in some detail [previously](https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/discussions/1710#discussioncomment-7882745), I wanted to share the results of my investigation into synchronous reset specifically for MegaBoom.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/205fd24f-9f6f-4153-ba6e-75a32f1f87a9)\r\n"}, {"user": "For my part, the questions were answered so closing."}]} +{"messages": [{"user": "I need a cell that does not rotate in both global and detailed placement. Is there any way to achieve it? I did not find any parameter. \r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/74424277/9d1b472c-dac6-4458-a3f6-f045e42abcfc)\r\n\r\nThanks\r\n\r\n"}, {"assistant": "If it is a standard cell the LEF for the cell gives its symmetry."}, {"assistant": "As this isn't a usual use case it has been lower priority. The simplest thing might be to just delete the rows that represent Y symmetry if you want to avoid such for your experiments."}]} +{"messages": [{"user": "Looks much more reasonable now. There are H-clock trees after CTS.\r\n\r\n`make cts_issue`; CTS takes ca. 25000 seconds on my machine: https://drive.google.com/file/d/13eenpP2JgzXJD0uP3KIpX4QLArBVjzT2/view?usp=sharing\r\n\r\nThis is apples and oranges comparision, but ... Minimum clock period is 5000ps, whereas I've seen claims on the order of 1000ps with commercial tools for the most similar design I know of to MegaBoom: https://carrv.github.io/2020/papers/CARRV2020_paper_15_Zhao.pdf\r\n\r\n```\r\n>>> report_clock_min_period\r\nclock period_min = 5403.70 fmax = 185.06\r\nclock_vir period_min = 0.00 fmax = inf\r\nfake_pll_clk period_min = 5403.70 fmax = 185.06\r\nserial_tl_0_clock period_min = 953.62 fmax = 1048.63\r\n```\r\n\r\nYellow are hold cells, very reasonable... Clock tree looks odd. Those leaf nodes on the right side are flip flops. It would be nice if there was some clear visual indication of macros vs. flip flop endpoints in the CTS view....\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/5837af84-df29-4b34-adbe-c8f9b1a48e14)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/6f0037fa-6c26-4904-88a0-e31fc5312cb0)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/3d39c96e-5d49-4a5e-add6-6e6517d4ccf8)\r\n\r\n\r\n```\r\nreport_checks -path_delay max -fields {fanout skew}\r\nStartpoint: reset (input port clocked by clock_vir)\r\nEndpoint: system/prci_ctrl_domain/_3041_\r\n (recovery check against rising-edge clock fake_pll_clk)\r\nPath Group: asynchronous\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock_vir (rise edge)\r\n 1000.00 1000.00 clock network delay (ideal)\r\n 1700.00 2700.00 v input external delay\r\n 1 0.00 2700.00 v reset (in)\r\n 1 10.58 2710.58 v hold4662/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 2723.18 v hold4387/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 2735.67 v hold4663/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.65 2748.32 v hold4335/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.65 2760.97 v hold4664/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.72 2773.69 v hold4388/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.81 2786.50 v hold4665/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.50 2799.00 v hold64/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.66 2811.66 v hold4666/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.66 2824.31 v hold4389/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.59 2836.91 v hold4667/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.71 2849.61 v hold4336/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.48 2862.09 v hold4668/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 2874.48 v hold4390/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.40 2886.88 v hold4669/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.34 2899.21 v hold56/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.32 2911.54 v hold4670/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.23 2923.77 v hold4391/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.45 2936.22 v hold4671/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 2948.71 v hold4337/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.35 2961.06 v hold4672/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.16 2973.22 v hold4392/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 2985.48 v hold4673/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.38 2997.87 v hold65/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.25 3010.12 v hold4674/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.19 3022.31 v hold4393/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.21 3034.52 v hold4675/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.21 3046.72 v hold4338/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.47 3059.19 v hold4676/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.59 3071.78 v hold4394/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.63 3087.41 v hold4677/Y (BUFx2_ASAP7_75t_R)\r\n 1 18.70 3106.12 v input5/Y (BUFx24_ASAP7_75t_R)\r\n 1 13.56 3119.68 v hold4678/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.47 3134.15 v hold4395/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3149.44 v hold4339/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3164.73 v hold4396/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 3180.00 v hold66/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3195.29 v hold4397/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.25 3210.53 v hold4340/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.21 3225.74 v hold4398/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3241.03 v hold57/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.30 3256.34 v hold4399/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.23 3271.56 v hold4341/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.26 3286.82 v hold4400/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3302.12 v hold67/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 3317.35 v hold4401/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.20 3332.56 v hold4342/Y (BUFx2_ASAP7_75t_R)\r\n 1 17.90 3350.46 v hold4402/Y (BUFx2_ASAP7_75t_R)\r\n 1 16.93 3367.38 v wire96200/Y (BUFx16f_ASAP7_75t_R)\r\n 1 14.22 3381.60 v hold4403/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.14 3396.75 v hold4343/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.26 3412.01 v hold4404/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3427.30 v hold68/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.19 3442.49 v hold4405/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.21 3457.70 v hold4344/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.28 3472.98 v hold4406/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 3488.22 v hold58/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.18 3503.40 v hold4407/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 3518.64 v hold4345/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.23 3533.87 v hold4408/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.18 3549.06 v hold69/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.15 3564.21 v hold4409/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.13 3579.33 v hold4346/Y (BUFx2_ASAP7_75t_R)\r\n 1 17.89 3597.22 v hold4410/Y (BUFx2_ASAP7_75t_R)\r\n 1 16.94 3614.16 v wire96199/Y (BUFx16f_ASAP7_75t_R)\r\n 1 14.34 3628.51 v hold4411/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3643.80 v hold4347/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.28 3659.08 v hold4412/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.28 3674.36 v hold70/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3689.65 v hold4413/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3704.94 v hold4348/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 3720.18 v hold4414/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 3735.49 v hold59/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.33 3750.82 v hold4415/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 3766.08 v hold4349/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 3781.32 v hold4416/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.21 3796.53 v hold71/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.32 3811.85 v hold4417/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.36 3827.21 v hold4350/Y (BUFx2_ASAP7_75t_R)\r\n 1 17.90 3845.10 v hold4418/Y (BUFx2_ASAP7_75t_R)\r\n 1 16.84 3861.95 v wire96198/Y (BUFx16f_ASAP7_75t_R)\r\n 1 14.33 3876.27 v hold4419/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.34 3891.61 v hold4351/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 3906.92 v hold4420/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.21 3922.13 v hold72/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.30 3937.43 v hold4421/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 3952.73 v hold4352/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.20 3967.93 v hold4422/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.33 3983.26 v hold60/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 3998.57 v hold4423/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 4013.88 v hold4353/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.28 4029.16 v hold4424/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.17 4044.33 v hold73/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 4059.57 v hold4425/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.37 4074.94 v hold4354/Y (BUFx2_ASAP7_75t_R)\r\n 1 17.95 4092.90 v hold4426/Y (BUFx2_ASAP7_75t_R)\r\n 1 16.85 4109.75 v wire96197/Y (BUFx16f_ASAP7_75t_R)\r\n 1 14.32 4124.07 v hold4427/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.33 4139.40 v hold4355/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.37 4154.77 v hold4428/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 4170.01 v hold74/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.19 4185.20 v hold4429/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.26 4200.45 v hold4356/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.22 4215.67 v hold4430/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 4230.98 v hold61/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 4246.25 v hold4431/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.28 4261.53 v hold4357/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.33 4276.86 v hold4432/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 4292.15 v hold75/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.21 4307.35 v hold4433/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.23 4322.59 v hold4358/Y (BUFx2_ASAP7_75t_R)\r\n 1 17.96 4340.55 v hold4434/Y (BUFx2_ASAP7_75t_R)\r\n 1 20.57 4361.13 v wire96196/Y (BUFx24_ASAP7_75t_R)\r\n 1 14.76 4375.89 v hold4435/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.31 4391.20 v hold4359/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.29 4406.49 v hold4436/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 4421.75 v hold76/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 4437.02 v hold4437/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 4452.26 v hold4360/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.26 4467.52 v hold4438/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 4482.79 v hold62/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.20 4497.99 v hold4439/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.18 4513.17 v hold4361/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.25 4528.42 v hold4440/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.24 4543.66 v hold77/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.22 4558.88 v hold4441/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.35 4574.23 v hold4362/Y (BUFx2_ASAP7_75t_R)\r\n 1 22.85 4597.08 v hold4442/Y (BUFx2_ASAP7_75t_R)\r\n 15 15.42 4612.50 ^ system/prci_ctrl_domain/_1567_/Y (INVx11_ASAP7_75t_R)\r\n 2.22 4614.72 ^ system/prci_ctrl_domain/_3041_/SETN (DFFASRHQNx1_ASAP7_75t_R)\r\n 4614.72 data arrival time\r\n\r\n 8500.00 8500.00 clock fake_pll_clk (rise edge)\r\n 474.60 8974.60 clock network delay (propagated)\r\n -10.00 8964.60 clock uncertainty\r\n 0.00 8964.60 clock reconvergence pessimism\r\n 8964.60 ^ system/prci_ctrl_domain/_3041_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 4.83 8969.43 library recovery time\r\n 8969.43 data required time\r\n---------------------------------------------------------------\r\n 8969.43 data required time\r\n -4614.72 data arrival time\r\n---------------------------------------------------------------\r\n 4354.71 slack (MET)\r\n\r\n\r\nStartpoint: system/prci_ctrl_domain/_2967_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: system/prci_ctrl_domain/_1576_\r\n (rising clock gating-check end-point clocked by fake_pll_clk)\r\nPath Group: gated clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 983.66 983.66 clock network delay (propagated)\r\n 0.00 983.66 ^ system/prci_ctrl_domain/_2967_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 29 134.66 1118.32 v system/prci_ctrl_domain/_2967_/QN (DFFASRHQNx1_ASAP7_75t_R)\r\n 1 41.06 1159.38 v hold6293/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.10 1173.47 v hold6165/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.29 1185.77 v hold6294/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 1198.07 v hold6101/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.29 1210.37 v hold6295/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 1222.63 v hold6166/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.25 1234.88 v hold6296/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.29 1247.17 v hold5379/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.23 1259.39 v hold6297/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.35 1271.74 v hold6167/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.36 1284.10 v hold6298/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.28 1296.38 v hold6102/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 1308.63 v hold6299/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.46 1321.09 v hold6168/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.73 1333.82 v hold6300/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.52 1346.34 v hold4926/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.20 1358.54 v hold6301/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 1370.85 v hold6169/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.27 1383.12 v hold6302/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.41 1395.53 v hold6103/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.73 1408.26 v hold6303/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.77 1421.03 v hold6170/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.69 1433.72 v hold6304/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.68 1446.40 v hold5380/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.80 1459.19 v hold6305/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.82 1472.02 v hold6171/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 1484.59 v hold6306/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.37 1496.96 v hold6104/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 1509.22 v hold6307/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.70 1521.92 v hold6172/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.82 1534.74 v hold6308/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 1547.36 v hold4681/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 1559.74 v hold6309/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.25 1572.00 v hold6173/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 1584.30 v hold6310/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.77 1597.06 v hold6105/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.51 1609.57 v hold6311/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.16 1621.73 v hold6174/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.80 1634.53 v hold6312/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.18 1647.71 v hold5381/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.15 1660.86 v hold6313/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.14 1674.00 v hold6175/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.11 1687.12 v hold6314/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.64 1699.76 v hold6106/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.21 1711.97 v hold6315/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 1724.29 v hold6176/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.02 1737.31 v hold6316/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 1749.93 v hold4927/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.77 1762.70 v hold6317/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.54 1775.24 v hold6177/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.73 1787.97 v hold6318/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.09 1801.06 v hold6107/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.16 1814.23 v hold6319/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.82 1827.04 v hold6178/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.89 1839.94 v hold6320/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 1852.42 v hold5382/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.64 1865.07 v hold6321/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.48 1877.55 v hold6179/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 1889.85 v hold6322/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.04 1902.89 v hold6108/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.16 1916.05 v hold6323/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 1928.68 v hold6180/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.66 1941.34 v hold6324/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.54 1953.88 v hold4532/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.28 1966.16 v hold6325/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.24 1978.40 v hold6181/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.20 1990.60 v hold6326/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.16 2002.76 v hold6109/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.10 2014.86 v hold6327/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.99 2027.85 v hold6182/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.77 2040.62 v hold6328/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.22 2052.84 v hold5383/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 2065.15 v hold6329/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 2077.41 v hold6183/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 2089.71 v hold6330/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.27 2101.98 v hold6110/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 2114.31 v hold6331/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.93 2127.24 v hold6184/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.67 2139.92 v hold6332/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.34 2152.26 v hold4928/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.52 2164.78 v hold6333/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 2177.41 v hold6185/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.58 2189.99 v hold6334/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.50 2202.48 v hold6111/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.76 2215.24 v hold6335/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.58 2227.82 v hold6186/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.00 2240.82 v hold6336/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.26 2254.08 v hold5384/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.10 2267.18 v hold6337/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.87 2280.06 v hold6187/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.40 2292.45 v hold6338/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.68 2305.14 v hold6112/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.17 2318.31 v hold6339/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.24 2331.55 v hold6188/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.95 2344.49 v hold6340/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.87 2357.37 v hold4682/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.08 2370.45 v hold6341/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.06 2383.51 v hold6189/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.44 2395.95 v hold6342/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.11 2409.06 v hold6113/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.52 2422.58 v hold6343/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.74 2435.33 v hold6190/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.02 2448.35 v hold6344/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.79 2461.14 v hold5385/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 2473.46 v hold6345/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.86 2486.32 v hold6191/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.72 2500.04 v hold6346/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.03 2514.08 v hold6114/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.71 2527.79 v hold6347/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.74 2540.53 v hold6192/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.77 2553.30 v hold6348/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.31 2566.61 v hold4929/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.47 2580.08 v hold6349/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.34 2593.42 v hold6193/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.42 2606.83 v hold6350/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.19 2620.02 v hold6115/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 2632.66 v hold6351/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 2644.99 v hold6194/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.72 2657.71 v hold6352/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 2670.28 v hold5386/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 2682.76 v hold6353/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.07 2695.84 v hold6195/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.42 2709.26 v hold6354/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.18 2722.44 v hold6116/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 2735.05 v hold6355/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.58 2747.62 v hold6196/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 2759.95 v hold6356/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.24 2772.19 v hold4317/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.23 2785.42 v hold6357/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.00 2798.42 v hold6197/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.88 2811.30 v hold6358/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.39 2824.69 v hold6117/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.02 2837.72 v hold6359/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.42 2850.13 v hold6198/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.99 2863.12 v hold6360/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.56 2876.68 v hold5387/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.89 2889.57 v hold6361/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.29 2901.86 v hold6199/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.09 2914.95 v hold6362/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.65 2928.60 v hold6118/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.02 2942.62 v hold6363/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.33 2956.95 v hold6200/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.03 2970.98 v hold6364/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.62 2984.61 v hold4930/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.56 2998.16 v hold6365/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.70 3011.86 v hold6201/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.86 3025.72 v hold6366/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.95 3038.67 v hold6119/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.52 3051.19 v hold6367/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 3063.79 v hold6202/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 3076.69 v hold6368/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.52 3089.21 v hold5388/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 3101.85 v hold6369/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.31 3115.16 v hold6203/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.79 3127.95 v hold6370/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.18 3141.13 v hold6120/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.51 3154.64 v hold6371/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.84 3167.48 v hold6204/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 3179.78 v hold6372/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.56 3192.33 v hold4683/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.37 3205.71 v hold6373/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.88 3218.58 v hold6205/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.30 3231.89 v hold6374/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.23 3245.11 v hold6121/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 3258.02 v hold6375/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 3270.59 v hold6206/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.22 3282.80 v hold6376/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.93 3295.74 v hold5389/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 3308.36 v hold6377/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.22 3321.59 v hold6207/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.04 3334.63 v hold6378/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.57 3348.20 v hold6122/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.15 3361.35 v hold6379/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.45 3374.80 v hold6208/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.14 3387.94 v hold6380/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.35 3400.29 v hold4931/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.88 3413.17 v hold6381/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.98 3426.15 v hold6209/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.53 3438.68 v hold6382/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.92 3451.60 v hold6123/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.50 3465.10 v hold6383/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.85 3477.95 v hold6210/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.95 3490.90 v hold6384/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.25 3504.15 v hold5390/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.53 3516.69 v hold6385/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.35 3529.04 v hold6211/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.55 3542.59 v hold6386/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.29 3555.88 v hold6124/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.40 3568.28 v hold6387/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.06 3581.34 v hold6212/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 3594.24 v hold6388/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.66 3606.90 v hold4533/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.85 3619.75 v hold6389/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.50 3632.25 v hold6213/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.53 3644.78 v hold6390/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.88 3657.66 v hold6125/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.42 3671.08 v hold6391/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.85 3683.93 v hold6214/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.78 3696.70 v hold6392/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.18 3709.88 v hold5391/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.83 3723.71 v hold6393/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.31 3738.02 v hold6215/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.03 3751.05 v hold6394/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.15 3764.20 v hold6126/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.54 3777.74 v hold6216/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.35 3791.09 v hold4932/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.76 3803.85 v hold6217/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.29 3816.14 v hold6127/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 3828.40 v hold6218/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 3841.01 v hold5392/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.96 3853.97 v hold6219/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.73 3866.70 v hold6128/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.69 3879.39 v hold6220/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.46 3891.85 v hold4684/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.43 3904.28 v hold6221/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.24 3916.52 v hold6129/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.46 3928.99 v hold6222/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.54 3941.53 v hold5393/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.28 3953.81 v hold6223/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.93 3966.75 v hold6130/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.08 3980.82 v hold6224/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.56 3995.38 v hold4933/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.17 4008.56 v hold6225/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.25 4020.80 v hold6131/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.36 4034.16 v hold6226/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.93 4047.10 v hold5394/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.47 4059.57 v hold6227/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.61 4072.18 v hold6132/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.43 4084.61 v hold6228/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.41 4097.02 v hold55/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.59 4109.60 v hold6229/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.92 4122.52 v hold6133/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.95 4135.47 v hold6230/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.91 4148.38 v hold5395/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.30 4161.68 v hold6231/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.06 4174.74 v hold6134/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.38 4188.13 v hold6232/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.81 4200.93 v hold4934/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 4213.19 v hold6233/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 4225.52 v hold6135/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.53 4238.05 v hold6234/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 4250.45 v hold5396/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.20 4262.65 v hold6235/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.24 4274.89 v hold6136/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.60 4287.49 v hold6236/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.72 4300.21 v hold4685/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.12 4313.32 v hold6237/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.48 4326.80 v hold6137/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.50 4340.29 v hold6238/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.69 4352.98 v hold5397/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.85 4365.83 v hold6239/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.29 4379.13 v hold6138/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.71 4391.84 v hold6240/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 4404.10 v hold4935/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.25 4416.35 v hold6241/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.19 4428.54 v hold6139/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.16 4441.69 v hold6242/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.98 4455.68 v hold5398/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.93 4469.61 v hold6243/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.80 4482.41 v hold6140/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.14 4495.55 v hold6244/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.52 4509.07 v hold4534/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 4521.64 v hold6245/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.23 4533.86 v hold6141/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.52 4546.38 v hold6246/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.67 4559.05 v hold5399/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.70 4571.76 v hold6247/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 4584.15 v hold6142/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.20 4597.34 v hold6248/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.86 4610.20 v hold4936/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.20 4622.40 v hold6249/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 4634.89 v hold6143/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.36 4647.24 v hold6250/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.34 4659.58 v hold5400/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.43 4672.01 v hold6251/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.28 4684.29 v hold6144/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.40 4697.68 v hold6252/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.97 4710.66 v hold4686/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.25 4723.91 v hold6253/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.75 4737.67 v hold6145/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.94 4750.60 v hold6254/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 4762.91 v hold5401/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.14 4775.05 v hold6255/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.37 4787.42 v hold6146/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 4799.99 v hold6256/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.98 4812.96 v hold4937/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.65 4825.62 v hold6257/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.30 4838.91 v hold6147/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.89 4852.81 v hold6258/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.08 4865.89 v hold5402/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 4878.28 v hold6259/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.81 4891.10 v hold6148/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.84 4903.94 v hold6260/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.36 4916.29 v hold4318/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.23 4928.52 v hold6261/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.05 4941.57 v hold6149/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.76 4955.33 v hold6262/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.92 4969.26 v hold5403/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.94 4983.20 v hold6263/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.94 4996.14 v hold6150/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.27 5008.41 v hold6264/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.32 5021.72 v hold4938/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.09 5034.82 v hold6265/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.31 5047.13 v hold6151/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.24 5060.37 v hold6266/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.45 5073.81 v hold5404/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.32 5087.13 v hold6267/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.48 5100.61 v hold6152/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.47 5114.08 v hold6268/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.50 5127.58 v hold4687/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.76 5141.34 v hold6269/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.92 5155.26 v hold6153/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 5168.17 v hold6270/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.02 5181.19 v hold5405/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.68 5193.87 v hold6271/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 5206.20 v hold6154/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.82 5219.02 v hold6272/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.08 5232.10 v hold4939/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.63 5244.73 v hold6273/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.49 5257.22 v hold6155/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.94 5270.15 v hold6274/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.64 5282.79 v hold5406/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.62 5295.42 v hold6275/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.66 5308.07 v hold6156/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.73 5320.81 v hold6276/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.22 5334.03 v hold4535/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.47 5347.49 v hold6277/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.64 5360.13 v hold6157/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.46 5372.59 v hold6278/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.60 5385.19 v hold5407/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 5397.58 v hold6279/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 5409.88 v hold6158/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.46 5422.34 v hold6280/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.32 5434.65 v hold4940/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.14 5446.79 v hold6281/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 5459.18 v hold6159/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.48 5471.66 v hold6282/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.29 5484.95 v hold5408/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.66 5498.61 v hold6283/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.76 5511.37 v hold6160/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 5524.28 v hold6284/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.92 5537.19 v hold4688/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.60 5549.79 v hold6285/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 5562.09 v hold6161/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.50 5574.59 v hold6286/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.39 5586.98 v hold5409/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.57 5599.54 v hold6287/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.79 5612.33 v hold6162/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.72 5625.05 v hold6288/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.32 5637.37 v hold4941/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 5649.62 v hold6289/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.30 5661.93 v hold6163/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.76 5674.69 v hold6290/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.90 5687.59 v hold5410/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.56 5700.14 v hold6291/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.33 5712.48 v hold6164/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.32 5724.80 v hold6292/Y (BUFx2_ASAP7_75t_R)\r\n 0.02 5724.82 v system/prci_ctrl_domain/_1576_/A (AND2x2_ASAP7_75t_R)\r\n 5724.82 data arrival time\r\n\r\n 8500.00 8500.00 clock fake_pll_clk (rise edge)\r\n 898.15 9398.15 clock network delay (propagated)\r\n -10.00 9388.15 clock uncertainty\r\n 0.00 9388.15 clock reconvergence pessimism\r\n 9388.15 ^ system/prci_ctrl_domain/_1576_/B (AND2x2_ASAP7_75t_R)\r\n 0.00 9388.15 clock gating setup time\r\n 9388.15 data required time\r\n---------------------------------------------------------------\r\n 9388.15 data required time\r\n -5724.82 data arrival time\r\n---------------------------------------------------------------\r\n 3663.32 slack (MET)\r\n\r\n\r\nStartpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 1459.67 1459.67 clock network delay (propagated)\r\n 0.00 1459.67 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 16 87.80 1547.47 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 8 25.27 1572.74 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055753_/Y (INVx13_ASAP7_75t_R)\r\n 3 21.71 1594.45 v max_length80840/Y (BUFx12f_ASAP7_75t_R)\r\n 10 106.10 1700.55 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100755_/CON (HAxp5_ASAP7_75t_R)\r\n 5 38.99 1739.54 ^ load_slew77788/Y (BUFx12f_ASAP7_75t_R)\r\n 6 18.39 1757.93 ^ load_slew77787/Y (BUFx12f_ASAP7_75t_R)\r\n 24 74.82 1832.75 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055925_/Y (OR4x2_ASAP7_75t_R)\r\n 1 52.70 1885.46 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055926_/Y (OA22x2_ASAP7_75t_R)\r\n 1 32.11 1917.56 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055940_/Y (AND5x1_ASAP7_75t_R)\r\n 4 40.36 1957.93 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055972_/Y (AND4x2_ASAP7_75t_R)\r\n 21 41.38 1999.31 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055973_/Y (NAND2x2_ASAP7_75t_R)\r\n 3 92.34 2091.65 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056022_/Y (OR3x4_ASAP7_75t_R)\r\n 4 34.23 2125.88 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056088_/Y (NOR3x2_ASAP7_75t_R)\r\n 1 82.97 2208.86 ^ wire54325/Y (BUFx16f_ASAP7_75t_R)\r\n 3 79.05 2287.91 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09171_/Y (NAND2x2_ASAP7_75t_R)\r\n 2 72.45 2360.36 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09366_/Y (OA21x2_ASAP7_75t_R)\r\n 1 30.95 2391.30 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09368_/Y (OR4x1_ASAP7_75t_R)\r\n 2 43.84 2435.15 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09369_/Y (OR4x2_ASAP7_75t_R)\r\n 5 41.86 2477.01 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10984_/Y (NOR3x2_ASAP7_75t_R)\r\n 20 54.43 2531.44 ^ wire46500/Y (BUFx16f_ASAP7_75t_R)\r\n 3 113.22 2644.66 ^ wire46499/Y (BUFx16f_ASAP7_75t_R)\r\n 2 74.22 2718.88 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383170_/Y (AND2x2_ASAP7_75t_R)\r\n 14 24.78 2743.66 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383188_/Y (NAND2x2_ASAP7_75t_R)\r\n 12 63.17 2806.83 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383224_/Y (AO21x2_ASAP7_75t_R)\r\n 5 24.83 2831.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_479882_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 11 84.15 2915.81 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732259_/CON (HAxp5_ASAP7_75t_R)\r\n 3 31.45 2947.26 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383227_/Y (INVx2_ASAP7_75t_R)\r\n 2 25.01 2972.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383231_/Y (AND2x2_ASAP7_75t_R)\r\n 2 22.19 2994.46 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732246_/CON (HAxp5_ASAP7_75t_R)\r\n 2 31.03 3025.49 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732246_/SN (HAxp5_ASAP7_75t_R)\r\n 1 31.95 3057.44 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393218_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 40.29 3097.73 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393222_/Y (AND5x2_ASAP7_75t_R)\r\n 1 38.93 3136.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09361_/Y (AO22x2_ASAP7_75t_R)\r\n 1 60.29 3196.95 ^ wire32998/Y (BUFx16f_ASAP7_75t_R)\r\n 1 63.16 3260.11 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09362_/Y (OR4x2_ASAP7_75t_R)\r\n 1 16.20 3276.31 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09363_/Y (OR4x1_ASAP7_75t_R)\r\n 1 19.72 3296.03 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09371_/Y (AO22x1_ASAP7_75t_R)\r\n 3 10.78 3306.81 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09372_/Y (INVx2_ASAP7_75t_R)\r\n 5 32.27 3339.08 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10980_/Y (AND3x4_ASAP7_75t_R)\r\n 2 32.46 3371.54 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10981_/Y (AND2x6_ASAP7_75t_R)\r\n 6 26.61 3398.15 v wire30552/Y (BUFx16f_ASAP7_75t_R)\r\n 3 117.06 3515.20 v wire30547/Y (BUFx16f_ASAP7_75t_R)\r\n 2 79.46 3594.66 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383202_/Y (AND2x2_ASAP7_75t_R)\r\n 13 30.10 3624.76 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383232_/Y (NAND2x2_ASAP7_75t_R)\r\n 37 104.44 3729.20 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383277_/Y (AO21x2_ASAP7_75t_R)\r\n 8 123.99 3853.19 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383285_/Y (NOR2x2_ASAP7_75t_R)\r\n 2 69.54 3922.74 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383289_/Y (AND2x2_ASAP7_75t_R)\r\n 2 70.43 3993.16 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732263_/SN (HAxp5_ASAP7_75t_R)\r\n 1 35.94 4029.10 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393224_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 33.88 4062.98 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393228_/Y (AND5x2_ASAP7_75t_R)\r\n 1 22.63 4085.61 v wire18339/Y (BUFx12f_ASAP7_75t_R)\r\n 1 90.65 4176.26 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09348_/Y (AO221x2_ASAP7_75t_R)\r\n 1 78.25 4254.51 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09352_/Y (OR4x1_ASAP7_75t_R)\r\n 2 12.50 4267.01 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09353_/Y (INVx1_ASAP7_75t_R)\r\n 2 29.33 4296.34 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13707_/Y (AND3x4_ASAP7_75t_R)\r\n 2 16.51 4312.85 ^ max_length17970/Y (BUFx12f_ASAP7_75t_R)\r\n 2 58.75 4371.60 ^ wire17968/Y (BUFx16f_ASAP7_75t_R)\r\n 4 69.67 4441.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383260_/Y (AND2x4_ASAP7_75t_R)\r\n 8 22.60 4463.87 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383290_/Y (NAND2x2_ASAP7_75t_R)\r\n 25 39.78 4503.65 v load_slew17553/Y (BUFx16f_ASAP7_75t_R)\r\n 8 52.97 4556.62 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_389614_/Y (OA21x2_ASAP7_75t_R)\r\n 15 27.29 4583.91 v max_length15743/Y (BUFx16f_ASAP7_75t_R)\r\n 6 44.22 4628.14 v wire15739/Y (BUFx16f_ASAP7_75t_R)\r\n 2 96.47 4724.61 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732319_/CON (HAxp5_ASAP7_75t_R)\r\n 10 26.31 4750.92 ^ wire10637/Y (BUFx12f_ASAP7_75t_R)\r\n 9 28.31 4779.22 ^ wire10635/Y (BUFx12f_ASAP7_75t_R)\r\n 5 23.85 4803.08 ^ wire10634/Y (BUFx16f_ASAP7_75t_R)\r\n 3 49.02 4852.10 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393150_/Y (INVx3_ASAP7_75t_R)\r\n 1 19.43 4871.53 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732322_/CON (HAxp5_ASAP7_75t_R)\r\n 2 13.70 4885.23 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732225_/Y (INVx1_ASAP7_75t_R)\r\n 2 54.56 4939.79 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732324_/CON (HAxp5_ASAP7_75t_R)\r\n 2 57.06 4996.85 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732324_/SN (HAxp5_ASAP7_75t_R)\r\n 1 39.36 5036.22 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393230_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 29.47 5065.69 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393234_/Y (AND5x2_ASAP7_75t_R)\r\n 1 38.32 5104.01 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09177_/Y (AO22x2_ASAP7_75t_R)\r\n 1 65.68 5169.69 v wire10120/Y (BUFx16f_ASAP7_75t_R)\r\n 1 85.75 5255.45 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09180_/Y (OR4x2_ASAP7_75t_R)\r\n 1 47.72 5303.17 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09181_/Y (OR4x2_ASAP7_75t_R)\r\n 1 14.50 5317.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09182_/Y (INVx1_ASAP7_75t_R)\r\n 3 20.96 5338.62 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09346_/Y (AO31x2_ASAP7_75t_R)\r\n 1 22.09 5360.71 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09357_/Y (AND2x2_ASAP7_75t_R)\r\n 3 22.17 5382.88 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09375_/Y (NAND3x2_ASAP7_75t_R)\r\n 2 44.87 5427.75 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13855_/Y (NOR2x2_ASAP7_75t_R)\r\n 4 31.84 5459.59 ^ max_length10066/Y (BUFx16f_ASAP7_75t_R)\r\n 3 46.40 5505.98 ^ wire10064/Y (BUFx16f_ASAP7_75t_R)\r\n 1 74.29 5580.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_14394_/Y (AND2x2_ASAP7_75t_R)\r\n 1 5.61 5585.88 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065683_/Y (INVx1_ASAP7_75t_R)\r\n 2 61.87 5647.75 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065702_/Y (OR5x2_ASAP7_75t_R)\r\n 2 53.28 5701.03 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065722_/Y (NAND2x2_ASAP7_75t_R)\r\n 24 24.22 5725.25 ^ max_length8441/Y (BUFx16f_ASAP7_75t_R)\r\n 22 43.01 5768.26 ^ wire8439/Y (BUFx16f_ASAP7_75t_R)\r\n 19 49.84 5818.10 ^ load_slew8429/Y (BUFx16f_ASAP7_75t_R)\r\n 14 47.09 5865.20 ^ wire8426/Y (BUFx16f_ASAP7_75t_R)\r\n 11 48.21 5913.41 ^ max_length8425/Y (BUFx16f_ASAP7_75t_R)\r\n 10 58.85 5972.26 ^ wire8424/Y (BUFx16f_ASAP7_75t_R)\r\n 10 61.11 6033.37 ^ max_length8423/Y (BUFx12f_ASAP7_75t_R)\r\n 11 38.21 6071.58 ^ wire8422/Y (BUFx16f_ASAP7_75t_R)\r\n 25 51.58 6123.15 ^ wire8421/Y (BUFx16f_ASAP7_75t_R)\r\n 6 60.76 6183.91 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1678_/Y (INVx11_ASAP7_75t_R)\r\n 24 21.32 6205.24 v max_length4569/Y (BUFx16f_ASAP7_75t_R)\r\n 11 62.98 6268.22 v wire4568/Y (BUFx16f_ASAP7_75t_R)\r\n 10 53.54 6321.76 v wire4567/Y (BUFx16f_ASAP7_75t_R)\r\n 12 73.47 6395.22 v wire4566/Y (BUFx16f_ASAP7_75t_R)\r\n 35 109.03 6504.25 v max_length4564/Y (BUFx16f_ASAP7_75t_R)\r\n 57 67.38 6571.63 v load_slew4563/Y (BUFx16f_ASAP7_75t_R)\r\n 1 95.45 6667.09 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1885_/Y (NAND2x1_ASAP7_75t_R)\r\n 13 52.03 6719.12 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1886_/Y (OA21x2_ASAP7_75t_R)\r\n 1 30.21 6749.33 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3041_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 30.06 6779.38 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3043_/Y (AND4x1_ASAP7_75t_R)\r\n 1 32.88 6812.26 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3047_/Y (AND5x1_ASAP7_75t_R)\r\n 1 19.43 6831.69 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3048_/Y (OR4x1_ASAP7_75t_R)\r\n 1 29.64 6861.33 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3133_/Y (OA31x2_ASAP7_75t_R)\r\n 2.24 6863.57 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_/D (DFFHQNx2_ASAP7_75t_R)\r\n 6863.57 data arrival time\r\n\r\n 8500.00 8500.00 clock clock (rise edge)\r\n 1476.29 9976.29 clock network delay (propagated)\r\n -10.00 9966.29 clock uncertainty\r\n 4.53 9970.81 clock reconvergence pessimism\r\n 9970.81 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -10.95 9959.87 library setup time\r\n 9959.87 data required time\r\n---------------------------------------------------------------\r\n 9959.87 data required time\r\n -6863.57 data arrival time\r\n---------------------------------------------------------------\r\n 3096.30 slack (MET)\r\n\r\n\r\nStartpoint: system/serial_tl_domain/_1142_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: serial_tl_0_bits_in_ready (output port clocked by clock_vir)\r\nPath Group: clock_vir\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 1486.19 1486.19 clock network delay (propagated)\r\n 0.00 1486.19 ^ system/serial_tl_domain/_1142_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 3 50.71 1536.90 ^ system/serial_tl_domain/_1142_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 3 35.82 1572.72 v system/serial_tl_domain/_0641_/Y (NOR3x2_ASAP7_75t_R)\r\n 1 61.16 1633.88 v output14/Y (BUFx2_ASAP7_75t_R)\r\n 0.02 1633.90 v serial_tl_0_bits_in_ready (out)\r\n 1633.90 data arrival time\r\n\r\n 8500.00 8500.00 clock clock_vir (rise edge)\r\n 1000.00 9500.00 clock network delay (ideal)\r\n -10.00 9490.00 clock uncertainty\r\n 0.00 9490.00 clock reconvergence pessimism\r\n -1700.00 7790.00 output external delay\r\n 7790.00 data required time\r\n---------------------------------------------------------------\r\n 7790.00 data required time\r\n -1633.90 data arrival time\r\n---------------------------------------------------------------\r\n 6156.10 slack (MET)\r\n\r\n\r\nStartpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_\r\n (rising edge-triggered flip-flop clocked by fake_pll_clk)\r\nPath Group: fake_pll_clk\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 1459.67 1459.67 clock network delay (propagated)\r\n 0.00 1459.67 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 16 87.80 1547.47 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100801_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 8 25.27 1572.74 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055753_/Y (INVx13_ASAP7_75t_R)\r\n 3 21.71 1594.45 v max_length80840/Y (BUFx12f_ASAP7_75t_R)\r\n 10 106.10 1700.55 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_100755_/CON (HAxp5_ASAP7_75t_R)\r\n 5 38.99 1739.54 ^ load_slew77788/Y (BUFx12f_ASAP7_75t_R)\r\n 6 18.39 1757.93 ^ load_slew77787/Y (BUFx12f_ASAP7_75t_R)\r\n 24 74.82 1832.75 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055925_/Y (OR4x2_ASAP7_75t_R)\r\n 1 52.70 1885.46 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055926_/Y (OA22x2_ASAP7_75t_R)\r\n 1 32.11 1917.56 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055940_/Y (AND5x1_ASAP7_75t_R)\r\n 4 40.36 1957.93 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055972_/Y (AND4x2_ASAP7_75t_R)\r\n 21 41.38 1999.31 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_055973_/Y (NAND2x2_ASAP7_75t_R)\r\n 3 92.34 2091.65 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056022_/Y (OR3x4_ASAP7_75t_R)\r\n 4 34.23 2125.88 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/rob/_056088_/Y (NOR3x2_ASAP7_75t_R)\r\n 1 82.97 2208.86 ^ wire54325/Y (BUFx16f_ASAP7_75t_R)\r\n 3 79.05 2287.91 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09171_/Y (NAND2x2_ASAP7_75t_R)\r\n 2 72.45 2360.36 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09366_/Y (OA21x2_ASAP7_75t_R)\r\n 1 30.95 2391.30 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09368_/Y (OR4x1_ASAP7_75t_R)\r\n 2 43.84 2435.15 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09369_/Y (OR4x2_ASAP7_75t_R)\r\n 5 41.86 2477.01 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10984_/Y (NOR3x2_ASAP7_75t_R)\r\n 20 54.43 2531.44 ^ wire46500/Y (BUFx16f_ASAP7_75t_R)\r\n 3 113.22 2644.66 ^ wire46499/Y (BUFx16f_ASAP7_75t_R)\r\n 2 74.22 2718.88 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383170_/Y (AND2x2_ASAP7_75t_R)\r\n 14 24.78 2743.66 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383188_/Y (NAND2x2_ASAP7_75t_R)\r\n 12 63.17 2806.83 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383224_/Y (AO21x2_ASAP7_75t_R)\r\n 5 24.83 2831.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_479882_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 11 84.15 2915.81 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732259_/CON (HAxp5_ASAP7_75t_R)\r\n 3 31.45 2947.26 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383227_/Y (INVx2_ASAP7_75t_R)\r\n 2 25.01 2972.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383231_/Y (AND2x2_ASAP7_75t_R)\r\n 2 22.19 2994.46 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732246_/CON (HAxp5_ASAP7_75t_R)\r\n 2 31.03 3025.49 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732246_/SN (HAxp5_ASAP7_75t_R)\r\n 1 31.95 3057.44 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393218_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 40.29 3097.73 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393222_/Y (AND5x2_ASAP7_75t_R)\r\n 1 38.93 3136.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09361_/Y (AO22x2_ASAP7_75t_R)\r\n 1 60.29 3196.95 ^ wire32998/Y (BUFx16f_ASAP7_75t_R)\r\n 1 63.16 3260.11 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09362_/Y (OR4x2_ASAP7_75t_R)\r\n 1 16.20 3276.31 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09363_/Y (OR4x1_ASAP7_75t_R)\r\n 1 19.72 3296.03 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09371_/Y (AO22x1_ASAP7_75t_R)\r\n 3 10.78 3306.81 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09372_/Y (INVx2_ASAP7_75t_R)\r\n 5 32.27 3339.08 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10980_/Y (AND3x4_ASAP7_75t_R)\r\n 2 32.46 3371.54 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_10981_/Y (AND2x6_ASAP7_75t_R)\r\n 6 26.61 3398.15 v wire30552/Y (BUFx16f_ASAP7_75t_R)\r\n 3 117.06 3515.20 v wire30547/Y (BUFx16f_ASAP7_75t_R)\r\n 2 79.46 3594.66 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383202_/Y (AND2x2_ASAP7_75t_R)\r\n 13 30.10 3624.76 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383232_/Y (NAND2x2_ASAP7_75t_R)\r\n 37 104.44 3729.20 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383277_/Y (AO21x2_ASAP7_75t_R)\r\n 8 123.99 3853.19 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383285_/Y (NOR2x2_ASAP7_75t_R)\r\n 2 69.54 3922.74 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383289_/Y (AND2x2_ASAP7_75t_R)\r\n 2 70.43 3993.16 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732263_/SN (HAxp5_ASAP7_75t_R)\r\n 1 35.94 4029.10 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393224_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 33.88 4062.98 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393228_/Y (AND5x2_ASAP7_75t_R)\r\n 1 22.63 4085.61 v wire18339/Y (BUFx12f_ASAP7_75t_R)\r\n 1 90.65 4176.26 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09348_/Y (AO221x2_ASAP7_75t_R)\r\n 1 78.25 4254.51 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09352_/Y (OR4x1_ASAP7_75t_R)\r\n 2 12.50 4267.01 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09353_/Y (INVx1_ASAP7_75t_R)\r\n 2 29.33 4296.34 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13707_/Y (AND3x4_ASAP7_75t_R)\r\n 2 16.51 4312.85 ^ max_length17970/Y (BUFx12f_ASAP7_75t_R)\r\n 2 58.75 4371.60 ^ wire17968/Y (BUFx16f_ASAP7_75t_R)\r\n 4 69.67 4441.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383260_/Y (AND2x4_ASAP7_75t_R)\r\n 8 22.60 4463.87 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_383290_/Y (NAND2x2_ASAP7_75t_R)\r\n 25 39.78 4503.65 v load_slew17553/Y (BUFx16f_ASAP7_75t_R)\r\n 8 52.97 4556.62 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_389614_/Y (OA21x2_ASAP7_75t_R)\r\n 15 27.29 4583.91 v max_length15743/Y (BUFx16f_ASAP7_75t_R)\r\n 6 44.22 4628.14 v wire15739/Y (BUFx16f_ASAP7_75t_R)\r\n 2 96.47 4724.61 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732319_/CON (HAxp5_ASAP7_75t_R)\r\n 10 26.31 4750.92 ^ wire10637/Y (BUFx12f_ASAP7_75t_R)\r\n 9 28.31 4779.22 ^ wire10635/Y (BUFx12f_ASAP7_75t_R)\r\n 5 23.85 4803.08 ^ wire10634/Y (BUFx16f_ASAP7_75t_R)\r\n 3 49.02 4852.10 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393150_/Y (INVx3_ASAP7_75t_R)\r\n 1 19.43 4871.53 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732322_/CON (HAxp5_ASAP7_75t_R)\r\n 2 13.70 4885.23 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732225_/Y (INVx1_ASAP7_75t_R)\r\n 2 54.56 4939.79 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732324_/CON (HAxp5_ASAP7_75t_R)\r\n 2 57.06 4996.85 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_732324_/SN (HAxp5_ASAP7_75t_R)\r\n 1 39.36 5036.22 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393230_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 29.47 5065.69 v system/tile_prci_domain/tile_reset_domain_boom_tile/lsu/_393234_/Y (AND5x2_ASAP7_75t_R)\r\n 1 38.32 5104.01 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09177_/Y (AO22x2_ASAP7_75t_R)\r\n 1 65.68 5169.69 v wire10120/Y (BUFx16f_ASAP7_75t_R)\r\n 1 85.75 5255.45 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09180_/Y (OR4x2_ASAP7_75t_R)\r\n 1 47.72 5303.17 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09181_/Y (OR4x2_ASAP7_75t_R)\r\n 1 14.50 5317.66 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09182_/Y (INVx1_ASAP7_75t_R)\r\n 3 20.96 5338.62 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09346_/Y (AO31x2_ASAP7_75t_R)\r\n 1 22.09 5360.71 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09357_/Y (AND2x2_ASAP7_75t_R)\r\n 3 22.17 5382.88 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/_09375_/Y (NAND3x2_ASAP7_75t_R)\r\n 2 44.87 5427.75 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_13855_/Y (NOR2x2_ASAP7_75t_R)\r\n 4 31.84 5459.59 ^ max_length10066/Y (BUFx16f_ASAP7_75t_R)\r\n 3 46.40 5505.98 ^ wire10064/Y (BUFx16f_ASAP7_75t_R)\r\n 1 74.29 5580.27 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/_14394_/Y (AND2x2_ASAP7_75t_R)\r\n 1 5.61 5585.88 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065683_/Y (INVx1_ASAP7_75t_R)\r\n 2 61.87 5647.75 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065702_/Y (OR5x2_ASAP7_75t_R)\r\n 2 53.28 5701.03 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/_065722_/Y (NAND2x2_ASAP7_75t_R)\r\n 24 24.22 5725.25 ^ max_length8441/Y (BUFx16f_ASAP7_75t_R)\r\n 22 43.01 5768.26 ^ wire8439/Y (BUFx16f_ASAP7_75t_R)\r\n 19 49.84 5818.10 ^ load_slew8429/Y (BUFx16f_ASAP7_75t_R)\r\n 14 47.09 5865.20 ^ wire8426/Y (BUFx16f_ASAP7_75t_R)\r\n 11 48.21 5913.41 ^ max_length8425/Y (BUFx16f_ASAP7_75t_R)\r\n 10 58.85 5972.26 ^ wire8424/Y (BUFx16f_ASAP7_75t_R)\r\n 10 61.11 6033.37 ^ max_length8423/Y (BUFx12f_ASAP7_75t_R)\r\n 11 38.21 6071.58 ^ wire8422/Y (BUFx16f_ASAP7_75t_R)\r\n 25 51.58 6123.15 ^ wire8421/Y (BUFx16f_ASAP7_75t_R)\r\n 6 60.76 6183.91 v system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1678_/Y (INVx11_ASAP7_75t_R)\r\n 24 21.32 6205.24 v max_length4569/Y (BUFx16f_ASAP7_75t_R)\r\n 11 62.98 6268.22 v wire4568/Y (BUFx16f_ASAP7_75t_R)\r\n 10 53.54 6321.76 v wire4567/Y (BUFx16f_ASAP7_75t_R)\r\n 12 73.47 6395.22 v wire4566/Y (BUFx16f_ASAP7_75t_R)\r\n 35 109.03 6504.25 v max_length4564/Y (BUFx16f_ASAP7_75t_R)\r\n 57 67.38 6571.63 v load_slew4563/Y (BUFx16f_ASAP7_75t_R)\r\n 1 95.45 6667.09 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1885_/Y (NAND2x1_ASAP7_75t_R)\r\n 13 52.03 6719.12 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_1886_/Y (OA21x2_ASAP7_75t_R)\r\n 1 30.21 6749.33 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3041_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 30.06 6779.38 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3043_/Y (AND4x1_ASAP7_75t_R)\r\n 1 32.88 6812.26 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3047_/Y (AND5x1_ASAP7_75t_R)\r\n 1 19.43 6831.69 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3048_/Y (OR4x1_ASAP7_75t_R)\r\n 1 29.64 6861.33 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3133_/Y (OA31x2_ASAP7_75t_R)\r\n 2.24 6863.57 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_/D (DFFHQNx2_ASAP7_75t_R)\r\n 6863.57 data arrival time\r\n\r\n 8500.00 8500.00 clock fake_pll_clk (rise edge)\r\n 1445.94 9945.94 clock network delay (propagated)\r\n -10.00 9935.94 clock uncertainty\r\n 0.00 9935.94 clock reconvergence pessimism\r\n 9935.94 ^ system/tile_prci_domain/tile_reset_domain_boom_tile/core/mem_issue_unit/slots_23/_3405_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -10.95 9924.99 library setup time\r\n 9924.99 data required time\r\n---------------------------------------------------------------\r\n 9924.99 data required time\r\n -6863.57 data arrival time\r\n---------------------------------------------------------------\r\n 3061.42 slack (MET)\r\n\r\n\r\nStartpoint: serial_tl_0_bits_out_ready (input port clocked by clock_vir)\r\nEndpoint: system/serial_tl_domain/_1190_\r\n (rising edge-triggered flip-flop clocked by serial_tl_0_clock)\r\nPath Group: serial_tl_0_clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock_vir (rise edge)\r\n 1000.00 1000.00 clock network delay (ideal)\r\n 1700.00 2700.00 v input external delay\r\n 1 0.00 2700.00 v serial_tl_0_bits_out_ready (in)\r\n 1 12.09 2712.09 v input11/Y (BUFx2_ASAP7_75t_R)\r\n 1 21.58 2733.66 v system/serial_tl_domain/_0823_/Y (AND2x6_ASAP7_75t_R)\r\n 1 25.37 2759.03 v wire96183/Y (BUFx12f_ASAP7_75t_R)\r\n 13 259.71 3018.74 v system/serial_tl_domain/_1128_/SN (HAxp5_ASAP7_75t_R)\r\n 3 104.06 3122.80 v system/serial_tl_domain/_0882_/Y (OR3x4_ASAP7_75t_R)\r\n 1 13.63 3136.44 ^ system/serial_tl_domain/_0897_/Y (AOI211x1_ASAP7_75t_R)\r\n 1 22.32 3158.76 ^ system/serial_tl_domain/_0898_/Y (AO221x1_ASAP7_75t_R)\r\n 1 23.94 3182.70 ^ system/serial_tl_domain/_0899_/Y (OR4x2_ASAP7_75t_R)\r\n 1 20.19 3202.89 ^ system/serial_tl_domain/_0900_/Y (OA22x2_ASAP7_75t_R)\r\n 0.01 3202.90 ^ system/serial_tl_domain/_1190_/D (DFFHQNx2_ASAP7_75t_R)\r\n 3202.90 data arrival time\r\n\r\n 8500.00 8500.00 clock serial_tl_0_clock (rise edge)\r\n 99.58 8599.58 clock network delay (propagated)\r\n -10.00 8589.58 clock uncertainty\r\n 0.00 8589.58 clock reconvergence pessimism\r\n 8589.58 ^ system/serial_tl_domain/_1190_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -5.33 8584.25 library setup time\r\n 8584.25 data required time\r\n---------------------------------------------------------------\r\n 8584.25 data required time\r\n -3202.90 data arrival time\r\n---------------------------------------------------------------\r\n 5381.35 slack (MET)\r\n```\r\n\r\n"}, {"user": "To get this to build in Yosys, I had to mock fake_pll_clk:\r\n\r\nhttps://github.com/The-OpenROAD-Project/megaboom/blob/931c2a882510bf5735dbf5efab1a8c474f838c49/mock/ChipTop.sv#L31\r\n\r\nWhereas Chipyard has this clock coming out of a PLL:\r\n\r\nhttps://github.com/The-OpenROAD-Project/megaboom/blob/931c2a882510bf5735dbf5efab1a8c474f838c49/rtl/ChipTop.sv#L150\r\n\r\nI don't know what the relationships are between these clocks, this is my first cut .sdc file that I used:\r\n\r\nhttps://github.com/The-OpenROAD-Project/megaboom/blob/main/constraints-chiptop.sdc"}, {"user": "I've reached out to Chipyard to get some help with the .sdc file for the clocks: https://groups.google.com/g/chipyard/c/PzVcnnqRwf8/m/t1pIDPnuAwAJ"}, {"user": "Failed in global routing, ca. 7000 seconds.\r\n\r\n`make macro_place_issue` reproducible case for mpl2: https://drive.google.com/file/d/1w_vIUNtWp7dBntP9i7WGEkgtGhTRD6M_/view?usp=sharing\r\n\r\nI suppose I could try to flatten the design for the two macros with contention, but if macro placement can't place these two bigger macros, what are the chances it can place many smaller macros(there are SRAMs inside the branch predictor and the data cache that have all the congestion on top)?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/520a354a-1e5e-42a3-b3c4-090050a08c42)\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/a4a48871-f7c9-4445-aff2-4621b73f551a)\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/199c6c47-e6ba-4471-8f98-1befb9677a22)\r\n\r\nIntentionally, BranchPredictor has all the pins on the left side. This is to break the rotational and mirroring symmetry such that mpl2 can try different directions to find one that is better.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/7272e784-c63e-4209-b0ac-3dd59f43b22d)\r\n\r\nThis is odd... Why is the macro rotated R180? That puts the pins on the right hand side... I would have thought, looking at the floorplan, that having the pins on the left side was better, given the placement...\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c54e3016-9444-4b17-805f-9a82a1d003d7)\r\n"}, {"assistant": "You can zoom in with the mouse wheel in the CTS view. If you do so on the odd branch on the right you can select the end points and see what they are. That would be helpful.\r\n\r\nThe setup paths with tons of hold buffers are quite odd. I suspect an SDC issue.\r\n\r\nYou might lower the placement density slightly to see if that helps with congestion. \r\n\r\nA test case for the flipping is needed to say much about it. Perhaps the connections go to pins on the right?"}, {"user": "Broke out #4513 and #4512 for further investigation"}, {"user": "So, I think I understand more or less what is going on.\r\n\r\nThe Verilog is not the way I want it yet. It contains a fake PLL that is controlled via the TileLink interface at the top level that multiplies the top level clock to the core frequency. This PLL is set up out of bounds of a single core.\r\n\r\nhttps://github.com/ucb-bar/chipyard/blob/c9fa23edf049f35f9b8e6291b0e2b82b1056540b/generators/chipyard/src/main/scala/clocking/ClockBinders.scala#L12"}]} +{"messages": [{"user": "\r\n\r\nI looked in OpenROAD documentation for Global Placement and Gate Resizer to get more detail about the units of the pad_left/right parameters of the `global_placement` command [(GPL)](https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/gpl) and the use/behavior of `repair_clock_inverters` [(RSZ).](https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/rsz/README.md) \r\n\r\nBoth the variables units description is missing (while present for DPL (site count units), but since the two tools are different I don't want to assume it is the same for both) in GPL, and there is no description concerning `repair_clock_inverters` use case or behavior description (like there would be for `repair_timing` or `repair_design`.\r\n\r\nWhat are the units of pad_left/right, and what does `repair_clock_inverters` do/how to use it ?"}, {"assistant": "The units are sites from the LEF.\r\n\r\nrepair_clock_inverters is useful when you have an inverter in the clock tree that would split the tree. It clones the inverter so you have one per flop instead."}, {"assistant": "before CTS see https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/181e9133776117ea1b9f74dbacbfdaadff8c331b/flow/scripts/cts.tcl#L7\r\n\r\nYou might benefit from investigating how ORFS works"}]} +{"messages": [{"user": "I would like to get https://github.com/The-OpenROAD-Project/megaboom to the point where it goes through a full build and then incrementally improve.\r\n\r\nThe idea with such big projects is to get the build under CI, separate concerns and continously improve...\r\n\r\nCurrently it stops in global routing:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/02068fde-3bb1-4ae7-a7b2-45f9a83db528)\r\n\r\nCurrent options for DigitalTop:\r\n\r\nhttps://github.com/The-OpenROAD-Project/megaboom/blob/391bbbd8d59b93b15b1cdb850294696a60d2dd4f/BUILD.bazel#L1636\r\n\r\n- the yellow are hold cells. Given the 2000+ps skew in the clock tree, I don't find it shocking that there's ca. 100000 hold cells. I have set clock_latency to 3300, which I could try to change to 1000 to be closer to what is actually going on, but that still leaves 1000ps of clock skew on either side of that... There is the familiar hold cell log jam at the pins...\r\n- there is a lot of congestion on top of the macro. What does that mean and how can it be fixed?\r\n- reduce placement density?\r\n- Increase number of global routing iterations from 30 to 100?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/f32c23ae-cb26-4b40-a649-c47071f3a21b)\r\n\r\nIf you want to have a look... \r\n\r\n1. Build OpenROAD https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/master/docs/user/BuildLocally.md\r\n2. download. 1.3gByte. https://drive.google.com/file/d/1HcAU-pOsPvhcMGKdSWvy_mV17By0qH65/view?usp=sharing\r\n3. untar\r\n4. run:\r\n\r\n```\r\n$ . ~/OpenROAD-flow-scripts/env.sh \r\nOPENROAD: /home/oyvind/OpenROAD-flow-scripts/tools/OpenROAD\r\n$ ./run-me-DigitalTop-asap7-base.sh\r\n```\r\n\r\n"}, {"assistant": "Some miscellaneous thoughts:\r\n\r\n* The keep-out region around the macros seems higher than necessary. Can it be shrunk?\r\n* Is there a way to push the macros all the way to the edges? If there are no pins on one side, then it should be fine to push it all the way to the edge. Right now, the gap between the macro and the edge is just wasted space.\r\n\r\n> ![image](https://private-user-images.githubusercontent.com/2798822/294173465-f32c23ae-cb26-4b40-a649-c47071f3a21b.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MDQzODc5MjUsIm5iZiI6MTcwNDM4NzYyNSwicGF0aCI6Ii8yNzk4ODIyLzI5NDE3MzQ2NS1mMzJjMjNhZS1jYjI2LTRiNDAtYTY0OS1jNDcwNzFmM2EyMWIucG5nP1gtQW16LUFsZ29yaXRobT1BV1M0LUhNQUMtU0hBMjU2JlgtQW16LUNyZWRlbnRpYWw9QUtJQVZDT0RZTFNBNTNQUUs0WkElMkYyMDI0MDEwNCUyRnVzLWVhc3QtMSUyRnMzJTJGYXdzNF9yZXF1ZXN0JlgtQW16LURhdGU9MjAyNDAxMDRUMTcwMDI1WiZYLUFtei1FeHBpcmVzPTMwMCZYLUFtei1TaWduYXR1cmU9NTc2NGJiMzAxYjU3ZmFkMzc3ZDk4OWExM2M2ZWY3NzhiOTdhMDJmMjc0N2MwZDllNzU0MzEyZDA0NzY5ZjI2ZiZYLUFtei1TaWduZWRIZWFkZXJzPWhvc3QmYWN0b3JfaWQ9MCZrZXlfaWQ9MCZyZXBvX2lkPTAifQ.1T6oUzQvPgbEHYZep6GOnSjXk8Xz7V07M8CsSou38jI)\r\n\r\n* I'm assuming the highlighted yellow are the hold cells? If so, it looks like they are feeding towards the I/Os. You should double check that your I/O constraints are in reference to the clock tree latency so that they are reasonable. For example, if the input constraint is 50ps, but the capture register has a 2000ps clock latency, then the tools need to insert 1950ps of hold buffers. If the output constraint is 50ps and the launch register clock latency is 2000ps, the best it could do is -1950ps slack.\r\n* Do your large macros have the clock tree latency annotated in them when extracted? I believe that CTS support for this was added to help balancing, but I am not sure if the GUI or the skew report reflect this. If a macro and a register have 1000ps of skew, it could be totally fine if the macro has an internal clock tree of 1000ps.\r\n* Even with that consideration, the clock tree looks very unbalanced. There might be something breaking down with the algorithm."}, {"assistant": "I think resolve the clock skew will go a long way to resolving the other problems so let's start there. Even without insertion delay the tree is quite skewed.\r\n\r\nMACRO_PLACE_HALO=\"20 20\" seems rather large. How did you pick those?"}, {"user": "Still cooking, but 100 global routing iterations + some fixes from the list above and only 6 violations. Lets see if it can push through...\r\n\r\nMany more things to test and tweak in the design, this is just intended to be a baseline. \r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/9fc2d3e7-1d39-4615-b3ae-2a714bcb1f32)\r\n"}, {"assistant": "In looking at auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock it goes into a user buffer prci_ctrl_domain/_1019_. I'm not clear why we would have a user buffer in the clock tree. Did you skip remove_buffers in floorplanning?"}, {"assistant": "How did you run cts? I see 75 instances named 'cklbuf*'. The clkbuf seem only related to a small area (showing only 'Clock tree' instances):\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/4dfbc6d9-ab65-4b1a-8e4a-a1d3ed27c2dd)\r\n\r\nI see 7535 instances named 'load_slew*'. It seems most of the tree is not actually clock buffers:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/05340a29-8d33-42b8-a98b-9c65969a1d56)\r\n"}, {"user": "@maliberty So it seems to me that outputting the clock from a module, so that you have the clock coming in with 0 insertion latency and the clock output with the clock tree leaf insertion latency would be useful to deal with a very large clock tree latency as follows:\r\n\r\nCreate FIFOs on the outside that take the input clock for the module with large clock tree insertion latency as well as the output clock. Now you have two clock domains, use this FIFO to cross the two clock domain. The input/output pins of the module with large clock tree insertion latency can now have a clock latency constraints that is approximately equal to the clock tree insertion latency, which relaxes the constraints within the module.\r\n\r\nIt is a bit annoying to set up that .sdc file, because you can't know the clock tree insertion latency until after you have run CTS, so a few iterations are probably needed...\r\n"}, {"user": "Another datapoint, running times for this design (macros not included):\r\n\r\n```\r\nLog Elapsed seconds\r\n1_1_yosys 2614\r\n1_1_yosys_hier_report 2518\r\n2_1_floorplan 186\r\n2_2_floorplan_io 6\r\n2_4_floorplan_macro 312\r\n2_5_floorplan_tapcell 108\r\n2_6_floorplan_pdn 234\r\n3_1_place_gp_skip_io 322\r\n3_2_place_iop 12\r\n3_3_place_gp 2904\r\n3_4_place_resized 590\r\n3_5_place_dp 683\r\n4_1_cts 5259\r\n```\r\n"}, {"assistant": "The cts runtime is likely mostly comprised of rsz runtime buffering that huge clock net. \r\n\r\nI haven't looked at the floorplan test case but I think I know what's going on. remove_buffers will not remove a buffer that is between a primary input and output (that would leave a pure feedthru which is a generally a bad thing). So it likely removes all the buffers but one as you have both in and out clock ports tied together.\r\n\r\nCTS sees the buffer and assumes you have a manually constructed tree and skips as shown above.\r\n\r\nThis is not a methodology that OR supports. It seems a difficult one to do in general as you have no real idea what the skew requirement on the output pin should be. I don't understand chipyard or this design so I'm not sure what to suggest here.\r\n\r\nre \"However, Yosys can't compile ChipTop, nor flatten the entire design(it would run forever), so I only build DigitalTop and hence we get clocks going out at the top level.\" Can you flatten just DigitalTop into ChipTop and not the whole design?"}, {"user": "@rovinski \r\n> Bad logical designs can absolutely hamper physical design, and this is one example. It is taking away options from the algorithms and defecting to the user to make the proper decision, which is the opposite of what is wanted for automated design and design space exploration.\r\n> \r\n> I have done a decent amount of clock tree structuring for taped out chips, and this is simply a bad methodology except in very specific hand-tuned circumstances. It only works if you ensure the tree is manually balanced and the only reason to do it is to save clock power by reducing the branching factor and/or to reduce clock tree jitter for specific endpoints.\r\n\r\nDon't take my word for what MegaBoom is doing and not doing and why. I just have a default assumption that the authors knew what they were doing and did what they did the way they did for a reason...\r\n\r\nSince I know they are making a CPU, it makes sense to me(a default assumption until I learn more) that the memory master interface of that CPU is running on a different clock domain and that it is providing the clock which slave devices must use is an output.\r\n\r\nOr.... perhaps I'm not generating the Verilog in the right way...? The AXI output clock for the memory master interface might be there for the simulation test harness rather than synthesis?\r\n\r\nThis Hammer file is for SonicBOOM (a smaller design than MegaBoom), it doesn't offer any clues as to what the AXI output clock means...\r\n\r\nhttps://github.com/ucb-bar/chipyard/blob/main/vlsi/example-designs/sky130-openroad.yml"}, {"user": "This is a screenshot from after global route of ChipTop.sv:\r\n\r\n- Standalone reproduction case for CTS in this case which includes the global routing result & congestion report: https://drive.google.com/file/d/1sAFbG_MpjmaN4inulYWUqbeuPsYLqx73/view?usp=sharing\r\n- I was wrong that ChipTop.sv didn't go through synthesis with Yosys. I can't recall what problems I was having, though there are some simulation only .sv files that won't go through Yosys that are not used by ChipTop, perhaps I was confused by those?\r\n- Only two global route failures indicated (white crosses)\r\n- How can I tell if I have a clock tree?\r\n- There are significant caveats still in that the macro abstracts are mocked: they only went through floorplan. I'll do a full build later. Still it is possible to learn something at this stage.\r\n- clock_uncore_clock is fed through to axi4_mem_0_clock and the text says that it is clocked by clock_uncore_clock_vir, which makes sense. clock_uncore_clock_vir is clock_uncore_clock + source latency.\r\n\r\n```\r\nStartpoint: clock_uncore_clock (clock source 'clock_uncore_clock')\r\nEndpoint: axi4_mem_0_clock (output port clocked by clock_uncore_clock_vir)\r\n```\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/abb63910-5d13-4ef2-b837-cb8060439fd1)\r\n\r\nThere is a second clock into the design, but my guess is that this has something to do with a peripheral or other, not the CPU:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/66e066a5-c2b6-4054-994c-7e02b7a74da1)\r\n\r\n```\r\nOpenROAD v2.0-11704-gfb0df7fb7 \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\n[WARNING STA-0357] virtual clock clock_uncore_clock_vir can not be propagated.\r\nEstimating parasitics\r\n[WARNING GUI-0076] QXcbConnection: XCB error: 3 (BadWindow), sequence: 3175, resource id: 16788675, major code: 40 (TranslateCoords), minor code: 0\r\n>>> report_checks -path_delay max -fields {fanout skew}\r\nStartpoint: reset_io (input port clocked by clock_uncore_clock_vir)\r\nEndpoint: system/prci_ctrl_domain/_0952_\r\n (recovery check against rising-edge clock clock_uncore_clock)\r\nPath Group: asynchronous\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock_uncore_clock_vir (rise edge)\r\n 1000.00 1000.00 clock network delay (ideal)\r\n 1700.00 2700.00 v input external delay\r\n 1 0.00 2700.00 v reset_io (in)\r\n 1 12.54 2712.54 v input87/Y (BUFx12f_ASAP7_75t_R)\r\n 1 70.17 2782.71 v wire49778/Y (BUFx16f_ASAP7_75t_R)\r\n 4 59.30 2842.00 ^ system/prci_ctrl_domain/_0722_/Y (INVx2_ASAP7_75t_R)\r\n 0.53 2842.54 ^ system/prci_ctrl_domain/_0952_/SETN (DFFASRHQNx1_ASAP7_75t_R)\r\n 2842.54 data arrival time\r\n\r\n 8500.00 8500.00 clock clock_uncore_clock (rise edge)\r\n 871.54 9371.54 clock network delay (propagated)\r\n -10.00 9361.54 clock uncertainty\r\n 0.00 9361.54 clock reconvergence pessimism\r\n 9361.54 ^ system/prci_ctrl_domain/_0952_/CLK (DFFASRHQNx1_ASAP7_75t_R)\r\n 15.79 9377.33 library recovery time\r\n 9377.33 data required time\r\n---------------------------------------------------------------\r\n 9377.33 data required time\r\n -2842.54 data arrival time\r\n---------------------------------------------------------------\r\n 6534.79 slack (MET)\r\n\r\n\r\nStartpoint: _32_ (negative level-sensitive latch clocked by clock_uncore_clock)\r\nEndpoint: _10_\r\n (rising clock gating-check end-point clocked by clock_uncore_clock)\r\nPath Group: gated clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 4250.00 4250.00 clock clock_uncore_clock (fall edge)\r\n 532.14 4782.14 clock network delay (propagated)\r\n 0.00 4782.14 v _32_/CLK (DLLx1_ASAP7_75t_R)\r\n 1 45.86 4828.00 v _32_/Q (DLLx1_ASAP7_75t_R)\r\n 0.02 4828.02 v _10_/B (AND2x4_ASAP7_75t_R)\r\n 4828.02 data arrival time\r\n\r\n 8500.00 8500.00 clock clock_uncore_clock (rise edge)\r\n 492.25 8992.25 clock network delay (propagated)\r\n -10.00 8982.25 clock uncertainty\r\n 0.00 8982.25 clock reconvergence pessimism\r\n 8982.25 ^ _10_/A (AND2x4_ASAP7_75t_R)\r\n 0.00 8982.25 clock gating setup time\r\n 8982.25 data required time\r\n---------------------------------------------------------------\r\n 8982.25 data required time\r\n -4828.02 data arrival time\r\n---------------------------------------------------------------\r\n 4154.23 slack (MET)\r\n\r\n\r\nStartpoint: system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095120_\r\n (rising edge-triggered flip-flop clocked by clock_uncore_clock)\r\nEndpoint: system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_80484_\r\n (rising edge-triggered flip-flop clocked by clock_uncore_clock)\r\nPath Group: clock_uncore_clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock_uncore_clock (rise edge)\r\n 1899.28 1899.28 clock network delay (propagated)\r\n 0.00 1899.28 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095120_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 6 75.38 1974.65 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095120_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 1 22.16 1996.82 ^ hold78251/Y (BUFx2_ASAP7_75t_R)\r\n 3 20.28 2017.09 ^ hold24171/Y (BUFx2_ASAP7_75t_R)\r\n 1 18.71 2035.80 ^ hold78252/Y (BUFx2_ASAP7_75t_R)\r\n 6 44.43 2080.23 ^ hold14462/Y (BUFx2_ASAP7_75t_R)\r\n 14 32.26 2112.50 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052537_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 10 114.99 2227.49 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095077_/CON (HAxp5_ASAP7_75t_R)\r\n 4 27.96 2255.44 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052831_/Y (INVx4_ASAP7_75t_R)\r\n 2 30.15 2285.59 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_064284_/Y (AND2x2_ASAP7_75t_R)\r\n 6 64.65 2350.24 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095079_/CON (HAxp5_ASAP7_75t_R)\r\n 6 43.78 2394.03 ^ wire30543/Y (BUFx12_ASAP7_75t_R)\r\n 2 20.98 2415.01 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052672_/Y (INVx11_ASAP7_75t_R)\r\n 3 15.28 2430.28 v max_length29072/Y (BUFx12f_ASAP7_75t_R)\r\n 3 32.78 2463.06 v max_length29071/Y (BUFx10_ASAP7_75t_R)\r\n 13 69.31 2532.38 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052686_/Y (OR4x2_ASAP7_75t_R)\r\n 2 63.47 2595.85 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052855_/Y (OR3x4_ASAP7_75t_R)\r\n 2 43.49 2639.34 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052856_/Y (AND3x4_ASAP7_75t_R)\r\n 16 17.48 2656.82 v wire25227/Y (BUFx16f_ASAP7_75t_R)\r\n 4 89.89 2746.71 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052858_/Y (AND4x2_ASAP7_75t_R)\r\n 1 21.42 2768.12 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09468_/Y (NAND2x2_ASAP7_75t_R)\r\n 3 27.61 2795.74 ^ wire22599/Y (BUFx12f_ASAP7_75t_R)\r\n 2 63.18 2858.92 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09478_/Y (OA21x2_ASAP7_75t_R)\r\n 1 21.19 2880.10 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09481_/Y (OR3x4_ASAP7_75t_R)\r\n 1 15.57 2895.67 ^ hold11148/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.93 2911.60 ^ hold8869/Y (BUFx2_ASAP7_75t_R)\r\n 3 22.93 2934.53 ^ hold11149/Y (BUFx2_ASAP7_75t_R)\r\n 5 33.02 2967.55 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_10524_/Y (NOR3x2_ASAP7_75t_R)\r\n 2 32.14 2999.70 v wire20615/Y (BUFx16f_ASAP7_75t_R)\r\n 19 76.62 3076.32 v wire20614/Y (BUFx16f_ASAP7_75t_R)\r\n 30 123.33 3199.65 v wire20613/Y (BUFx16f_ASAP7_75t_R)\r\n 16 26.25 3225.90 v wire20612/Y (BUFx16f_ASAP7_75t_R)\r\n 1 60.57 3286.46 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140035_/Y (AND3x1_ASAP7_75t_R)\r\n 9 19.01 3305.47 v wire19271/Y (BUFx16f_ASAP7_75t_R)\r\n 1 89.99 3395.47 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140050_/Y (AND2x2_ASAP7_75t_R)\r\n 7 36.72 3432.19 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140051_/Y (AO21x2_ASAP7_75t_R)\r\n 6 51.35 3483.53 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140087_/Y (INVx13_ASAP7_75t_R)\r\n 5 35.71 3519.24 ^ wire16755/Y (BUFx16f_ASAP7_75t_R)\r\n 7 104.20 3623.44 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267695_/CON (HAxp5_ASAP7_75t_R)\r\n 5 26.52 3649.96 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140053_/Y (INVx3_ASAP7_75t_R)\r\n 2 31.74 3681.71 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140060_/Y (AND3x1_ASAP7_75t_R)\r\n 2 23.56 3705.27 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267682_/CON (HAxp5_ASAP7_75t_R)\r\n 2 24.40 3729.67 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267682_/SN (HAxp5_ASAP7_75t_R)\r\n 1 28.23 3757.89 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149590_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 43.36 3801.25 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149594_/Y (AND5x2_ASAP7_75t_R)\r\n 1 24.45 3825.70 ^ wire13571/Y (BUFx12f_ASAP7_75t_R)\r\n 1 64.03 3889.73 ^ wire13570/Y (BUFx16f_ASAP7_75t_R)\r\n 1 79.93 3969.66 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09472_/Y (AO221x2_ASAP7_75t_R)\r\n 1 68.57 4038.23 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09473_/Y (OR5x2_ASAP7_75t_R)\r\n 1 13.72 4051.94 ^ hold11977/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.26 4064.20 ^ hold7674/Y (BUFx2_ASAP7_75t_R)\r\n 2 14.63 4078.84 ^ hold11978/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.72 4094.55 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09475_/Y (OA21x2_ASAP7_75t_R)\r\n 2 20.63 4115.18 ^ hold7675/Y (BUFx2_ASAP7_75t_R)\r\n 5 24.11 4139.29 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_10522_/Y (NOR3x2_ASAP7_75t_R)\r\n 1 22.06 4161.35 v hold18417/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.68 4174.03 v hold10243/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.21 4186.24 v hold18418/Y (BUFx2_ASAP7_75t_R)\r\n 2 20.53 4206.77 v hold7676/Y (BUFx2_ASAP7_75t_R)\r\n 1 18.19 4224.96 v hold18419/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.59 4237.55 v hold10244/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.38 4252.93 v hold18420/Y (BUFx2_ASAP7_75t_R)\r\n 2 13.31 4266.24 v load_slew12502/Y (BUFx12f_ASAP7_75t_R)\r\n 1 15.05 4281.29 v hold18421/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.37 4296.67 v hold10245/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.35 4312.02 v hold18422/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.30 4327.32 v hold7677/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.27 4342.59 v hold18423/Y (BUFx2_ASAP7_75t_R)\r\n 3 30.80 4373.39 v hold10246/Y (BUFx2_ASAP7_75t_R)\r\n 3 35.71 4409.10 v max_length12501/Y (BUFx16f_ASAP7_75t_R)\r\n 17 68.42 4477.52 v wire12498/Y (BUFx16f_ASAP7_75t_R)\r\n 29 122.51 4600.04 v max_length12497/Y (BUFx16f_ASAP7_75t_R)\r\n 18 24.10 4624.14 v max_length12496/Y (BUFx16f_ASAP7_75t_R)\r\n 3 67.14 4691.28 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140063_/Y (AND3x4_ASAP7_75t_R)\r\n 10 59.39 4750.67 v max_length12300/Y (BUFx16f_ASAP7_75t_R)\r\n 3 72.57 4823.25 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140076_/Y (XNOR2x2_ASAP7_75t_R)\r\n 9 20.37 4843.61 ^ load_slew11681/Y (BUFx16f_ASAP7_75t_R)\r\n 5 23.34 4866.96 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_201351_/Y (CKINVDCx16_ASAP7_75t_R)\r\n 3 45.17 4912.12 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267727_/CON (HAxp5_ASAP7_75t_R)\r\n 3 20.27 4932.39 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140092_/Y (INVx2_ASAP7_75t_R)\r\n 1 21.44 4953.83 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267721_/CON (HAxp5_ASAP7_75t_R)\r\n 2 16.81 4970.65 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267668_/Y (INVx1_ASAP7_75t_R)\r\n 2 57.58 5028.23 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267723_/SN (HAxp5_ASAP7_75t_R)\r\n 1 30.13 5058.35 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149595_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 35.26 5093.62 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149601_/Y (AND5x2_ASAP7_75t_R)\r\n 1 34.85 5128.46 v wire8234/Y (BUFx16f_ASAP7_75t_R)\r\n 1 69.42 5197.89 v wire8233/Y (BUFx16f_ASAP7_75t_R)\r\n 1 86.50 5284.38 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09501_/Y (AO221x2_ASAP7_75t_R)\r\n 1 64.90 5349.29 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09502_/Y (OR4x2_ASAP7_75t_R)\r\n 1 15.04 5364.33 v hold11691/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.71 5377.04 v hold8103/Y (BUFx2_ASAP7_75t_R)\r\n 2 15.24 5392.28 v hold11692/Y (BUFx2_ASAP7_75t_R)\r\n 1 8.30 5400.59 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09503_/Y (NOR2x1_ASAP7_75t_R)\r\n 1 16.07 5416.66 ^ hold11693/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.98 5428.63 ^ hold8104/Y (BUFx2_ASAP7_75t_R)\r\n 2 14.25 5442.89 ^ hold11694/Y (BUFx2_ASAP7_75t_R)\r\n 6 33.66 5476.55 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_13871_/Y (AND3x4_ASAP7_75t_R)\r\n 1 19.94 5496.49 ^ hold17405/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.17 5508.66 ^ hold11980/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.81 5520.46 ^ hold17406/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.68 5532.14 ^ hold11695/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.84 5543.97 ^ hold11981/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.84 5555.81 ^ hold8105/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.69 5567.50 ^ hold11982/Y (BUFx2_ASAP7_75t_R)\r\n 1 11.65 5579.15 ^ hold11696/Y (BUFx2_ASAP7_75t_R)\r\n 1 14.92 5594.07 ^ hold11983/Y (BUFx2_ASAP7_75t_R)\r\n 2 13.10 5607.17 ^ max_length7476/Y (BUFx12f_ASAP7_75t_R)\r\n 1 16.07 5623.24 ^ hold11984/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.88 5639.12 ^ hold11697/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.95 5655.07 ^ hold11985/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.87 5670.94 ^ hold8106/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.89 5686.83 ^ hold11986/Y (BUFx2_ASAP7_75t_R)\r\n 2 26.49 5713.32 ^ hold11698/Y (BUFx2_ASAP7_75t_R)\r\n 2 26.12 5739.44 ^ hold11987/Y (BUFx2_ASAP7_75t_R)\r\n 3 20.02 5759.46 ^ wire7475/Y (BUFx16f_ASAP7_75t_R)\r\n 6 50.30 5809.76 ^ max_length7474/Y (BUFx12f_ASAP7_75t_R)\r\n 2 66.91 5876.68 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140099_/Y (AND2x2_ASAP7_75t_R)\r\n 1 17.15 5893.83 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_140100_/Y (NAND2x2_ASAP7_75t_R)\r\n 8 30.84 5924.67 v wire6776/Y (BUFx16f_ASAP7_75t_R)\r\n 13 114.72 6039.39 v load_slew6775/Y (BUFx16f_ASAP7_75t_R)\r\n 1 54.63 6094.02 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_146049_/Y (OR2x2_ASAP7_75t_R)\r\n 7 41.21 6135.24 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_146050_/Y (OA21x2_ASAP7_75t_R)\r\n 9 39.67 6174.90 v wire5396/Y (BUFx16f_ASAP7_75t_R)\r\n 5 51.31 6226.22 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267763_/CON (HAxp5_ASAP7_75t_R)\r\n 5 17.32 6243.54 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149526_/Y (INVx5_ASAP7_75t_R)\r\n 1 56.08 6299.62 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267765_/CON (HAxp5_ASAP7_75t_R)\r\n 2 29.02 6328.63 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267663_/Y (INVx1_ASAP7_75t_R)\r\n 2 126.39 6455.02 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267767_/SN (HAxp5_ASAP7_75t_R)\r\n 1 54.46 6509.49 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149603_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 37.55 6547.04 v system/tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149608_/Y (AND5x2_ASAP7_75t_R)\r\n 1 37.85 6584.88 v wire4143/Y (BUFx16f_ASAP7_75t_R)\r\n 1 69.84 6654.72 v wire4142/Y (BUFx16f_ASAP7_75t_R)\r\n 1 84.81 6739.53 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09493_/Y (AO221x2_ASAP7_75t_R)\r\n 1 57.90 6797.43 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09494_/Y (OR4x2_ASAP7_75t_R)\r\n 1 14.94 6812.38 v hold30872/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.79 6825.17 v hold13130/Y (BUFx2_ASAP7_75t_R)\r\n 2 14.65 6839.82 v hold30873/Y (BUFx2_ASAP7_75t_R)\r\n 2 20.21 6860.03 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09495_/Y (OR2x2_ASAP7_75t_R)\r\n 1 14.23 6874.25 v hold30874/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.10 6886.36 v hold13131/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.38 6898.74 v hold30875/Y (BUFx2_ASAP7_75t_R)\r\n 1 13.47 6912.20 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09505_/Y (AO21x1_ASAP7_75t_R)\r\n 1 12.83 6925.03 v hold30876/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.37 6937.40 v hold13132/Y (BUFx2_ASAP7_75t_R)\r\n 1 15.35 6952.75 v hold30877/Y (BUFx2_ASAP7_75t_R)\r\n 17 31.60 6984.35 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_09506_/Y (NOR3x2_ASAP7_75t_R)\r\n 1 22.33 7006.68 ^ hold32043/Y (BUFx2_ASAP7_75t_R)\r\n 1 12.37 7019.06 ^ hold30878/Y (BUFx2_ASAP7_75t_R)\r\n 4 22.96 7042.02 ^ hold13133/Y (BUFx2_ASAP7_75t_R)\r\n 35 24.88 7066.90 ^ load_slew4133/Y (BUFx16f_ASAP7_75t_R)\r\n 2 26.42 7093.32 ^ hold13134/Y (BUFx2_ASAP7_75t_R)\r\n 5 31.12 7124.44 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/_13971_/Y (AND2x6_ASAP7_75t_R)\r\n 2 27.47 7151.91 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/_3835_/Y (INVx2_ASAP7_75t_R)\r\n 1 14.40 7166.30 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/_5294_/Y (NOR2x2_ASAP7_75t_R)\r\n 5 17.30 7183.60 ^ wire3988/Y (BUFx16f_ASAP7_75t_R)\r\n 1 84.04 7267.64 ^ wire3987/Y (BUFx16f_ASAP7_75t_R)\r\n 8 66.05 7333.69 ^ wire3986/Y (BUFx16f_ASAP7_75t_R)\r\n 9 136.20 7469.90 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_52698_/Y (AND4x2_ASAP7_75t_R)\r\n 6 60.97 7530.87 ^ wire3601/Y (BUFx16f_ASAP7_75t_R)\r\n 10 86.11 7616.98 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_54157_/Y (AND2x6_ASAP7_75t_R)\r\n 14 23.34 7640.32 ^ wire2977/Y (BUFx16f_ASAP7_75t_R)\r\n 8 50.78 7691.10 ^ max_length2976/Y (BUFx12f_ASAP7_75t_R)\r\n 16 39.60 7730.70 ^ max_length2975/Y (BUFx16f_ASAP7_75t_R)\r\n 14 17.45 7748.16 ^ wire2974/Y (BUFx16f_ASAP7_75t_R)\r\n 16 29.41 7777.57 ^ wire2973/Y (BUFx16f_ASAP7_75t_R)\r\n 3 77.98 7855.55 ^ wire2972/Y (BUFx16f_ASAP7_75t_R)\r\n 2 82.43 7937.98 v system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_54165_/Y (NOR2x2_ASAP7_75t_R)\r\n 10 30.56 7968.54 v max_length1585/Y (BUFx16f_ASAP7_75t_R)\r\n 12 70.74 8039.28 v load_slew1584/Y (BUFx12f_ASAP7_75t_R)\r\n 8 18.25 8057.53 v max_length1583/Y (BUFx12f_ASAP7_75t_R)\r\n 11 46.63 8104.16 v load_slew1582/Y (BUFx16f_ASAP7_75t_R)\r\n 12 55.12 8159.28 v wire1580/Y (BUFx16f_ASAP7_75t_R)\r\n 12 57.79 8217.07 v max_length1579/Y (BUFx16f_ASAP7_75t_R)\r\n 1 39.31 8256.38 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_54636_/Y (AOI221x1_ASAP7_75t_R)\r\n 0.01 8256.39 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_80484_/D (DFFHQNx2_ASAP7_75t_R)\r\n 8256.39 data arrival time\r\n\r\n 8500.00 8500.00 clock clock_uncore_clock (rise edge)\r\n 380.41 8880.41 clock network delay (propagated)\r\n -10.00 8870.41 clock uncertainty\r\n 0.00 8870.41 clock reconvergence pessimism\r\n 8870.41 ^ system/tile_prci_domain/tile_reset_domain/boom_tile/core/fp_rename_stage/maptable/_80484_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -5.21 8865.20 library setup time\r\n 8865.20 data required time\r\n---------------------------------------------------------------\r\n 8865.20 data required time\r\n -8256.39 data arrival time\r\n---------------------------------------------------------------\r\n 608.81 slack (MET)\r\n\r\n\r\nStartpoint: clock_uncore_clock (clock source 'clock_uncore_clock')\r\nEndpoint: axi4_mem_0_clock (output port clocked by clock_uncore_clock_vir)\r\nPath Group: clock_uncore_clock_vir\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 4250.00 4250.00 clock clock_uncore_clock (fall edge)\r\n 1775.06 6025.06 clock network delay\r\n 6025.06 v axi4_mem_0_clock (out)\r\n 6025.06 data arrival time\r\n\r\n 8500.00 8500.00 clock clock_uncore_clock_vir (rise edge)\r\n 1000.00 9500.00 clock network delay (ideal)\r\n -10.00 9490.00 clock uncertainty\r\n 0.00 9490.00 clock reconvergence pessimism\r\n -1700.00 7790.00 output external delay\r\n 7790.00 data required time\r\n---------------------------------------------------------------\r\n 7790.00 data required time\r\n -6025.06 data arrival time\r\n---------------------------------------------------------------\r\n 1764.93 slack (MET)\r\n\r\n\r\nStartpoint: serial_tl_bits_out_ready\r\n (input port clocked by clock_uncore_clock_vir)\r\nEndpoint: system/subsystem_fbus/out_async/_1122_\r\n (rising edge-triggered flip-flop clocked by serial_tl_clock)\r\nPath Group: serial_tl_clock\r\nPath Type: max\r\n\r\nFanout Delay Time Description\r\n---------------------------------------------------------------\r\n 0.00 0.00 clock clock_uncore_clock_vir (rise edge)\r\n 1000.00 1000.00 clock network delay (ideal)\r\n 1700.00 2700.00 v input external delay\r\n 1 0.00 2700.00 v serial_tl_bits_out_ready (in)\r\n 1 11.42 2711.42 v input121/Y (BUFx2_ASAP7_75t_R)\r\n 1 21.57 2733.00 v system/subsystem_fbus/out_async/_0655_/Y (AND2x6_ASAP7_75t_R)\r\n 1 27.18 2760.18 ^ system/subsystem_fbus/out_async/_1119_/CON (HAxp5_ASAP7_75t_R)\r\n 1 9.72 2769.90 v system/subsystem_fbus/out_async/_1118_/Y (INVx1_ASAP7_75t_R)\r\n 1 13.58 2783.48 ^ system/subsystem_fbus/out_async/_1120_/CON (HAxp5_ASAP7_75t_R)\r\n 1 8.76 2792.23 v system/subsystem_fbus/out_async/_1117_/Y (INVx1_ASAP7_75t_R)\r\n 12 204.22 2996.46 v system/subsystem_fbus/out_async/_1121_/SN (HAxp5_ASAP7_75t_R)\r\n 12 53.79 3050.25 v load_slew27103/Y (BUFx6f_ASAP7_75t_R)\r\n 2 24.58 3074.83 v system/subsystem_fbus/out_async/_0587_/Y (XNOR2x1_ASAP7_75t_R)\r\n 1 26.20 3101.02 v system/subsystem_fbus/out_async/_0588_/Y (OR3x1_ASAP7_75t_R)\r\n 33 54.44 3155.46 v system/subsystem_fbus/out_async/_0593_/Y (AO22x2_ASAP7_75t_R)\r\n 33 113.80 3269.27 ^ system/subsystem_fbus/out_async/_0594_/Y (NAND2x2_ASAP7_75t_R)\r\n 1 46.55 3315.82 ^ system/subsystem_fbus/out_async/_0679_/Y (OA21x2_ASAP7_75t_R)\r\n 0.02 3315.84 ^ system/subsystem_fbus/out_async/_1122_/D (DFFHQNx2_ASAP7_75t_R)\r\n 3315.84 data arrival time\r\n\r\n 8500.00 8500.00 clock serial_tl_clock (rise edge)\r\n 191.14 8691.14 clock network delay (propagated)\r\n -10.00 8681.14 clock uncertainty\r\n 0.00 8681.14 clock reconvergence pessimism\r\n 8681.14 ^ system/subsystem_fbus/out_async/_1122_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -5.07 8676.07 library setup time\r\n 8676.07 data required time\r\n---------------------------------------------------------------\r\n 8676.07 data required time\r\n -3315.84 data arrival time\r\n---------------------------------------------------------------\r\n 5360.23 slack (MET)\r\n```\r\n"}, {"user": "I've posted a question to Chipyard: https://groups.google.com/g/chipyard/c/BXsafsGlhJ0"}]} +{"messages": [{"user": "I want to reduce the rebuilding when the SDC file changes in https://github.com/The-OpenROAD-Project/megaboom\r\n\r\nWhat stages actually use the .sdc file?\r\n\r\n- floorplan.tcl reads in and writes out the .sdc file, but I don't think floorplan.tcl itself uses the information in the .sdc file. What about other floorplan stages?\r\n- placement uses(I think), but does not modify the .tcl file\r\n- cts uses and writes out a new .tcl file (propagated clocks)\r\n- routing uses(I think), but does not modify the .sdc file\r\n- final uses(I think) the .sdc file, but does not modify the .sdc file"}, {"assistant": "floorplan.tcl calls check_setup which does use SDC info. I don't know that it modifies the SDC though.\r\n\r\nIn principle steps that modify the netlist could update the SDC (ie move/copy a constraint on a pin that is being modified). In practice we don't do that much today but I don't think we should preclude it."}]} +{"messages": [{"user": "I am running into problems with too many OpenROAD binaries running in parallel when using Bazel ORFS layer.\r\n\r\nI'm looking into whether I can get Bazel not to overuse CPUs in the system: https://groups.google.com/g/bazel-discuss/c/KVDcZ-EDfZw\r\n\r\nWhat other options are there? Surely this is not a new problem. What does other types of toolchains do?\r\n\r\nHowever, could and should OpenROAD be modified so that it communicates with other OpenROAD instances in the system and throttles usage to avoid overallocation of CPU and memory?\r\n\r\nIdea:\r\n\r\n- add new option to openroad `-limit `\r\n- this would cause openroad instances to communicate with eachother not to overallocate CPU and memory"}, {"assistant": "This seems to be more about job scheduling than OR. Usually a job scheduler will have some ability to specify the required resources for a job. OR itself will allow you to give a max number of threads if that's helpful.\r\n\r\nFor example in [condor](https://htcondor.readthedocs.io/en/latest/users-manual/submitting-a-job.html):\r\n```\r\nrequest_cpus = 1\r\nrequest_memory = 1024M\r\nrequest_disk = 10240K\r\n```\r\n\r\nI don't think OR should try to solve this as you can run into the same issue between unrelated tools (yosys, klayout, or, etc). "}, {"user": "Turns out there is an infinite loop, probably, in DRC. I thought things ground to a halt because of CPU thrashing, but the detailed router might actually be stuck here. https://github.com/The-OpenROAD-Project/OpenROAD/issues/4466\r\n\r\nIf there is some performance degradation like 30-50% when running multiple detailed routing in parallel, that's tolerable."}]} +{"messages": [{"user": "I get a lot of clock skew with https://github.com/The-OpenROAD-Project/megaboom/commit/f5dd1af7841cf1c811a51206bda6f36b446ff335 \r\n\r\n\r\n\r\n```\r\n>>> report_clock_skew\r\nClock auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock\r\nLatency CRPR Skew\r\nprci_ctrl_domain/_0952_/CLK ^\r\n 11.20\r\ntile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095958_/CLK ^\r\n2185.78 0.00 -2174.58\r\n\r\nClock clock\r\nNo launch/capture paths found.\r\n\r\nClock clock_vir\r\nNo launch/capture paths found.\r\n\r\nClock debug_clock\r\nLatency CRPR Skew\r\ntlDM/dmInner/_0926_/CLK ^\r\n 118.89\r\ntlDM/dmInner/dmInner/_13930_/CLK ^\r\n 143.67 0.00 -24.78\r\n```\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/faff2190-acda-4d7f-a513-7d4a3c847cdd)\r\n\r\nHowever, a simple clock skew number doesn't really tell me if the clock skew is a problem. This presentation talks about that: https://www.eng.biu.ac.il/temanad/files/2017/02/Lecture-8-CTS.pdf\r\n\r\nThe clock skew is a problem if two flip flops that have a path between them have a large clock skew. Overcompensating for clock skew is bad for power/area/performance.\r\n\r\nThough, it is hard to believe that 2000ps clock skew isn't going to be an issue....\r\n\r\n\r\nLooking at the max path, ignoring all the hold elements(clock skew?), it seems like a very deep logic path going from the reorder buffer, through the load store unit and back into the rename stage. I can definitely see how this needs to be flattened in synthesis.\r\n\r\n```\r\nStartpoint: tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095683_\r\n (rising edge-triggered flip-flop clocked by auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock)\r\nEndpoint: tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_44863_\r\n (rising edge-triggered flip-flop clocked by auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock)\r\nPath Group: auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock (rise edge)\r\n1958.08 1958.08 clock network delay (propagated)\r\n 0.00 1958.08 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095683_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 82.49 2040.56 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095683_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 80.51 2121.07 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052821_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 86.15 2207.22 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095639_/CON (HAxp5_ASAP7_75t_R)\r\n 37.20 2244.42 v load_slew37373/Y (BUFx6f_ASAP7_75t_R)\r\n 19.23 2263.65 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052860_/Y (CKINVDCx9p33_ASAP7_75t_R)\r\n 24.44 2288.08 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_064857_/Y (AND2x2_ASAP7_75t_R)\r\n 88.61 2376.70 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095641_/CON (HAxp5_ASAP7_75t_R)\r\n 51.73 2428.42 v max_cap29793/Y (BUFx10_ASAP7_75t_R)\r\n 34.45 2462.87 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053096_/Y (OA222x2_ASAP7_75t_R)\r\n 20.54 2483.41 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053100_/Y (AND5x1_ASAP7_75t_R)\r\n 25.37 2508.78 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053118_/Y (AND3x4_ASAP7_75t_R)\r\n 49.24 2558.02 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053120_/Y (AND2x6_ASAP7_75t_R)\r\n 46.31 2604.33 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053122_/Y (AND4x2_ASAP7_75t_R)\r\n 72.25 2676.58 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09441_/Y (NAND2x1_ASAP7_75t_R)\r\n 23.28 2699.86 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09452_/Y (OA21x2_ASAP7_75t_R)\r\n 6.13 2705.99 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09453_/Y (INVx1_ASAP7_75t_R)\r\n 14.46 2720.45 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09455_/Y (AND4x2_ASAP7_75t_R)\r\n 12.60 2733.05 v hold3456/Y (BUFx2_ASAP7_75t_R)\r\n 12.42 2745.47 v hold3147/Y (BUFx2_ASAP7_75t_R)\r\n 12.35 2757.83 v hold3457/Y (BUFx2_ASAP7_75t_R)\r\n 12.25 2770.08 v hold2749/Y (BUFx2_ASAP7_75t_R)\r\n 12.23 2782.31 v hold3458/Y (BUFx2_ASAP7_75t_R)\r\n 12.22 2794.54 v hold3148/Y (BUFx2_ASAP7_75t_R)\r\n 12.34 2806.88 v hold3459/Y (BUFx2_ASAP7_75t_R)\r\n 12.28 2819.16 v hold2589/Y (BUFx2_ASAP7_75t_R)\r\n 12.26 2831.41 v hold3460/Y (BUFx2_ASAP7_75t_R)\r\n 12.22 2843.64 v hold3149/Y (BUFx2_ASAP7_75t_R)\r\n 12.29 2855.93 v hold3461/Y (BUFx2_ASAP7_75t_R)\r\n 12.30 2868.23 v hold2750/Y (BUFx2_ASAP7_75t_R)\r\n 12.57 2880.80 v hold3462/Y (BUFx2_ASAP7_75t_R)\r\n 13.60 2894.40 v hold3150/Y (BUFx2_ASAP7_75t_R)\r\n 13.82 2908.22 v hold3463/Y (BUFx2_ASAP7_75t_R)\r\n 27.44 2935.66 v tile_prci_domain/tile_reset_domain/boom_tile/core/_10541_/Y (AND3x4_ASAP7_75t_R)\r\n 18.64 2954.30 v wire17733/Y (BUFx16f_ASAP7_75t_R)\r\n 89.70 3044.00 v wire17732/Y (BUFx16f_ASAP7_75t_R)\r\n 119.92 3163.91 v max_length17731/Y (BUFx16f_ASAP7_75t_R)\r\n 30.15 3194.06 v wire17730/Y (BUFx16f_ASAP7_75t_R)\r\n 91.23 3285.29 v wire17729/Y (BUFx16f_ASAP7_75t_R)\r\n 79.50 3364.80 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139693_/Y (AND2x2_ASAP7_75t_R)\r\n 30.15 3394.94 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139694_/Y (NAND2x2_ASAP7_75t_R)\r\n 54.32 3449.26 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139729_/Y (AOI21x1_ASAP7_75t_R)\r\n 27.75 3477.02 v max_cap15253/Y (BUFx12f_ASAP7_75t_R)\r\n 108.62 3585.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267045_/CON (HAxp5_ASAP7_75t_R)\r\n 21.51 3607.14 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139732_/Y (CKINVDCx12_ASAP7_75t_R)\r\n 28.07 3635.22 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267043_/CON (HAxp5_ASAP7_75t_R)\r\n 15.42 3650.63 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267017_/Y (INVx1_ASAP7_75t_R)\r\n 53.40 3704.04 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267041_/CON (HAxp5_ASAP7_75t_R)\r\n 35.49 3739.53 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267041_/SN (HAxp5_ASAP7_75t_R)\r\n 31.36 3770.89 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149214_/Y (XNOR2x1_ASAP7_75t_R)\r\n 31.07 3801.95 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149219_/Y (AND5x2_ASAP7_75t_R)\r\n 20.78 3822.73 v wire11834/Y (BUFx12f_ASAP7_75t_R)\r\n 81.40 3904.13 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09445_/Y (AO221x2_ASAP7_75t_R)\r\n 25.17 3929.30 v wire11643/Y (BUFx16f_ASAP7_75t_R)\r\n 70.74 4000.04 v wire11642/Y (BUFx16f_ASAP7_75t_R)\r\n 84.41 4084.45 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09446_/Y (OR5x2_ASAP7_75t_R)\r\n 15.55 4100.01 v hold2875/Y (BUFx2_ASAP7_75t_R)\r\n 12.67 4112.67 v hold2611/Y (BUFx2_ASAP7_75t_R)\r\n 12.70 4125.38 v hold2876/Y (BUFx2_ASAP7_75t_R)\r\n 12.45 4137.83 v hold2489/Y (BUFx2_ASAP7_75t_R)\r\n 12.41 4150.23 v hold2877/Y (BUFx2_ASAP7_75t_R)\r\n 12.47 4162.71 v hold2612/Y (BUFx2_ASAP7_75t_R)\r\n 14.28 4176.98 v hold2878/Y (BUFx2_ASAP7_75t_R)\r\n 6.16 4183.14 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09447_/Y (INVx1_ASAP7_75t_R)\r\n 12.17 4195.32 ^ hold2613/Y (BUFx2_ASAP7_75t_R)\r\n 11.66 4206.97 ^ hold2490/Y (BUFx2_ASAP7_75t_R)\r\n 11.89 4218.86 ^ hold2614/Y (BUFx2_ASAP7_75t_R)\r\n 12.66 4231.52 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09449_/Y (AO21x1_ASAP7_75t_R)\r\n 12.91 4244.43 ^ hold2615/Y (BUFx2_ASAP7_75t_R)\r\n 11.74 4256.17 ^ hold2491/Y (BUFx2_ASAP7_75t_R)\r\n 13.34 4269.51 ^ hold2616/Y (BUFx2_ASAP7_75t_R)\r\n 21.75 4291.26 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_10540_/Y (AND3x4_ASAP7_75t_R)\r\n 12.97 4304.23 ^ hold2753/Y (BUFx2_ASAP7_75t_R)\r\n 12.13 4316.36 ^ hold2617/Y (BUFx2_ASAP7_75t_R)\r\n 12.16 4328.52 ^ hold2754/Y (BUFx2_ASAP7_75t_R)\r\n 12.13 4340.65 ^ hold2591/Y (BUFx2_ASAP7_75t_R)\r\n 12.20 4352.86 ^ hold2755/Y (BUFx2_ASAP7_75t_R)\r\n 12.19 4365.04 ^ hold2618/Y (BUFx2_ASAP7_75t_R)\r\n 12.19 4377.23 ^ hold2756/Y (BUFx2_ASAP7_75t_R)\r\n 12.13 4389.36 ^ hold2492/Y (BUFx2_ASAP7_75t_R)\r\n 12.22 4401.58 ^ hold2757/Y (BUFx2_ASAP7_75t_R)\r\n 12.31 4413.89 ^ hold2619/Y (BUFx2_ASAP7_75t_R)\r\n 12.35 4426.24 ^ hold2758/Y (BUFx2_ASAP7_75t_R)\r\n 25.20 4451.44 ^ hold2592/Y (BUFx2_ASAP7_75t_R)\r\n 39.44 4490.88 ^ wire10835/Y (BUFx16f_ASAP7_75t_R)\r\n 118.30 4609.18 ^ wire10834/Y (BUFx16f_ASAP7_75t_R)\r\n 42.72 4651.90 ^ wire10832/Y (BUFx16f_ASAP7_75t_R)\r\n 92.03 4743.92 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139741_/Y (AND3x4_ASAP7_75t_R)\r\n 131.71 4875.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139752_/Y (XNOR2x2_ASAP7_75t_R)\r\n 23.62 4899.25 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_200474_/Y (INVx13_ASAP7_75t_R)\r\n 25.32 4924.57 v max_length9483/Y (BUFx16f_ASAP7_75t_R)\r\n 70.19 4994.76 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267079_/CON (HAxp5_ASAP7_75t_R)\r\n 16.21 5010.97 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139765_/Y (CKINVDCx6p67_ASAP7_75t_R)\r\n 31.91 5042.88 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139770_/Y (AND3x1_ASAP7_75t_R)\r\n 106.34 5149.23 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267049_/SN (HAxp5_ASAP7_75t_R)\r\n 44.98 5194.21 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149221_/Y (XNOR2x1_ASAP7_75t_R)\r\n 33.17 5227.38 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149226_/Y (AND5x2_ASAP7_75t_R)\r\n 25.28 5252.66 v wire7254/Y (BUFx12f_ASAP7_75t_R)\r\n 77.52 5330.18 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09462_/Y (AO221x2_ASAP7_75t_R)\r\n 21.54 5351.72 v wire7115/Y (BUFx16f_ASAP7_75t_R)\r\n 69.67 5421.39 v wire7114/Y (BUFx16f_ASAP7_75t_R)\r\n 74.63 5496.02 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09468_/Y (OR4x1_ASAP7_75t_R)\r\n 14.86 5510.88 v hold3695/Y (BUFx2_ASAP7_75t_R)\r\n 12.38 5523.26 v hold2552/Y (BUFx2_ASAP7_75t_R)\r\n 12.33 5535.59 v hold3696/Y (BUFx2_ASAP7_75t_R)\r\n 12.31 5547.89 v hold2504/Y (BUFx2_ASAP7_75t_R)\r\n 12.31 5560.21 v hold3697/Y (BUFx2_ASAP7_75t_R)\r\n 13.56 5573.77 v hold2553/Y (BUFx2_ASAP7_75t_R)\r\n 5.94 5579.70 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_13953_/Y (INVx1_ASAP7_75t_R)\r\n 12.23 5591.93 ^ hold2554/Y (BUFx2_ASAP7_75t_R)\r\n 11.66 5603.59 ^ hold2505/Y (BUFx2_ASAP7_75t_R)\r\n 11.73 5615.32 ^ hold2555/Y (BUFx2_ASAP7_75t_R)\r\n 28.61 5643.93 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_13955_/Y (AND4x2_ASAP7_75t_R)\r\n 13.70 5657.64 ^ hold2883/Y (BUFx2_ASAP7_75t_R)\r\n 11.87 5669.51 ^ hold2556/Y (BUFx2_ASAP7_75t_R)\r\n 11.76 5681.27 ^ hold2884/Y (BUFx2_ASAP7_75t_R)\r\n 11.68 5692.95 ^ hold2525/Y (BUFx2_ASAP7_75t_R)\r\n 11.99 5704.94 ^ hold2885/Y (BUFx2_ASAP7_75t_R)\r\n 12.13 5717.06 ^ hold2557/Y (BUFx2_ASAP7_75t_R)\r\n 12.07 5729.14 ^ hold2886/Y (BUFx2_ASAP7_75t_R)\r\n 11.83 5740.97 ^ hold2506/Y (BUFx2_ASAP7_75t_R)\r\n 11.69 5752.66 ^ hold2887/Y (BUFx2_ASAP7_75t_R)\r\n 11.82 5764.48 ^ hold2558/Y (BUFx2_ASAP7_75t_R)\r\n 11.91 5776.39 ^ hold2888/Y (BUFx2_ASAP7_75t_R)\r\n 11.94 5788.33 ^ hold2526/Y (BUFx2_ASAP7_75t_R)\r\n 12.00 5800.33 ^ hold2889/Y (BUFx2_ASAP7_75t_R)\r\n 16.89 5817.22 ^ hold2559/Y (BUFx2_ASAP7_75t_R)\r\n 34.94 5852.15 ^ hold2890/Y (BUFx2_ASAP7_75t_R)\r\n 26.15 5878.30 ^ max_length6496/Y (BUFx16f_ASAP7_75t_R)\r\n 13.60 5891.91 ^ hold2891/Y (BUFx2_ASAP7_75t_R)\r\n 12.02 5903.93 ^ hold2560/Y (BUFx2_ASAP7_75t_R)\r\n 11.87 5915.80 ^ hold2892/Y (BUFx2_ASAP7_75t_R)\r\n 11.74 5927.54 ^ hold2527/Y (BUFx2_ASAP7_75t_R)\r\n 11.79 5939.33 ^ hold2893/Y (BUFx2_ASAP7_75t_R)\r\n 11.81 5951.14 ^ hold2561/Y (BUFx2_ASAP7_75t_R)\r\n 11.96 5963.09 ^ hold2894/Y (BUFx2_ASAP7_75t_R)\r\n 11.93 5975.03 ^ hold2507/Y (BUFx2_ASAP7_75t_R)\r\n 11.94 5986.97 ^ hold2895/Y (BUFx2_ASAP7_75t_R)\r\n 11.87 5998.84 ^ hold2562/Y (BUFx2_ASAP7_75t_R)\r\n 11.96 6010.80 ^ hold2896/Y (BUFx2_ASAP7_75t_R)\r\n 11.88 6022.68 ^ hold2528/Y (BUFx2_ASAP7_75t_R)\r\n 11.83 6034.51 ^ hold2897/Y (BUFx2_ASAP7_75t_R)\r\n 29.92 6064.43 ^ hold2563/Y (BUFx2_ASAP7_75t_R)\r\n 64.30 6128.72 ^ wire6494/Y (BUFx12f_ASAP7_75t_R)\r\n 65.09 6193.82 ^ wire6493/Y (BUFx16f_ASAP7_75t_R)\r\n 75.13 6268.94 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139772_/Y (AND2x2_ASAP7_75t_R)\r\n 30.93 6299.88 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139794_/Y (NAND2x2_ASAP7_75t_R)\r\n 37.31 6337.19 v max_length5802/Y (BUFx16f_ASAP7_75t_R)\r\n 41.02 6378.21 v load_slew5800/Y (BUFx16f_ASAP7_75t_R)\r\n 20.76 6398.97 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_145708_/Y (NOR2x1_ASAP7_75t_R)\r\n 55.06 6454.03 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_145709_/Y (XNOR2x2_ASAP7_75t_R)\r\n 103.05 6557.08 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_193309_/Y (NOR2x2_ASAP7_75t_R)\r\n 50.56 6607.64 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_212054_/Y (AND2x2_ASAP7_75t_R)\r\n 26.07 6633.71 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267110_/CON (HAxp5_ASAP7_75t_R)\r\n 25.60 6659.31 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267110_/SN (HAxp5_ASAP7_75t_R)\r\n 25.32 6684.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149203_/Y (XOR2x1_ASAP7_75t_R)\r\n 58.24 6742.87 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149205_/Y (AND5x2_ASAP7_75t_R)\r\n 57.64 6800.51 ^ wire3875/Y (BUFx16f_ASAP7_75t_R)\r\n 78.48 6878.99 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09474_/Y (AO221x2_ASAP7_75t_R)\r\n 34.79 6913.78 ^ wire3865/Y (BUFx16f_ASAP7_75t_R)\r\n 56.61 6970.39 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09475_/Y (OR4x1_ASAP7_75t_R)\r\n 13.02 6983.41 ^ hold3416/Y (BUFx2_ASAP7_75t_R)\r\n 11.71 6995.11 ^ hold2992/Y (BUFx2_ASAP7_75t_R)\r\n 11.65 7006.76 ^ hold3417/Y (BUFx2_ASAP7_75t_R)\r\n 11.64 7018.40 ^ hold2679/Y (BUFx2_ASAP7_75t_R)\r\n 11.69 7030.09 ^ hold3418/Y (BUFx2_ASAP7_75t_R)\r\n 11.66 7041.75 ^ hold2993/Y (BUFx2_ASAP7_75t_R)\r\n 11.77 7053.52 ^ hold3419/Y (BUFx2_ASAP7_75t_R)\r\n 14.52 7068.04 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09476_/Y (AO22x2_ASAP7_75t_R)\r\n 12.18 7080.22 ^ hold3699/Y (BUFx2_ASAP7_75t_R)\r\n 11.67 7091.90 ^ hold2994/Y (BUFx2_ASAP7_75t_R)\r\n 11.66 7103.56 ^ hold3700/Y (BUFx2_ASAP7_75t_R)\r\n 11.73 7115.29 ^ hold2680/Y (BUFx2_ASAP7_75t_R)\r\n 11.77 7127.06 ^ hold3701/Y (BUFx2_ASAP7_75t_R)\r\n 11.84 7138.90 ^ hold2995/Y (BUFx2_ASAP7_75t_R)\r\n 11.86 7150.75 ^ hold3702/Y (BUFx2_ASAP7_75t_R)\r\n 16.27 7167.03 ^ hold3420/Y (BUFx2_ASAP7_75t_R)\r\n 6.40 7173.43 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09477_/Y (INVx1_ASAP7_75t_R)\r\n 12.83 7186.26 v hold2996/Y (BUFx2_ASAP7_75t_R)\r\n 12.44 7198.70 v hold2681/Y (BUFx2_ASAP7_75t_R)\r\n 13.05 7211.75 v hold2997/Y (BUFx2_ASAP7_75t_R)\r\n 23.94 7235.69 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09480_/Y (AND3x4_ASAP7_75t_R)\r\n 17.05 7252.74 v hold3703/Y (BUFx2_ASAP7_75t_R)\r\n 13.73 7266.47 v hold2998/Y (BUFx2_ASAP7_75t_R)\r\n 13.82 7280.29 v hold3704/Y (BUFx2_ASAP7_75t_R)\r\n 13.62 7293.91 v hold2682/Y (BUFx2_ASAP7_75t_R)\r\n 13.64 7307.54 v hold3705/Y (BUFx2_ASAP7_75t_R)\r\n 13.25 7320.80 v hold2999/Y (BUFx2_ASAP7_75t_R)\r\n 12.85 7333.65 v hold3706/Y (BUFx2_ASAP7_75t_R)\r\n 36.78 7370.43 v hold3421/Y (BUFx2_ASAP7_75t_R)\r\n 38.82 7409.25 v hold3707/Y (BUFx2_ASAP7_75t_R)\r\n 15.66 7424.91 v max_length3853/Y (BUFx12f_ASAP7_75t_R)\r\n 11.90 7436.81 v hold3708/Y (BUFx2_ASAP7_75t_R)\r\n 12.17 7448.98 v hold3000/Y (BUFx2_ASAP7_75t_R)\r\n 12.28 7461.26 v hold3709/Y (BUFx2_ASAP7_75t_R)\r\n 12.32 7473.58 v hold2683/Y (BUFx2_ASAP7_75t_R)\r\n 12.42 7486.00 v hold3710/Y (BUFx2_ASAP7_75t_R)\r\n 12.22 7498.22 v hold3001/Y (BUFx2_ASAP7_75t_R)\r\n 12.30 7510.52 v hold3711/Y (BUFx2_ASAP7_75t_R)\r\n 30.05 7540.57 v hold3422/Y (BUFx2_ASAP7_75t_R)\r\n 34.72 7575.29 v tile_prci_domain/tile_reset_domain/boom_tile/core/_14044_/Y (AND2x6_ASAP7_75t_R)\r\n 17.31 7592.60 v hold4909/Y (BUFx2_ASAP7_75t_R)\r\n 17.42 7610.02 v hold3002/Y (BUFx2_ASAP7_75t_R)\r\n 17.51 7627.53 v hold4910/Y (BUFx2_ASAP7_75t_R)\r\n 17.30 7644.84 v hold2684/Y (BUFx2_ASAP7_75t_R)\r\n 16.93 7661.77 v hold4911/Y (BUFx2_ASAP7_75t_R)\r\n 15.77 7677.54 v hold3003/Y (BUFx2_ASAP7_75t_R)\r\n 14.70 7692.24 v hold4912/Y (BUFx2_ASAP7_75t_R)\r\n 27.90 7720.14 v hold3423/Y (BUFx2_ASAP7_75t_R)\r\n 56.26 7776.40 v wire3837/Y (BUFx16f_ASAP7_75t_R)\r\n 43.71 7820.11 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05007_/Y (INVx1_ASAP7_75t_R)\r\n 27.46 7847.57 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05009_/Y (OR3x4_ASAP7_75t_R)\r\n 41.42 7889.00 ^ wire3756/Y (BUFx16f_ASAP7_75t_R)\r\n 91.66 7980.65 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05011_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 48.71 8029.36 v wire3438/Y (BUFx12f_ASAP7_75t_R)\r\n 70.54 8099.90 v wire3437/Y (BUFx16f_ASAP7_75t_R)\r\n 146.90 8246.80 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25600_/Y (AND3x4_ASAP7_75t_R)\r\n 29.19 8275.99 v max_length2710/Y (BUFx12f_ASAP7_75t_R)\r\n 38.04 8314.04 v wire2709/Y (BUFx16f_ASAP7_75t_R)\r\n 127.32 8441.35 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25735_/Y (AND3x4_ASAP7_75t_R)\r\n 44.12 8485.47 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25736_/Y (AO21x2_ASAP7_75t_R)\r\n 48.25 8533.72 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25737_/Y (AO21x2_ASAP7_75t_R)\r\n 66.41 8600.12 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25738_/Y (AOI21x1_ASAP7_75t_R)\r\n 40.95 8641.07 ^ max_cap481/Y (BUFx10_ASAP7_75t_R)\r\n 12.72 8653.80 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_38380_/Y (OAI21x1_ASAP7_75t_R)\r\n 18.12 8671.91 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_38384_/Y (AO21x1_ASAP7_75t_R)\r\n 0.01 8671.92 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_44863_/D (DFFHQNx2_ASAP7_75t_R)\r\n 8671.92 data arrival time\r\n\r\n8500.00 8500.00 clock auto_prci_ctrl_domain_reset_setter_clock_in_member_allClocks_uncore_clock (rise edge)\r\n 201.71 8701.71 clock network delay (propagated)\r\n -10.00 8691.71 clock uncertainty\r\n 0.00 8691.71 clock reconvergence pessimism\r\n 8691.71 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_44863_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n 15.71 8707.42 library setup time\r\n 8707.42 data required time\r\n---------------------------------------------------------\r\n 8707.42 data required time\r\n -8671.92 data arrival time\r\n---------------------------------------------------------\r\n 35.50 slack (MET)\r\n```\r\n\r\n\r\nIf I strip away everything but the logic, I get:\r\n\r\n```\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 82.49 2040.56 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095683_/QN (DFFHQNx2_ASAP7_75t_R)\r\n 80.51 2121.07 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052821_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 86.15 2207.22 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095639_/CON (HAxp5_ASAP7_75t_R)\r\n 19.23 2263.65 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_052860_/Y (CKINVDCx9p33_ASAP7_75t_R)\r\n 24.44 2288.08 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_064857_/Y (AND2x2_ASAP7_75t_R)\r\n 88.61 2376.70 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_095641_/CON (HAxp5_ASAP7_75t_R)\r\n 34.45 2462.87 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053096_/Y (OA222x2_ASAP7_75t_R)\r\n 20.54 2483.41 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053100_/Y (AND5x1_ASAP7_75t_R)\r\n 25.37 2508.78 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053118_/Y (AND3x4_ASAP7_75t_R)\r\n 49.24 2558.02 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053120_/Y (AND2x6_ASAP7_75t_R)\r\n 46.31 2604.33 v tile_prci_domain/tile_reset_domain/boom_tile/core/rob/_053122_/Y (AND4x2_ASAP7_75t_R)\r\n 72.25 2676.58 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09441_/Y (NAND2x1_ASAP7_75t_R)\r\n 23.28 2699.86 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09452_/Y (OA21x2_ASAP7_75t_R)\r\n 6.13 2705.99 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09453_/Y (INVx1_ASAP7_75t_R)\r\n 14.46 2720.45 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09455_/Y (AND4x2_ASAP7_75t_R)\r\n 27.44 2935.66 v tile_prci_domain/tile_reset_domain/boom_tile/core/_10541_/Y (AND3x4_ASAP7_75t_R)\r\n 79.50 3364.80 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139693_/Y (AND2x2_ASAP7_75t_R)\r\n 30.15 3394.94 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139694_/Y (NAND2x2_ASAP7_75t_R)\r\n 54.32 3449.26 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139729_/Y (AOI21x1_ASAP7_75t_R)\r\n 108.62 3585.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267045_/CON (HAxp5_ASAP7_75t_R)\r\n 21.51 3607.14 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139732_/Y (CKINVDCx12_ASAP7_75t_R)\r\n 28.07 3635.22 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267043_/CON (HAxp5_ASAP7_75t_R)\r\n 15.42 3650.63 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267017_/Y (INVx1_ASAP7_75t_R)\r\n 53.40 3704.04 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267041_/CON (HAxp5_ASAP7_75t_R)\r\n 35.49 3739.53 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267041_/SN (HAxp5_ASAP7_75t_R)\r\n 31.36 3770.89 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149214_/Y (XNOR2x1_ASAP7_75t_R)\r\n 31.07 3801.95 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149219_/Y (AND5x2_ASAP7_75t_R)\r\n 81.40 3904.13 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09445_/Y (AO221x2_ASAP7_75t_R)\r\n 84.41 4084.45 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09446_/Y (OR5x2_ASAP7_75t_R)\r\n 6.16 4183.14 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09447_/Y (INVx1_ASAP7_75t_R)\r\n 12.66 4231.52 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09449_/Y (AO21x1_ASAP7_75t_R)\r\n 21.75 4291.26 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_10540_/Y (AND3x4_ASAP7_75t_R)\r\n 92.03 4743.92 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139741_/Y (AND3x4_ASAP7_75t_R)\r\n 131.71 4875.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139752_/Y (XNOR2x2_ASAP7_75t_R)\r\n 23.62 4899.25 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_200474_/Y (INVx13_ASAP7_75t_R)\r\n 70.19 4994.76 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267079_/CON (HAxp5_ASAP7_75t_R)\r\n 16.21 5010.97 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139765_/Y (CKINVDCx6p67_ASAP7_75t_R)\r\n 31.91 5042.88 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139770_/Y (AND3x1_ASAP7_75t_R)\r\n 106.34 5149.23 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267049_/SN (HAxp5_ASAP7_75t_R)\r\n 44.98 5194.21 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149221_/Y (XNOR2x1_ASAP7_75t_R)\r\n 33.17 5227.38 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149226_/Y (AND5x2_ASAP7_75t_R)\r\n 77.52 5330.18 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09462_/Y (AO221x2_ASAP7_75t_R)\r\n 74.63 5496.02 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09468_/Y (OR4x1_ASAP7_75t_R)\r\n 5.94 5579.70 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_13953_/Y (INVx1_ASAP7_75t_R)\r\n 28.61 5643.93 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_13955_/Y (AND4x2_ASAP7_75t_R)\r\n 75.13 6268.94 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139772_/Y (AND2x2_ASAP7_75t_R)\r\n 30.93 6299.88 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_139794_/Y (NAND2x2_ASAP7_75t_R)\r\n 20.76 6398.97 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_145708_/Y (NOR2x1_ASAP7_75t_R)\r\n 55.06 6454.03 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_145709_/Y (XNOR2x2_ASAP7_75t_R)\r\n 103.05 6557.08 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_193309_/Y (NOR2x2_ASAP7_75t_R)\r\n 50.56 6607.64 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_212054_/Y (AND2x2_ASAP7_75t_R)\r\n 26.07 6633.71 v tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267110_/CON (HAxp5_ASAP7_75t_R)\r\n 25.60 6659.31 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_267110_/SN (HAxp5_ASAP7_75t_R)\r\n 25.32 6684.63 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149203_/Y (XOR2x1_ASAP7_75t_R)\r\n 58.24 6742.87 ^ tile_prci_domain/tile_reset_domain/boom_tile/lsu/_149205_/Y (AND5x2_ASAP7_75t_R)\r\n 78.48 6878.99 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09474_/Y (AO221x2_ASAP7_75t_R)\r\n 56.61 6970.39 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09475_/Y (OR4x1_ASAP7_75t_R)\r\n 14.52 7068.04 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/_09476_/Y (AO22x2_ASAP7_75t_R)\r\n 6.40 7173.43 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09477_/Y (INVx1_ASAP7_75t_R)\r\n 23.94 7235.69 v tile_prci_domain/tile_reset_domain/boom_tile/core/_09480_/Y (AND3x4_ASAP7_75t_R)\r\n 34.72 7575.29 v tile_prci_domain/tile_reset_domain/boom_tile/core/_14044_/Y (AND2x6_ASAP7_75t_R)\r\n 43.71 7820.11 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05007_/Y (INVx1_ASAP7_75t_R)\r\n 27.46 7847.57 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05009_/Y (OR3x4_ASAP7_75t_R)\r\n 91.66 7980.65 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/_05011_/Y (CKINVDCx20_ASAP7_75t_R)\r\n 146.90 8246.80 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25600_/Y (AND3x4_ASAP7_75t_R)\r\n 127.32 8441.35 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25735_/Y (AND3x4_ASAP7_75t_R)\r\n 44.12 8485.47 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25736_/Y (AO21x2_ASAP7_75t_R)\r\n 48.25 8533.72 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25737_/Y (AO21x2_ASAP7_75t_R)\r\n 66.41 8600.12 ^ tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_25738_/Y (AOI21x1_ASAP7_75t_R)\r\n 12.72 8653.80 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_38380_/Y (OAI21x1_ASAP7_75t_R)\r\n 18.12 8671.91 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_38384_/Y (AO21x1_ASAP7_75t_R)\r\n 0.01 8671.92 v tile_prci_domain/tile_reset_domain/boom_tile/core/rename_stage/freelist/_44863_/D (DFFHQNx2_ASAP7_75t_R)\r\n```\r\n\r\nThis is a delay of 70 levels of logic yielding 3445.12ps. The fanout of a number of these levels are in the 10-20 range.\r\n"}, {"user": "@precisionmoon FYI"}, {"assistant": "The reported clock skew from sta considers only ff that have a path between them."}]} +{"messages": [{"user": "For instance, what does \"5/45\" mean?\r\n\r\nIt is a bit hard to read, it would have been easier if there were two columns for the \"Instances\" numbers...\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/463b3945-3120-4da2-a36a-43152809a47a)\r\n"}, {"assistant": "```/```\r\n\r\nThe tradeoff of more columns is that it takes more screen real estate. Its already a pretty wide window."}]} +{"messages": [{"user": "I'm trying to create a mock SRAM for the L2 in https://github.com/The-OpenROAD-Project/megaboom\r\n\r\nHere is the behavioral model:\r\n\r\n```verilog\r\nmodule cc_banks_8192x64(\r\n input [12:0] RW0_addr,\r\n input RW0_en,\r\n RW0_clk,\r\n RW0_wmode,\r\n input [63:0] RW0_wdata,\r\n output [63:0] RW0_rdata\r\n);\r\n\r\n reg [63:0] Memory[0:8191];\r\n reg [12:0] _RW0_raddr_d0;\r\n reg _RW0_ren_d0;\r\n reg _RW0_rmode_d0;\r\n always @(posedge RW0_clk) begin\r\n _RW0_raddr_d0 <= RW0_addr;\r\n _RW0_ren_d0 <= RW0_en;\r\n _RW0_rmode_d0 <= RW0_wmode;\r\n if (RW0_en & RW0_wmode)\r\n Memory[RW0_addr] <= RW0_wdata;\r\n end // always @(posedge)\r\n assign RW0_rdata = _RW0_ren_d0 & ~_RW0_rmode_d0 ? Memory[_RW0_raddr_d0] : 64'bx;\r\nendmodule\r\n```\r\n\r\n`8192 rows x 64 bits = 5*10^5 bits`. This yields `2.7*10^6` instances. At CORE_UTILIZATION=40%, this yields the following floorplan 640um * 1400um.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c86a5532-5e36-4b32-a3aa-5bbf0f4396e1)\r\n\r\nThe build times for this module become prohibitive. Synthesis is ca. 6000s, 30000s for global placement, and at least as long for CTS. So I really don't want to run through more than the floorplan and at that point create an abstract.\r\n\r\nI have some work in progress where I can mock a smaller area: https://github.com/The-OpenROAD-Project/megaboom/pull/9\r\n\r\nI don't have a way to mock a realistic clock period for the .lib file that comes out of the floorplan, nor do I know exactly what is realistic for such an SRAM on ASAP7.\r\n\r\n90ps minimum clock period for a 8192x64 SRAM seems pretty good...\r\n\r\n```\r\n>>> report_clock_min_period\r\nRW0_clk period min = 89.24 fmax 11206.30\r\n```\r\n\r\nI can't reconcile the min period of 90ps with what is observed in Timing Report:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/f397f170-1746-4e77-8dfc-f2fd34ef50d7)\r\n\r\nI wonder if the .lib file that comes out of the floorplan can be useful in architectural exploration.\r\n\r\nThis raises a rather open ended question...\r\n\r\nQ: How does the .lib file that comes out of the floorplan compare to a realistic .lib file?\r\n\r\nIs it a \"simple matter of scaling\" the .lib file, like I can scale area to get something that is something that is in the range of what I want in my architectural exploration?\r\n\r\n\r\n\r\n\r\n\r\n"}, {"assistant": "I believe the min clock period is based on internal reg-to-reg paths and not reg-IO paths as shown above.\r\n\r\nUsing a memory generator is a better idea as this will only get worse the bigger you make the rams. "}, {"assistant": "Expecting to build to build 2.5M instance blocks quickly will be very difficult in any tool."}, {"user": "Trying a different approach... Since all I care about is to mock area and timing(creating realistic SRAMs is a separate concern that I'm not tackling now), it doens't matter what the Verilog actually does. Below I have reduced the size of the Memory while I'm using all the address bits.\r\n\r\n```\r\nmodule cc_banks_8192x64(\r\n input [12:0] RW0_addr,\r\n input RW0_en,\r\n RW0_clk,\r\n RW0_wmode,\r\n input [63:0] RW0_wdata,\r\n output [63:0] RW0_rdata\r\n);\r\n\r\n reg [63:0] Memory[0:127]; // Smaller memory array\r\n reg [12:0] _RW0_raddr_d0;\r\n reg _RW0_ren_d0;\r\n reg _RW0_rmode_d0;\r\n // XOR high and low bits of the address to use all bits\r\n wire [6:0] effective_addr = RW0_addr[6:0] ^ RW0_addr[12:7];\r\n always @(posedge RW0_clk) begin\r\n _RW0_raddr_d0 <= effective_addr;\r\n _RW0_ren_d0 <= RW0_en;\r\n _RW0_rmode_d0 <= RW0_wmode;\r\n if (RW0_en & RW0_wmode)\r\n Memory[effective_addr] <= RW0_wdata;\r\n end // always @(posedge)\r\n assign RW0_rdata = _RW0_ren_d0 & ~_RW0_rmode_d0 ? Memory[_RW0_raddr_d0] : 64'bx;\r\nendmodule\r\n```\r\n\r\nAfter a few minutes, I have some area and timing for a mock SRAM that should allow me to see what else is going on in this design...\r\n\r\nIf I want more aggressive timing, I can adjust the Verilog to be even simpler. Area can be scaled up and down, using the mock_area feature.\r\n\r\nAfter CTS:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/e59c2ccd-b58f-4940-8c8c-96bf9286e638)\r\n\r\n"}, {"user": "So with the above approach, I can easily mock large SRAMs and I also have a way to mock the area.\r\n\r\nThis allows me to set aside the SRAM concerns to investigate what else is going on in the design and learn something interesting.\r\n\r\nSetting aside the SRAM concern, I can see a lot of logic and high fanout in the timing path for the FpPipeline in the megaboom design.\r\n\r\nWhat timing closure does this have in commercial tools at a small node? It seems like a lot to ask that PDK and improved post synthesis stages are going to get this to GHz frequencies. Could it be a synthesis problem? Perhaps this version of MegaBoom is missing a pipeline stage or two here? Could there be some structure that has to be specialized in floating point units just like SRAM must be?\r\n\r\nFrom `make DESIGN_NAME=FpPipeline gui_place`:\r\n\r\n```\r\n>>> report_checks -rise_from io_flush_pipeline -rise_through input504/A -rise_through input504/Y -rise_through wire12207/A -rise_through wire12207/Y -rise_through max_length12204/A -rise_through max_length12204/Y -rise_through fp_issue_unit/_46407_/B -fall_through fp_issue_unit/_46407_/Y -fall_through fp_issue_unit/_46408_/B -rise_through fp_issue_unit/_46408_/Y -rise_through max_length4078/A -rise_through max_length4078/Y -rise_through fp_issue_unit/_46439_/C -rise_through fp_issue_unit/_46439_/Y -rise_through fp_issue_unit/_46571_/A -fall_through fp_issue_unit/_46571_/Y -fall_through fp_issue_unit/_47883_/A -rise_through fp_issue_unit/_47883_/Y -rise_through fp_issue_unit/_47884_/B -rise_through fp_issue_unit/_47884_/Y -rise_through fp_issue_unit/_47885_/C -rise_through fp_issue_unit/_47885_/Y -rise_through fp_issue_unit/_47886_/D -rise_through fp_issue_unit/_47886_/Y -rise_through fp_issue_unit/_47887_/C -rise_through fp_issue_unit/_47887_/Y -rise_through fp_issue_unit/_47888_/C ...\r\nStartpoint: io_flush_pipeline (input port clocked by clock_vir)\r\nEndpoint: fp_issue_unit/_89827_\r\n (rising edge-triggered flip-flop clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 0.00 clock clock_vir (rise edge)\r\n 400.00 400.00 clock network delay (ideal)\r\n 300.00 700.00 ^ input external delay\r\n 1 0.79 0.00 0.00 700.00 ^ io_flush_pipeline (in)\r\n io_flush_pipeline (net)\r\n 0.06 0.02 700.02 ^ input504/A (BUFx2_ASAP7_75t_R)\r\n 1 4.55 17.58 15.46 715.48 ^ input504/Y (BUFx2_ASAP7_75t_R)\r\n net504 (net)\r\n 17.89 1.29 716.77 ^ wire12207/A (BUFx16f_ASAP7_75t_R)\r\n 24 53.86 28.61 18.16 734.93 ^ wire12207/Y (BUFx16f_ASAP7_75t_R)\r\n net12207 (net)\r\n 83.92 25.50 760.43 ^ max_length12204/A (BUFx16f_ASAP7_75t_R)\r\n 32 49.26 12.98 29.13 789.57 ^ max_length12204/Y (BUFx16f_ASAP7_75t_R)\r\n net12204 (net)\r\n 220.31 69.86 859.42 ^ fp_issue_unit/_46407_/B (AOI211x1_ASAP7_75t_R)\r\n 3 3.74 59.98 45.43 904.85 v fp_issue_unit/_46407_/Y (AOI211x1_ASAP7_75t_R)\r\n fp_issue_unit/_44478_ (net)\r\n 59.98 0.21 905.07 v fp_issue_unit/_46408_/B (NAND2x2_ASAP7_75t_R)\r\n 26 33.42 134.87 68.93 973.99 ^ fp_issue_unit/_46408_/Y (NAND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_44479_ (net)\r\n 134.89 1.12 975.12 ^ max_length4078/A (BUFx16f_ASAP7_75t_R)\r\n 22 31.72 20.83 33.87 1008.99 ^ max_length4078/Y (BUFx16f_ASAP7_75t_R)\r\n net4078 (net)\r\n 22.31 2.51 1011.50 ^ fp_issue_unit/_46439_/C (AND4x2_ASAP7_75t_R)\r\n 5 7.55 36.45 46.10 1057.60 ^ fp_issue_unit/_46439_/Y (AND4x2_ASAP7_75t_R)\r\n fp_issue_unit/_44510_ (net)\r\n 36.56 1.15 1058.76 ^ fp_issue_unit/_46571_/A (NAND2x2_ASAP7_75t_R)\r\n 4 3.26 16.65 13.84 1072.59 v fp_issue_unit/_46571_/Y (NAND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_44641_ (net)\r\n 16.66 0.11 1072.70 v fp_issue_unit/_47883_/A (INVx1_ASAP7_75t_R)\r\n 2 1.33 12.37 10.21 1082.91 ^ fp_issue_unit/_47883_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_45951_ (net)\r\n 12.37 0.02 1082.93 ^ fp_issue_unit/_47884_/B (AND4x2_ASAP7_75t_R)\r\n 3 5.96 30.73 40.69 1123.62 ^ fp_issue_unit/_47884_/Y (AND4x2_ASAP7_75t_R)\r\n fp_issue_unit/_45952_ (net)\r\n 30.87 1.14 1124.77 ^ fp_issue_unit/_47885_/C (AND3x4_ASAP7_75t_R)\r\n 3 5.79 18.52 31.17 1155.94 ^ fp_issue_unit/_47885_/Y (AND3x4_ASAP7_75t_R)\r\n fp_issue_unit/_45953_ (net)\r\n 19.20 1.89 1157.83 ^ fp_issue_unit/_47886_/D (AND4x2_ASAP7_75t_R)\r\n 3 5.98 31.11 42.40 1200.23 ^ fp_issue_unit/_47886_/Y (AND4x2_ASAP7_75t_R)\r\n fp_issue_unit/_45954_ (net)\r\n 31.45 1.82 1202.06 ^ fp_issue_unit/_47887_/C (AND3x4_ASAP7_75t_R)\r\n 3 5.71 17.88 31.40 1233.46 ^ fp_issue_unit/_47887_/Y (AND3x4_ASAP7_75t_R)\r\n fp_issue_unit/_45955_ (net)\r\n 18.17 1.22 1234.68 ^ fp_issue_unit/_47888_/C (AND3x4_ASAP7_75t_R)\r\n 2 5.25 17.00 29.05 1263.73 ^ fp_issue_unit/_47888_/Y (AND3x4_ASAP7_75t_R)\r\n fp_issue_unit/_45956_ (net)\r\n 17.11 0.76 1264.49 ^ fp_issue_unit/_47889_/B (NAND2x2_ASAP7_75t_R)\r\n 3 3.85 15.69 11.87 1276.36 v fp_issue_unit/_47889_/Y (NAND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_45957_ (net)\r\n 15.84 0.84 1277.19 v fp_issue_unit/_47890_/B (OR2x2_ASAP7_75t_R)\r\n 2 3.01 13.61 25.21 1302.41 v fp_issue_unit/_47890_/Y (OR2x2_ASAP7_75t_R)\r\n fp_issue_unit/_45958_ (net)\r\n 13.61 0.09 1302.50 v fp_issue_unit/_47907_/C (OR3x4_ASAP7_75t_R)\r\n 105 99.41 170.82 89.41 1391.91 v fp_issue_unit/_47907_/Y (OR3x4_ASAP7_75t_R)\r\n fp_issue_unit/_45975_ (net)\r\n 172.27 9.22 1401.13 v fp_issue_unit/_47909_/C (NAND3x2_ASAP7_75t_R)\r\n 4 5.43 62.45 62.61 1463.73 ^ fp_issue_unit/_47909_/Y (NAND3x2_ASAP7_75t_R)\r\n fp_issue_unit/_45977_ (net)\r\n 62.45 0.14 1463.88 ^ fp_issue_unit/_47962_/A (NAND3x2_ASAP7_75t_R)\r\n 2 3.47 24.56 17.68 1481.56 v fp_issue_unit/_47962_/Y (NAND3x2_ASAP7_75t_R)\r\n fp_issue_unit/_46030_ (net)\r\n 24.59 0.45 1482.00 v fp_issue_unit/_47966_/B (OR3x2_ASAP7_75t_R)\r\n 3 3.30 17.68 37.03 1519.04 v fp_issue_unit/_47966_/Y (OR3x2_ASAP7_75t_R)\r\n fp_issue_unit/_46034_ (net)\r\n 17.73 0.51 1519.55 v fp_issue_unit/_47971_/C (OR4x2_ASAP7_75t_R)\r\n 7 20.75 71.34 71.67 1591.22 v fp_issue_unit/_47971_/Y (OR4x2_ASAP7_75t_R)\r\n fp_issue_unit/_46039_ (net)\r\n 71.41 1.35 1592.57 v fp_issue_unit/_47972_/A (CKINVDCx16_ASAP7_75t_R)\r\n 32 25.55 28.08 16.95 1609.51 ^ fp_issue_unit/_47972_/Y (CKINVDCx16_ASAP7_75t_R)\r\n fp_issue_unit/_46040_ (net)\r\n 28.08 0.03 1609.55 ^ fp_issue_unit/_47975_/B (OR3x4_ASAP7_75t_R)\r\n 4 5.14 14.79 26.50 1636.05 ^ fp_issue_unit/_47975_/Y (OR3x4_ASAP7_75t_R)\r\n fp_issue_unit/_46043_ (net)\r\n 15.26 1.43 1637.47 ^ fp_issue_unit/_47976_/B (OR2x2_ASAP7_75t_R)\r\n 2 2.90 13.93 21.14 1658.61 ^ fp_issue_unit/_47976_/Y (OR2x2_ASAP7_75t_R)\r\n fp_issue_unit/_46044_ (net)\r\n 13.93 0.13 1658.74 ^ fp_issue_unit/_47980_/B (OR3x2_ASAP7_75t_R)\r\n 2 3.24 14.84 19.30 1678.04 ^ fp_issue_unit/_47980_/Y (OR3x2_ASAP7_75t_R)\r\n fp_issue_unit/_46048_ (net)\r\n 14.93 0.63 1678.68 ^ fp_issue_unit/_47985_/C (OR4x2_ASAP7_75t_R)\r\n 21 25.71 98.46 51.90 1730.57 ^ fp_issue_unit/_47985_/Y (OR4x2_ASAP7_75t_R)\r\n fp_issue_unit/_46053_ (net)\r\n 98.46 0.42 1730.99 ^ load_slew1306/A (BUFx16f_ASAP7_75t_R)\r\n 28 30.02 16.08 30.35 1761.34 ^ load_slew1306/Y (BUFx16f_ASAP7_75t_R)\r\n net1306 (net)\r\n 17.27 1.57 1762.91 ^ fp_issue_unit/_48140_/B (NAND2x1_ASAP7_75t_R)\r\n 2 1.81 14.47 11.73 1774.64 v fp_issue_unit/_48140_/Y (NAND2x1_ASAP7_75t_R)\r\n fp_issue_unit/_06668_ (net)\r\n 14.47 0.03 1774.67 v fp_issue_unit/_48141_/B (OR3x2_ASAP7_75t_R)\r\n 3 3.52 18.24 35.07 1809.73 v fp_issue_unit/_48141_/Y (OR3x2_ASAP7_75t_R)\r\n fp_issue_unit/_06669_ (net)\r\n 18.24 0.11 1809.84 v fp_issue_unit/_48142_/D (OR4x2_ASAP7_75t_R)\r\n 13 37.62 133.19 75.35 1885.19 v fp_issue_unit/_48142_/Y (OR4x2_ASAP7_75t_R)\r\n fp_issue_unit/_06670_ (net)\r\n 133.22 1.49 1886.68 v load_slew1217/A (BUFx16f_ASAP7_75t_R)\r\n 25 39.76 25.02 40.53 1927.21 v load_slew1217/Y (BUFx16f_ASAP7_75t_R)\r\n net1217 (net)\r\n 25.03 0.48 1927.69 v fp_issue_unit/_48144_/B (AND2x2_ASAP7_75t_R)\r\n 3 3.40 13.73 25.88 1953.57 v fp_issue_unit/_48144_/Y (AND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_06672_ (net)\r\n 13.73 0.05 1953.63 v fp_issue_unit/_48145_/B (NOR2x2_ASAP7_75t_R)\r\n 3 2.92 20.73 12.02 1965.65 ^ fp_issue_unit/_48145_/Y (NOR2x2_ASAP7_75t_R)\r\n fp_issue_unit/_06673_ (net)\r\n 20.73 0.02 1965.66 ^ fp_issue_unit/_48146_/A2 (AOI21x1_ASAP7_75t_R)\r\n 6 10.17 53.11 27.64 1993.30 v fp_issue_unit/_48146_/Y (AOI21x1_ASAP7_75t_R)\r\n fp_issue_unit/_06674_ (net)\r\n 53.17 1.07 1994.37 v fp_issue_unit/_65458_/A (NAND2x2_ASAP7_75t_R)\r\n 7 16.17 72.15 46.53 2040.90 ^ fp_issue_unit/_65458_/Y (NAND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_22642_ (net)\r\n 72.97 4.40 2045.30 ^ wire1108/A (BUFx16f_ASAP7_75t_R)\r\n 30 37.30 21.35 27.72 2073.02 ^ wire1108/Y (BUFx16f_ASAP7_75t_R)\r\n net1108 (net)\r\n 75.70 23.26 2096.27 ^ fp_issue_unit/_65465_/A (NAND2x2_ASAP7_75t_R)\r\n 13 21.19 71.00 42.21 2138.48 v fp_issue_unit/_65465_/Y (NAND2x2_ASAP7_75t_R)\r\n fp_issue_unit/_22649_ (net)\r\n 71.33 2.88 2141.36 v load_slew1091/A (BUFx16f_ASAP7_75t_R)\r\n 25 35.92 17.57 30.98 2172.34 v load_slew1091/Y (BUFx16f_ASAP7_75t_R)\r\n net1091 (net)\r\n 78.63 24.44 2196.78 v fp_issue_unit/_67437_/B (AO21x2_ASAP7_75t_R)\r\n 1 4.12 17.15 34.88 2231.66 v fp_issue_unit/_67437_/Y (AO21x2_ASAP7_75t_R)\r\n fp_issue_unit/_46219_ (net)\r\n 17.44 1.21 2232.86 v fp_issue_unit/_89797_/A (FAx1_ASAP7_75t_R)\r\n 1 6.02 144.25 107.03 2339.89 v fp_issue_unit/_89797_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46223_ (net)\r\n 144.48 3.10 2343.00 v fp_issue_unit/_89798_/A (FAx1_ASAP7_75t_R)\r\n 1 2.72 73.82 58.15 2401.14 ^ fp_issue_unit/_89798_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46254_ (net)\r\n 1 1.06 45.86 22.62 2423.76 v fp_issue_unit/_89798_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_00644_ (net)\r\n 45.86 0.06 2423.83 v fp_issue_unit/_67461_/A (INVx1_ASAP7_75t_R)\r\n 1 2.41 25.51 20.41 2444.24 ^ fp_issue_unit/_67461_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46226_ (net)\r\n 25.51 0.10 2444.34 ^ fp_issue_unit/_89799_/B (FAx1_ASAP7_75t_R)\r\n 1 1.65 36.10 24.28 2468.62 v fp_issue_unit/_89799_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46261_ (net)\r\n 1 0.86 37.25 19.10 2487.72 ^ fp_issue_unit/_89799_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46232_ (net)\r\n 37.25 0.03 2487.75 ^ fp_issue_unit/_67462_/A (INVx1_ASAP7_75t_R)\r\n 1 2.56 21.51 16.75 2504.50 v fp_issue_unit/_67462_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46229_ (net)\r\n 21.51 0.24 2504.74 v fp_issue_unit/_89800_/A (FAx1_ASAP7_75t_R)\r\n 1 1.68 39.83 26.98 2531.72 ^ fp_issue_unit/_89800_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46264_ (net)\r\n 1 0.90 25.69 17.11 2548.83 v fp_issue_unit/_89800_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46244_ (net)\r\n 25.69 0.03 2548.86 v fp_issue_unit/_89787_/A (INVx1_ASAP7_75t_R)\r\n 1 2.56 21.35 16.40 2565.26 ^ fp_issue_unit/_89787_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46231_ (net)\r\n 21.36 0.17 2565.43 ^ fp_issue_unit/_89803_/B (FAx1_ASAP7_75t_R)\r\n 1 2.30 44.45 26.10 2591.54 v fp_issue_unit/_89803_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46267_ (net)\r\n 1 0.78 39.67 20.18 2611.72 ^ fp_issue_unit/_89803_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46249_ (net)\r\n 39.67 0.01 2611.73 ^ fp_issue_unit/_89786_/A (INVx1_ASAP7_75t_R)\r\n 1 1.74 17.87 14.14 2625.88 v fp_issue_unit/_89786_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46243_ (net)\r\n 17.87 0.04 2625.92 v fp_issue_unit/_89804_/CI (FAx1_ASAP7_75t_R)\r\n 1 0.76 33.65 19.73 2645.65 ^ fp_issue_unit/_89804_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_00646_ (net)\r\n 1 0.74 28.73 15.02 2660.67 v fp_issue_unit/_89804_/SN (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_00645_ (net)\r\n 28.73 0.01 2660.68 v fp_issue_unit/_67482_/A (INVx1_ASAP7_75t_R)\r\n 1 1.02 13.34 11.32 2672.00 ^ fp_issue_unit/_67482_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46248_ (net)\r\n 13.34 0.02 2672.02 ^ fp_issue_unit/_89817_/B (HAxp5_ASAP7_75t_R)\r\n 1 0.78 21.67 12.77 2684.79 v fp_issue_unit/_89817_/CON (HAxp5_ASAP7_75t_R)\r\n fp_issue_unit/_00647_ (net)\r\n 21.67 0.01 2684.80 v fp_issue_unit/_89769_/A (INVx1_ASAP7_75t_R)\r\n 1 2.06 17.70 13.87 2698.68 ^ fp_issue_unit/_89769_/Y (INVx1_ASAP7_75t_R)\r\n fp_issue_unit/_46269_ (net)\r\n 17.70 0.03 2698.70 ^ fp_issue_unit/_89811_/A (FAx1_ASAP7_75t_R)\r\n 2 2.91 47.02 26.02 2724.72 v fp_issue_unit/_89811_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_46274_ (net)\r\n 47.02 0.08 2724.80 v fp_issue_unit/_89814_/A (FAx1_ASAP7_75t_R)\r\n 1 1.69 43.76 33.26 2758.06 ^ fp_issue_unit/_89814_/CON (FAx1_ASAP7_75t_R)\r\n fp_issue_unit/_04309_ (net)\r\n 43.76 0.01 2758.07 ^ fp_issue_unit/_48635_/B (XOR2x1_ASAP7_75t_R)\r\n 1 1.16 22.73 24.82 2782.89 ^ fp_issue_unit/_48635_/Y (XOR2x1_ASAP7_75t_R)\r\n fp_issue_unit/_07145_ (net)\r\n 22.73 0.02 2782.92 ^ fp_issue_unit/_48636_/B (NAND2x1_ASAP7_75t_R)\r\n 2 1.32 14.09 11.34 2794.26 v fp_issue_unit/_48636_/Y (NAND2x1_ASAP7_75t_R)\r\n fp_issue_unit/_07146_ (net)\r\n 14.09 0.02 2794.27 v fp_issue_unit/_48637_/B (OR2x2_ASAP7_75t_R)\r\n 3 2.18 11.43 23.11 2817.38 v fp_issue_unit/_48637_/Y (OR2x2_ASAP7_75t_R)\r\n fp_issue_unit/_07147_ (net)\r\n 11.43 0.05 2817.43 v fp_issue_unit/_48639_/C (OR3x1_ASAP7_75t_R)\r\n 1 0.71 10.68 24.49 2841.92 v fp_issue_unit/_48639_/Y (OR3x1_ASAP7_75t_R)\r\n fp_issue_unit/_00000_ (net)\r\n 10.68 0.01 2841.93 v fp_issue_unit/_89827_/D (DFFHQNx2_ASAP7_75t_R)\r\n 2841.93 data arrival time\r\n\r\n 0.00 1500.00 1500.00 clock clock (rise edge)\r\n 0.00 1500.00 clock network delay (ideal)\r\n -10.00 1490.00 clock uncertainty\r\n 0.00 1490.00 clock reconvergence pessimism\r\n 1490.00 ^ fp_issue_unit/_89827_/CLK (DFFHQNx2_ASAP7_75t_R)\r\n -7.35 1482.65 library setup time\r\n 1482.65 data required time\r\n-----------------------------------------------------------------------------\r\n 1482.65 data required time\r\n -2841.93 data arrival time\r\n-----------------------------------------------------------------------------\r\n -1359.27 slack (VIOLATED)\r\n\r\n\r\n```\r\n "}]} +{"messages": [{"user": "In the OpenFASoC [LDO generator](https://github.com/idea-fasoc/OpenFASOC/tree/main/openfasoc/generators/ldo-gen), a two-row tall comparator latch is custom placed using the `place_cell` command in a [tcl script](https://github.com/idea-fasoc/OpenFASOC/blob/f7b3440c485ff2accbf549aa11a12a75c01186c1/openfasoc/generators/ldo-gen/flow/scripts/openfasoc/custom_place.tcl#L7).\r\n\r\nThis used to work in earlier versions of OpenROAD, but recently the CI is [failing](https://github.com/idea-fasoc/OpenFASOC/actions/runs/7301239627/job/19897490889#step:4:1990) with the following error:\r\n```\r\n[ERROR DPL-0017] cannot place instance cmp1.\r\n```\r\n The custom placement is done before running the `detailed_placement` command in the [detail_place.tcl](https://github.com/idea-fasoc/OpenFASOC/blob/main/openfasoc/generators/ldo-gen/flow/scripts/detail_place.tcl) script. If the `detailed_placement` command is removed, the following error is returned:\r\n```\r\n[ERROR DPL-0044] Cell cmp1 with height 8140 is taller than any row.\r\nError: detail_place.tcl, 26 DPL-0044\r\n```\r\n\r\nRelevant Information:\r\n- OpenROAD Version hash: `e89829335596b351ce665dcc3b73619c0b191c14`\r\n- Comparator Latch Cell: [LEF](https://github.com/idea-fasoc/OpenFASOC/blob/main/openfasoc/generators/ldo-gen/blocks/sky130hvl/lef/LDO_COMPARATOR_LATCH.lef) / [GDS](https://github.com/idea-fasoc/OpenFASOC/blob/main/openfasoc/generators/ldo-gen/blocks/sky130hvl/gds/LDO_COMPARATOR_LATCH.gds)\r\n- Custom placement script: [custom_place.tcl](https://github.com/idea-fasoc/OpenFASOC/blob/main/openfasoc/generators/ldo-gen/flow/scripts/openfasoc/custom_place.tcl)\r\n\r\nIs there a way to place this cell (not as a macro) without placement violations?\r\n\r\ncc: @msaligane "}, {"assistant": "Have you tried marking the cells as `FIXED` instead of `PLACED`?"}, {"assistant": "We have recently being doing work related to multi-height cells. The error indicates that the detailed placer is trying to legalize this instance which is sounds like you don't want. FIRM should work for that purpose. Can you provide a test case?"}, {"assistant": "Your other option is to provide double height site rows."}]} +{"messages": [{"user": "We're working with a PDK where the two PDN layers' preferred direction for routing is not the one we want for its part of the core ring, i.e., the layer's preferred direction is vertical but we'd like its part of the core ring to be horizontal. A workaround is modifying the technology LEF for just that step, but is there a way to do that otherwise?"}, {"assistant": "There isn't currently. I'm curious why it is desirable."}]} +{"messages": [{"user": "This is in regard to [https://github.com/chipsalliance/ideas/blob/main/gsoc-2023-ideas.md#create-feol-classes-in-openroad-and-a-gds-writer](url), a GSoC project proposed in 2023. I would like to take this up for 2024's run of GSoC, and was **wondering what the project entails**. For reference, I have been contributing to OpenFASoC for a large part of the year and have good knowledge of their codebase, and some knowledge of OpenROAD-flow-scripts"}, {"assistant": "@msaligane was the mentor in 2023 so it would be good to get his input. I expect the hardest part would be dealing with hierarchy (aref/sref) as OR's odb is rather flat in its lef/def orientation. New layers shouldn't be too hard. The rest of the system will have to be more aware of them and the GUI will need some updating.\r\n\r\nI would be good to have a specific use case beyond just read/write gds. There should be some value added by doing it in OR as opposed to klayout or gdsfactory."}, {"assistant": "Having openroad write gds/oas would be useful, because it reduces the file size compared to odb.\r\n\r\nBut I would recommend not to duplicate the ability to read and collect all the gds/oas pieces coming from various other sources. This functionality already exists in strm2oas."}, {"assistant": "We have been looking into this in the previous GSOC. Hopefully, this project gets approved for Chetanya to finish the project."}]} +{"messages": [{"user": "I was wondering if there was a way to quickly summarize the ratio between the number of paths and number of failing paths (with regard to timing) using OpenSTA. I know it can report the slack in each path in a detailled manner, but I would like to have a report in the vein of : \"Here is the number of paths that the design has that needs to be tested for timing vs. the number of path that failed the test\""}, {"assistant": "I don't see an easy way as the number of paths is exponential. How would you use the result?\r\n\r\n@tspyrou any thoughts?"}, {"assistant": "@lustefan97 Could this be a use-case for timing histogram(supported in OpenROAD under Charts)."}, {"assistant": "Note that to get the histograms you have to have qt charts installed. During cmake you should get a message like \"Charts widget is enabled\" and not \"Charts widget is not enabled\""}, {"assistant": "> It is just a shame that it is so out if the way, I forget that we do... Can it be moved to the tabs where clocktree, hierarchy, etc. is?\r\n\r\nIt is a docking window the same as all the others and can be position wherever you like."}, {"assistant": "> Anyway: I think it would be great if this feature could be made more available out of the box and not hidden away behind \"cmake magic\" and curious defaults.\r\n\r\nIt is on by default, but qtcharts is not available for centos7 and so can't be assumed."}, {"assistant": "A less anaemic slack histogram example:\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/aes/config.mk cts\r\n```\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/aes/config.mk gui_cts\r\n```\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/1caeb16b-836f-4ae5-b5a6-6b235791ab90)\r\n"}, {"user": "@maliberty @oharboe Ok so I updated my OpenROAD to the latest version while having QT chart installed and enabled. After loading a database in that I knew had reported a slack, I tried to make a timing chart but resulted in the GUI crashing. \r\n\r\nI got a warning telling me that timing data was not stored in the database and must be loaded separately if needed, are they not stored in the .odb ? Is the .odb file only \"geometric\" (would not be surprising since a .lef and .def files are needed), even if .lib files and RC rules have been used to produce the final result ?"}, {"assistant": "@AcKoucher FYI"}, {"assistant": "@AcKoucher Just one more example of where the horizontal labels are gone completely:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/7fa91044-d0df-4ffe-84b2-b5a264d959db)\r\n"}, {"user": "@oharboe @maliberty I have a quick but important question, right now I run my TCL scripts on a device that has no GUI, how would I need to proceed if I wanted to design a chip on it using OpenROAD but then move the results and generate the histogram on another computer (capable of opening a GUI).\r\n\r\nI ran a test script in which I saved the design in a .odb file and the timing results from OpenSTA in a .sdf file, but when I loaded the .odb back in another GUI session (as well as the .sdf file using `read_sdf`), multiple warnings were raised during loading and no histogram was created..."}]} +{"messages": [{"user": "How do I get the power for each Instance\uff1fI have no power report after reading the odb file in gui.\r\n![power_report](https://github.com/The-OpenROAD-Project/OpenROAD/assets/107295305/d747e889-1ea2-448e-ba0b-11b6c08e2b52)\r\n\r\n"}, {"assistant": "```report_power -instances [get_cells *]``` should do it. "}]} +{"messages": [{"user": "I would have expected estimated routing congestion and routing congestion to be somewhat similar, but they are very, very different.\r\n\r\nThis is with the MegaBoom design:\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/3844d7c6-25d9-4cce-93f7-f0d6f1b9b301)\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/73812f67-ef06-4370-a56c-49bd85f8852b)\r\n"}, {"assistant": "I would say the general pattern of the congestion is actually quite good but the magnitude seems off. My first guess is layer derating as the estimator doesn't know about it today. If you try with 0 derate do you get a closer answer?"}]} +{"messages": [{"user": "What does it do and why is it not run with rtlmp?\r\n\r\nDoes it need to be run where there is no macro placement?"}, {"assistant": "The old macro placer requires it. Once that is fully removed this step can be dropped.\n\nIt does global placement including the macros (timing driven mixed size)"}]} +{"messages": [{"user": "I realized that size of my designs is not matching \"design area\" reported. On the GUI view I can see my design uses a rectangular space of around 24 um2 (not including the halo) but\r\n\r\n finish report_design_area\r\n Design area 15 u^2 60% utilization.\r\n\r\nwas in the log. So, that seems to mean that the macros placed totaled 15 um2 of space but packed into 24 um2 of silicon. It is useful to know both numbers but I think the size of the space inside the halo is more practical to know. It certainly seems that space would be the most likely expectation for the meaning of \"design area\".\r\n\r\nJust calling attention to this. Not a bug, but users could be easily misled about what it means."}, {"assistant": "This is standard terminology.\r\n\"Design area\": total area consumed by instances.\r\n\"Core area\": total area in which instances can be placed.\r\n\"Die area\": the total area of the chip.\r\nDie area >= core area >= design area. Design area utilization (the 60% in the above) is also always expressed as (design area)/(core area)"}, {"assistant": "By 'halo' do you mean the area between the core and the die area?"}]} +{"messages": [{"user": "I see from chatter here that some folks use place_pins, but it seems not to work for me, with the error message showing in the title. My io.tcl is:\r\n-----\r\n\r\nset leftPins {}\r\nforeach port [get_ports _l_*] {\r\n lappend leftPins [get_property $port name]\r\n}\r\n\r\nset_io_pin_constraint -region left:* -pin_names $leftPins\r\n\r\nset_io_pin_constraint -region right:* -pin_names {\r\n _r_h_in _r_g_in _r_f_in _r_e_rot25 _r_e_rot11 _r_e_rot06 _r_e_in\r\n _r_d_in _r_c_in _r_l_in _r_a_rot22 _r_a_rot13 _r_a_rot02 _r_a_in\r\n _r_KW0_in\r\n}\r\n\r\nset_io_pin_constraint -region top:* -pin_names {\r\n _t_aCarryIn0 _t_aCarryIn1 _t_aCpropIn\r\n _t_eCarryIn0 _t_eCarryIn1 _t_eCarryIn2 _t_eCpropIn\r\n}\r\n\r\nset_io_pin_constraint -region bottom:* -pin_names {\r\n _b_aCarryOut0 _b_aCarryOut1 _b_aCpropOut\r\n _b_eCarryOut0 _b_eCarryOut1 _b_eCarryOut2 _b_eCpropOut\r\n}\r\n\r\nplace_pins -hor_layers metal4 -ver_layers metal5 -min_distance_in_tracks 4\r\n---\r\n\r\nwhich works fine until I added the place_pins command.\r\n\r\nI also used M4 and M5 for layer names (ASAP7) since those are what the openroad -gui viewer shows.\r\n\r\nIs this command blocked by something else? Is the track-multiplier not supported?\r\nThanks!"}, {"assistant": "You might try the recent -annealing options. @eder-matheus any further comments?"}, {"assistant": "Would you include a screen shot of what you are seeing? Note that -min_distance means pin can be that close together at a minimum, not that they will necessarily be that close together if there is extra space available."}, {"assistant": "@TanjIsGray Do you have a reproducible you can share regarding the minimum distance not being respected? We have a bunch of unit tests with different minimum distance values, and all seem to work properly."}, {"user": "I can share the source, make and tcl. These are not large, a few hundred lines of verilog."}]} +{"messages": [{"user": "Hello,\r\n\r\nI am trying to run a custom script to characterize OpenROAD's behavior when the design utilization is varying for a fixed placement_density, using the ASAP7 PDK, when all IO's are on the top metal layer.\r\n\r\nI currently use the ibex design as a test design and I am aiming at a DU of 60%, with a placement density fixed at 1. The issue I have is that I encounter this warning during the global routing step : \r\n\r\n\"[WARNING GRT-0026] Missing route to pin (name of the pin)\"\r\n\r\nIt does this for all pins. During detailed routing it seems to try and fix this problem (as OpenROAD give me the [INFO-DRT-1000] code), but it fails to do so and thus stop the flow after indicating : \r\n\r\n\"[ERROR DRT-0218] Guide is not connected to design\"\r\n\r\nI want to fix this issue, but I have no idea as to where to look, or what to do...\r\n\r\nI use the \"grid-strategy-M1-M2-M5-M6.tcl\" as well as the make_tracks.tcl found in the OpenROAD-flow-scripts/flow/platforms/asap7/ directory."}, {"assistant": "@eder-matheus is this warning one that you fixed recently?\r\n\r\n@lustefan97 its better to give an issue with a test case if possible."}]} +{"messages": [{"user": "I am asking about the function of these arguments. There is no documentation for them:\r\n```\r\n-skip_pin_swap\r\n-skip_gate_cloning\r\n-floorplan_initialize\r\n```"}, {"assistant": "It is helpful to say what they are arguments of. \r\n\r\nread_def -floorplan_initialize : does not read the netlist but just floorplan information like pin locations, instance locations, etc.\r\nrepair_timing -skip_pin_swap & -skip_gate_cloning : disable two new optimizations in case of trouble. More of an escape than something we expect people to use regularly."}]} +{"messages": [{"user": "Hello,\r\n\r\nIs it possible to write and obtain a congestion report at all time, even when there is no violation ? I am aware of the possibility to have a report written when the wire congestion is too high, but I don't see a way to get the heat map data in a text file for example.\r\n\r\nIs there a way to do such a thing ?"}, {"assistant": "In https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/gui/README.md#heat-maps see gui::dump_heatmap"}]} +{"messages": [{"user": "Hi all,\r\n\r\nI am trying to load custom lef/lib files for pnr, and my lef files contain some properties unsupported by openroad. I got too much warning messages from this and the unsupported properties didn't have effect on my pnr results. Is there any way to disable the LEF warning messages temporarily? I checked the documents but failed to find an option that can turn off the warnings. Sorry if I missed it from the documents.\r\n\r\nThanks in advance!\r\n\r\n"}, {"assistant": "There is no method to do that currently. No single message will print more than 1k times."}, {"assistant": "@maliberty Correct me if I am wrong, but doesn't Tcl function `suppress_message` do this? \r\n\r\nEdit: i guess there's no function that achieves full suppression for all warnings, what OP requested\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/28892de3bef1af52f3371d547f752acf0af20021/test/helpers.tcl#L203\r\n\r\nCorresponding source:\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/utl/src/Logger.cpp\r\n"}]} +{"messages": [{"user": "I just want to know if OpenRCX a engine integrated in OpenRoad or is it a RC signoff tool like Cadence Quantas "}, {"assistant": "It is integrated with OR but aspires to be signoff quality. During optimization we use estimated parasitics."}, {"user": "thankyou @maliberty "}]} +{"messages": [{"user": "Hello OpenRoad devs,\r\n\r\nI am following https://github.com/The-OpenROAD-Project/OpenROAD/discussions/3619 to implement a structure to share scan chain data between OpenROAD's components but I am blocked at an compile issue.\r\n\r\nSee: https://github.com/fgaray/OpenROAD/tree/ctl_db, path src/odb/src/codeGenerator/schema/scan\r\n\r\nI am adding 3 new *.json files: dbScanInst.json dbScanPartition.json dbScanPin.json\r\n\r\nIn dbScanPin.json I am defining an \"union\" of dbBTerm and dbITerm\r\n\r\nIn dbScanPartition.json I am trying to use dbScanPin for my \"start\" and \"stop\" fields.\r\n\r\n\r\nI am running the ./generate script in src/odb/src/codeGenerator to generate the C++ code but I am getting the following error:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/1619948/fc8774d8-b742-4407-86ef-e877d347f5d3)\r\n\r\nLooks like it is trying to use dbScanPin in the private dbScanPartition.h class, but if I change it to _dbScanPin in my dbScanPartition.json, then it fails in the public class definition in db.h.\r\n\r\nIs there an step that I am missing or maybe some config?\r\n\r\nThanks!\r\n"}, {"assistant": "Use dbId to store references to other db objects\r\n```\r\n \"name\": \"start\",\r\n- \"type\": \"dbScanPin\"\r\n+ \"type\": \"dbId\"\r\n },\r\n {\r\n \"name\": \"stop\",\r\n- \"type\": \"dbScanPin\"\r\n+ \"type\": \"dbId\"\r\n },\r\n```"}, {"user": "I forgot to close this issue, but the answer was given by @maliberty .\r\n\r\nWriting the custom setter was the way to go when implementing this."}]} +{"messages": [{"user": "Hello,\r\n\r\nI'm trying to use openroad commands to place custom pdk cells but they overlap with power grid.\r\n\r\nHere in https://github.com/OuDret/my_pdk/tree/main you can see all the files I'm using. \r\n\r\nThere are also all the commands I'm running in ./flow.txt. You can simply copy-paste all the lines in flow.txt file into OpenRoad command line at once to reproduce the case. \r\n\r\nUnfortunately I'm using absolute path when loading tech and design so you may need to change it.\r\n\r\nI'm trying to simplify the flow as much as I can so I may have forgotten to run some important steps.\r\n\r\nThank you for any advice you can provide\r\n\r\n[EDIT] I forgot to show the 2 warnings that are raised when I run ```improve_placement``` which must be related to the overlap issue.\r\n```\r\n [WARNING DPO-0201] Placement check failure during legalization.\r\n [WARNING DPO-0381] Encountered 57 issues when orienting cells for rows.\r\n```\r\n\r\n![cell_overlap_power_grid](https://github.com/The-OpenROAD-Project/OpenROAD/assets/74424277/43d68ad2-28ab-4749-968d-c9cfd65a4397)\r\n![counter_design](https://github.com/The-OpenROAD-Project/OpenROAD/assets/74424277/849b8ffe-5426-4157-b8a2-60d43c628e38)\r\n"}, {"assistant": "Where is this process are you manually placing these cells? Are you marking them as fixed?"}, {"assistant": "I tried to run flow.txt but I get in global placement:\r\n```\r\n[ERROR GRT-0126] Layers met2 and met3 have the same preferred routing direction \r\n(VERTICAL).\r\n```\r\nThis seems wrong - can you explain what the intention is?"}]} +{"messages": [{"user": "Hello,\r\n\r\nI have a question about the target placement density in the GPL tool. \r\n\r\nI don't really get what it does quantitatively speaking. I get that the closer target_density is close to 1, the tighter the placement will be, but it doesn't seems to be computed relatively to the die area. I mean by that that I would expect a placement density of 0.1 to be as sparse as possible on the die, but if the die is too small then the placement density also need to be reduced so I visualize some cells to be \"outside\" the die which OpenROAD don't like. \r\n\r\nBut again, how does the target density argument is influencing the placement tool ? The density is computed with regard to what ?"}, {"assistant": "The layout is divided into bins of fixed area. For each bin the density is the area of cells in the bin divided by the bin area. Cells that want to cluster tightly together will be limited by the target density. It has nothing to do with overall design area as you note."}]} +{"messages": [{"user": "I have a design which uses multiples of 4 blocks or macros which were designed to be individually optimized and then placed by abutment. I can get pretty decent runs on one block at a time but when I try to use the blocks in the whole design all that comes out is the first listed block.\r\n\r\nLooking through examples I see similar behavior with AES. The whole design does evidence hierarchy with fuzzy clouds for the repeated blocks, but they are not macros using the block design. If aes-block is run it generates a nice compact aes_rcon but ignores aes_sbox, and that is all it generates. Not a whole AES pipe.\r\n\r\nI tried the mock-array example but the results look nothing like I see in discussions here. Probably something I have not got right in chisel or other parts. Anyway the build is so indirect that I could spend a long time puzzling over it and never fix it or learn about blocks.\r\n\r\nIt looks to me like AES is intended to work the same kind of design, with two tightly optimized blocks that are then repeated. Are other people seeing it do that? Any hints why I see no blocks incorporated in the aes project, and only one lone block in aes-block with everything else missing?"}, {"assistant": "Is this what you see for aes-blocks?\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/56fe74b4-26ef-4603-9fb6-4c53c158bf6c)\r\n"}]} +{"messages": [{"user": "I am trying to use a proprietary pdk and I hit issue when running command pin_access.\r\n\r\n# Global routing\r\npin_access -bottom_routing_layer $min_routing_layer \\\r\n -top_routing_layer $max_routing_layer\r\n\r\nFrom the error message, it looks like layer \"VV\" is not recognized. However, while reading tech file (earlier in the flow), It did find this layer. There are lots of warnings during tech file read but I see similar warnings for other layers too.\r\n\r\nThis is the error message I get:\r\n[WARNING DRT-0124] Via VV with unused layer VV_XX_450_450_450_450_VV will be ignored.\r\n[ERROR DRT-0129] Unknown layer VV for viarule VV_VIAGEN.\r\n\r\nThese are some of information and warnings while reading tech file.\r\n[WARNING ODB-0279] parse mismatch in layer property LEF58_TYPE for layer II_QM_BOT : \"TYPE SPECIALCUT LAYER IA QM ;\"\r\n[INFO ODB-0388] unsupported LEF58_ANTENNAGATEPLUSDIFF property for layer VV :\"ANTENNAGATEPLUSDIFF OXIDE1 5.0 ; \"\r\n\r\nMy question is -\r\nIt seems to read tech file without error at the beginning of the flow. Then why is it reading tech and libs again with the command pin_access. First time it didn't error out, but it generates error during this step.\r\n\r\n# Global routing\r\npin_access -bottom_routing_layer $min_routing_layer \\\r\n -top_routing_layer $max_routing_layer\r\n[INFO DRT-0149] Reading tech and libs.\r\n\r\nI have checked that layer VV is defined in the tech file.\r\n\r\nAny suggestions and ideas on what I can try to bypass this error.\r\n\r\nI am only interested in rough timing and area results after global routing.\r\n\r\n\r\n\r\n"}, {"assistant": "If you only want rough results you can skip the pin_access command. The LEF was read earlier but the interpretation is being made now and some issue is being flagged. The exact issue is hard to say from this info."}, {"user": "Thanks for suggestion. This enabled me to get past this point and finish global route. "}]} +{"messages": [{"user": "Hello,\r\n\r\nI have a quick question out of pure curiosity : How does OpenROAD compute the die area when using the core_utilization argument in the `initialize_floorplan`?"}, {"assistant": "The code starts at https://github.com/The-OpenROAD-Project/OpenROAD/blob/2bdae1c13b8c6387644f12f760254f472b04f4e7/src/ifp/src/InitFloorplan.cc#L126\r\n\r\nIn short we take the area of the instances coming from synthesis and convert that to a core area based on the utilization. We then shape that core area based on the aspect_ratio. Finally we expand it by the spacing on each edge to get the die area."}]} +{"messages": [{"user": "Hello,\r\n\r\nI have some questions about a warning that I stumble upon while trying to use the `extract_parasitics` function with the rcx_pattern.rules file. I have an adder of variable size with two input words and one output word, the nets linked to the output word are raising some warnings while those for the input words do not.\r\n\r\nThe warning types are the following : \r\n\r\n[WARNING RCX-0114] Net 282 S[122] does not start from an iterm or a bterm.\r\n\r\nBut the thing is that when I highlight this net in the gui, it seems to be connected to a pin on the top layer from the first metal layer (I have hidden the Pad layer to make the name readable) : \r\n\r\n\"Capture\r\n\r\nI don't really understand what this warning is about since the net (and the others) do seems to be connected from front to end, and I didn't do anything particular to it compared to the input words nets.\r\n\r\nI thus have three questions : \r\n\r\n1) What does this warning means, and what should I look for to solve it ?\r\n2) What is the difference between \"iterm\" and \"bterm\" ?\r\n3) I also have a DRT warning saying \"Cut layer V0 has no default via defined\", should a design have default vias ? How to define them and what are they used for ? Are they there to connect the standard cells source/gate/drain to M1 ?"}, {"assistant": "1) Its hard to tell whats going on with the routing in the image. Can you provide a test case?\r\n2) an iterm is the pin of a cell whereas a bterm is a top level pin\r\n3) I wouldn't worry about it. Which PDK is this?"}]} +{"messages": [{"user": "What is OpenROAD trying to tell me here? 221.3120, 482.4900 is at the \"W\" in the image below:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/a30f8201-095a-4c31-9e75-04c320159f48)\r\n\r\n\r\n"}, {"assistant": "That it can't legally put any via here to make a connection between these shapes. It isn't necessarily a problem but it could be so it lets you know."}]} +{"messages": [{"user": "How can I use \"check_drc\"?\r\n1. I load a LEF file (`read_lef file.lef`)\r\n2. I load a DEF file (`read_def file.def`) produced after `detailed_route` with still some DRC violations.\r\n3. I run `drt::check_drc -output_file file.rpt`\r\n4. OpenROAD crashes with:\r\n```bash\r\n/usr/include/c++/10/bits/stl_vector.h:1063: std::vector<_Tp, _Alloc>::const_reference std::vector<_Tp, _Alloc>::operator[](std::vector<_Tp, _Alloc>::size_type) const [with _Tp = std::unique_ptr; _Alloc = std::allocator >; std::vector<_Tp, _Alloc>::const_reference = const std::unique_ptr&; std::vector<_Tp, _Alloc>::size_type = long unsigned int]: Assertion '__builtin_expect(__n < this->size(), true)' failed.\r\nSignal 6 received\r\nStack trace:\r\n 0# 0x000055F65D6A0236 in openroad\r\n 1# 0x00007F3C42497D60 in /lib/x86_64-linux-gnu/libc.so.6\r\n 2# gsignal in /lib/x86_64-linux-gnu/libc.so.6\r\n 3# abort in /lib/x86_64-linux-gnu/libc.so.6\r\n 4# 0x000055F65D6A08A2 in openroad\r\n 5# fr::io::Parser::initRPin_rpin() in openroad\r\n 6# fr::io::Parser::initRPin() in openroad\r\n 7# triton_route::TritonRoute::initGuide() in openroad\r\n 8# triton_route::TritonRoute::checkDRC(char const*, int, int, int, int) in openroad\r\n 9# 0x000055F65DEBB7C8 in openroad\r\n10# TclNRRunCallbacks in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n11# Tcl_RecordAndEvalObj in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n12# Tcl_MainEx in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n13# main in openroad\r\n14# __libc_start_main in /lib/x86_64-linux-gnu/libc.so.6\r\n15# _start in openroad\r\n[1] 4098007 abort openroad\r\n```"}, {"assistant": "Be aware check_drc is not a general purpose checker and is only verifying the signal routing according to LEF. It is expecting to see guides as well so you could either\r\n1) Use read_db to load the database that has guides in it\r\n2) Write out the guide and load them later.\r\n\r\n1 is probably simpler."}]} +{"messages": [{"user": "I am using Yosys for synthesis of memory. Then I am taking the netlist generated to openroad for all the next sequence of steps. However, it is showing syntax error whenever I have a memory type element. Even if I try for a single port ram, it is showing syntax error at the line of memory.\r\nBy memory I mean (ex- reg [0:3] cpu [0:15]) \r\nI am using gcd nangate45 library"}, {"assistant": "reg [0:3] cpu [0:15] should not be in the output of synthesis so something is wrong there. It is not a structural construct. There is too little information to suggest anything. Please open an issue with a test case if possible."}]} +{"messages": [{"user": "Hello,\r\n\r\nI have a question regarding the relationship between the design size and the memory usage.\r\n\r\nI use a virtual machine, with 16GB of RAM allocated to it. I tried to run an LDPC design, which made the memory usage skyrocket. I wanted to see some test to see what would have the most impact on memory usage, so I created a very simple and stupid adder design where I increased its input and output word size from 128bit to 5120bit. Then I ran the design through OpenROAD, where I started from a very large die (`core_utilization=5` and `placement_density=0.1`) and reduced the die size incrementally (up to `core_utilization=50`and `placement_density=0.8`). These are the results that I obtained :\r\n\r\n![OpenROAD_memory_vs_size](https://github.com/The-OpenROAD-Project/OpenROAD/assets/61243950/dd43a2fd-2320-43e5-bf46-07bd1e7e1795)\r\n\r\nWhat surprised me was that even though, unsurprisingly, higher cell count and wire length (due to the larger adder) resulted in higher memory usage, the memory footprint was always higher when using a larger die area even if the design in itself was very small in comparison. \r\n\r\nI was wondering why it was so, why is it that when the die is bigger so is the memory used, is it because objects such as filler cells are also loaded in ? \r\nSince the memory used also increase during the run : would it be possible to run a design, too big to be done in one run, in two separated runs to alleviate the limited RAM available ? Or will the memory be filled as soon as the database is loaded in ?\r\n "}, {"assistant": "A bigger die area means more placement sites in the rows, more area to manage during placement, more fill cells, etc. \r\n\r\nOn what PDK was this experiment? In your highest memory case, what was the memory usage at each step?\r\n\r\nIf you split the design and the build an abstract (a .lef & .lib) for each piece then the top level will take less memory as it isn't seeing the details. This is a common strategy for hierarchical design. You can see an example of this in https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/tree/master/flow/designs/asap7/mock-array"}]} +{"messages": [{"user": "My apologies if this is an obvious question. I am working with a fab trying to develop a new process that currently has 2 metal layers, and we were wondering if we could use OpenROAD/OpenLANE to build test chips. I was unable to find an answer in the documentation, but if it is there I would love to know where to look. Thank you for your help!"}, {"assistant": "In theory we could route in two layers but we've never tried it. We don't have a specialized channel router. My expectation is that we will hit some issues and have to iterate. If the PDK is closed it will be harder to do so."}, {"assistant": "I'm sure that Fastroute and TritonRoute are capable of routing on two layers. "}]} +{"messages": [{"user": "This is for the top level of MegaBoom that I'm playing around with.\r\n\r\nIs this warning telling me that it can't find a route for the buffer tree for the pin in the warning?\r\n\r\nIt looks like this buffer tree is going from the iregister_read macro to the ALUExeUnit, which traverses Rob(reorder buffer), rename stage and the memory issue unit. The mpl2 macro placement is unfortunate here...\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/e3c6b965-bf83-403c-9dd5-70413735a8ca)\r\n\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c2a76f06-f286-4b5a-8bc7-2fc0219bc9f8)\r\n"}, {"assistant": "@eder-matheus please respond"}, {"assistant": "@oharboe @maliberty This warning is related to the estimate_parasitics using global route parasitics. It usually happens when a routing topology is not correctly translated to the parasitics estimation structures. I will look into the test case and fix the cause of this bug."}]} +{"messages": [{"user": "Trying to use \r\nopenroad==2.0_10145_g0de6f5131 installed with conda gives the following error -\r\n`openroad: error while loading shared libraries: libfmt.so.8: cannot open shared object file: No such file or directory`\r\n\r\nThis error occurs only on Ubuntu20.04 because libfmt version 8 does not exist for it. \r\nAre there any workarounds to this? "}, {"assistant": "I don't think we host a conda installation. The installer would be from a third party and you should ask them for support."}, {"assistant": "@proppy is the conda installer something you support?"}, {"assistant": "yes, it seems they already filed an issue over at https://github.com/hdl/conda-eda/issues/360 (so feel free to close the issue here)."}]} +{"messages": [{"user": "Hello,\r\n\r\nI have a question regarding the differences between the PPL and PAD tools, especially the PAD bump placement for flip chip designs. I don't really get the differences between the PPL and PAD tools when it comes to IO placed on the top metal layer, and their \"relationship\" with the GPL tool.\r\n\r\nI am right now doing some tests using different designs using the PPL tool. It is used with GPL first by placing the IO without considering GPL, then doing Global PLacement followed by a Pin PLacement after it, finishing by a final GPL. I read that it was due to some circular dependency between the two tools, so this was the way things were done. \r\nNow I am using PPL to do some 3D Face-to-Face implementation, and am using the `define_pin_shape_pattern` command to place the IO on the top metal layer.\r\n\r\nFrom what I understood PPL doesn't have/need a LEF object for the bump as it will create a metal shape in place of the pin, based off of the constraint given to the tool by the user before being routed in the subsequent steps.\r\n\r\n\r\nI am now trying to understand what the PAD tool really is about, how it differs from what PPL is and what his use case may be, but I am a bit confused when it comes to 3D interconnect.\r\n\r\nI understand that PAD is used for chip level connection, which raise a question for me (that is asked below), that requires a LEF object for top layer bumps.\r\nWhen it comes to flip chip design, the PAD tool seems to be the default candidate but something is bothering me, it is simply that there is no pin position optimization in it as opposed to PPL (which would probably not give a minimal \"3D\" wire length), that the bump assignement is done manually, and that in the example script given in _OpenROAD/src/pad/test_ link the bumps to an IO ring which I don't think is the goal in my application.\r\n\r\nAbout the pin position optimization, I was told by @rovinski in #4061 that GPL will still do some HPWL optimization (and that the team would probably be interested in implementing 3D interconnect as part of the PPL tool), but at first sight it doesn't seem to be the most optimal way to proceed for \"3D\" routing since the assignement will be done manually. This leads me to the second question about assignment : Since I will probably need to have thousands of IOs on the top layer, manual assignment seems tedious if not even suboptimal due to the lack of automatic bump repositioning. \r\nI get that using a tool for flip-chip design would be make more sense but I must say that, when it comes to top layer bumps, I don't see really the interest in going for PAD rather than PPL\r\n\r\n\r\n\r\nMy questions thus are : \r\n\r\n0) What are the exact mechanisms that OpenROAD use to minimize wire length w.r.t. IO pins ?\r\n1) If PAD is used for chip level connections then what is the use case for PPL ?\r\n2) What are the inherent differences between PAD and PPL ?\r\n3) If PAD is the default for flip-chip design, why implementing such a thing as part of PPL ?\r\n4) Does will OpenROAD route differently when using PAD or PPL ? Especially when talking about memory usage ?\r\n5) Will the use of a LEF object in the PAD tool create a difference with regard to the pin created by PPL ? Could I use a LEF object for PPL instead to benefit from the placement optimization?\r\n6) Could we imaging eventually a flow mixing PAD and PPL, where the PPL tool is used for 3D interconnections ?\r\n\r\n\r\n"}, {"assistant": "What is driving the bumps? Usually you need an IO driver and that means you need to use pad."}, {"assistant": "I think the biggest difference between pad and ppl is that pad tries to deal with io cells. Typically the foundry will require you to place specialized io cells that deal with esd and what not.\r\n\r\nppl does a similar pin placement, but doesn't deal with io cells. If you don't need io cells between your dies then ppl probably is the solution you should use or enhance "}]} +{"messages": [{"user": "Hi ,\r\nI'm working with foreign tech that has the std cell BUFFX16 with huge M1 shape for output pin. \r\nDuring pin access routing, the DRC rule on min via1 cut is not satisfied, so the pin has no access point stopping the flow.\r\nI read on other discusstion that is not yet possible to place multiple via cut, so, could be possible to exclude the drc check for minimum cut number to use for a list of std cells?\r\n\r\nAn alternative approach should be modify the LEF using a thinner M1 shape, correct?\r\n\r\nThanks"}, {"assistant": "Have you verified that the problem is min cut and not another rule? If so, you might just exclude that cell from being used putting it in the don't use list."}]} +{"messages": [{"user": "\r\nI've been trying to fully install OpenROAD using the` ./build_openroad.sh --local --threads 1` command but I keep getting the error\r\n```\r\n[INFO FLW-0027] Saving logs to build_openroad.log\r\n[INFO FLW-0028] ./build_openroad.sh --local --threads 1\r\n[INFO FLW-0002] Updating git submodules.\r\n[INFO FLW-0001] Using local build method. This will create binaries at 'tools/install' unless overwritten.\r\n[INFO FLW-0017] Compiling Yosys.\r\nmake: Entering directory '/home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/yosys'\r\nmkdir -p /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin\r\ncp yosys yosys-config yosys-abc yosys-filterlib yosys-smtbmc /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin\r\nstrip -S /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys\r\nstrip /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys-abc\r\nstrip /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys-filterlib\r\nmkdir -p /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/share/yosys\r\ncp -r share/. /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/share/yosys/.\r\nmake: Leaving directory '/home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/yosys'\r\n[INFO FLW-0018] Compiling OpenROAD.\r\n-- OpenROAD version: v2.0-10669-g436c7801a\r\n-- System name: Linux\r\n-- Compiler: GNU 11.4.0\r\n-- Build type: RELEASE\r\n-- Install prefix: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/OpenROAD\r\n-- C++ Standard: 17\r\n-- C++ Standard Required: ON\r\n-- C++ Extensions: OFF\r\n-- TCL library: /usr/lib/x86_64-linux-gnu/libtcl.so\r\n-- TCL header: /usr/include/tcl/tcl.h\r\n-- TCL readline library: /usr/lib/x86_64-linux-gnu/libtclreadline.so\r\n-- TCL readline header: /usr/include/x86_64-linux-gnu\r\n-- boost: 1.74.0\r\n-- spdlog: 1.9.2\r\nCMake Warning at src/CMakeLists.txt:242 (message):\r\n spdlog: SPDLOG_FMT_EXTERNAL=ON\r\n\r\n\r\n-- Could NOT find Doxygen (missing: DOXYGEN_EXECUTABLE) \r\n-- STA version: 2.4.0\r\n-- STA git sha: 44f06c521560e803859218732255b3259de048e1\r\n-- System name: Linux\r\n-- Compiler: GNU 11.4.0\r\n-- Build type: RELEASE\r\n-- Build CXX_FLAGS: -O3 -DNDEBUG\r\n-- Install prefix: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/OpenROAD\r\n-- TCL library: /usr/lib/x86_64-linux-gnu/libtcl.so\r\n-- TCL header: /usr/include/tcl/tcl.h\r\n-- SSTA: 0\r\n-- STA executable: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/OpenROAD/src/sta/app/sta\r\nCMake Error at src/gpl/CMakeLists.txt:44 (find_package):\r\n By not providing \"Findortools.cmake\" in CMAKE_MODULE_PATH this project has\r\n asked CMake to find a package configuration file provided by \"ortools\", but\r\n CMake did not find one.\r\n\r\n Could not find a package configuration file provided by \"ortools\" with any\r\n of the following names:\r\n\r\n ortoolsConfig.cmake\r\n ortools-config.cmake\r\n\r\n Add the installation prefix of \"ortools\" to CMAKE_PREFIX_PATH or set\r\n \"ortools_DIR\" to a directory containing one of the above files. If\r\n \"ortools\" provides a separate development package or SDK, be sure it has\r\n been installed.\r\n\r\n\r\n-- Configuring incomplete, errors occurred!\r\n\r\n```\r\nI've installed or-tools using `git clone https://github.com/google/or-tools.git` and I'm still getting the error "}, {"assistant": "This is better to submit as an issue in order to get a better handle on your environment.\r\n\r\nThat being said, where are you installing ortools? The default location that CMake looks for is the default paths searched by CMake's `find_package` and also `/opt/or-tools/lib64/` and `/opt/or-tools/lib/`. If it's not in one of those locations, you should either install it there, or add `--openroad-args \"ortools_DIR=path/to/your/ortools/cmake/file\"` to your script invocation."}, {"user": "Thanks. I've added `--openroad-args \"ortools_DIR=path/to/your/ortools/cmake/file\"` to my script, and it works kind of but I'm getting another error\r\n\r\n```\r\n[INFO FLW-0027] Saving logs to build_openroad.log\r\n[INFO FLW-0028] ./build_openroad.sh --local threads 2 --openroad-args /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build\r\n[INFO FLW-0002] Updating git submodules.\r\n[INFO FLW-0001] Using local build method. This will create binaries at 'tools/install' unless overwritten.\r\n[INFO FLW-0017] Compiling Yosys.\r\nmake: Entering directory '/home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/yosys'\r\nmkdir -p /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin\r\ncp yosys yosys-config yosys-abc yosys-filterlib yosys-smtbmc /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin\r\nstrip -S /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys\r\nstrip /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys-abc\r\nstrip /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/bin/yosys-filterlib\r\nmkdir -p /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/share/yosys\r\ncp -r share/. /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/yosys/share/yosys/.\r\nmake: Leaving directory '/home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/yosys'\r\n[INFO FLW-0018] Compiling OpenROAD.\r\n-- ortools version: 9.7.3002\r\n-- Build type: Release\r\n-- Build C++ library: ON\r\n-- Build Python: OFF\r\n-- Build Java: OFF\r\n-- Build .Net: OFF\r\n-- Build Flatzinc: ON\r\n-- Build LP Parser: ON\r\n-- Build standalone Glop: OFF\r\n-- Build samples: ON\r\n-- Build C++ samples: ON\r\n-- Build Python samples: OFF\r\n-- Build Java samples: OFF\r\n-- Build .Net samples: OFF\r\n-- Build examples: ON\r\n-- Build C++ examples: ON\r\n-- Build Python examples: OFF\r\n-- Build Java examples: OFF\r\n-- Build .Net examples: OFF\r\n-- Build documentation: OFF\r\n-- Install doc: OFF\r\n-- Build all dependencies: ON\r\n-- Build ZLIB: ON\r\n-- Build abseil-cpp: ON\r\n-- Build protobuf: ON\r\n-- Build re2: ON\r\n-- Build googletest: ON\r\n-- COIN-OR support: OFF\r\n-- GLPK support: OFF\r\n-- HiGHS support: OFF\r\n-- PDLP support: ON\r\n-- Build PDLP: ON\r\n-- Build eigen3: ON\r\n-- SCIP support: OFF\r\n-- CPLEX support: OFF\r\n-- XPRESS support: OFF\r\n-- C++: Build doc: OFF\r\n-- Fetching ZLIB\r\n-- Populating zlib\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/zlib-subbuild\r\n[100%] Built target zlib-populate\r\n-- Fetching ZLIB - fetched\r\n-- Fetching Abseil-cpp\r\n-- Populating absl\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/absl-subbuild\r\n[100%] Built target absl-populate\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:605 (message):\r\n ABSL_CXX_STANDARD:\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMakeLists.txt:86 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:606 (message):\r\n CMAKE_CXX_STANDARD: 17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMakeLists.txt:86 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:607 (message):\r\n CMAKE_CXX_STANDARD_REQUIRED: ON\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMakeLists.txt:86 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:608 (message):\r\n CMAKE_CXX_FLAGS:\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMakeLists.txt:86 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/absl/copts/AbseilConfigureCopts.cmake:97 (message):\r\n ABSL_CXX_STANDARD: 17.\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMake/AbseilHelpers.cmake:18 (include)\r\n build/_deps/absl-src/CMakeLists.txt:87 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:605 (message):\r\n ABSL_CXX_STANDARD: 17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMake/AbseilHelpers.cmake:19 (include)\r\n build/_deps/absl-src/CMakeLists.txt:87 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:606 (message):\r\n CMAKE_CXX_STANDARD: 17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMake/AbseilHelpers.cmake:19 (include)\r\n build/_deps/absl-src/CMakeLists.txt:87 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:607 (message):\r\n CMAKE_CXX_STANDARD_REQUIRED: ON\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMake/AbseilHelpers.cmake:19 (include)\r\n build/_deps/absl-src/CMakeLists.txt:87 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilDll.cmake:608 (message):\r\n CMAKE_CXX_FLAGS:\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/CMake/AbseilHelpers.cmake:19 (include)\r\n build/_deps/absl-src/CMakeLists.txt:87 (include)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:20 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:33 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:44 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:58 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:76 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:95 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:107 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:121 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:140 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:161 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:177 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:220 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:249 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:428 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:539 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:591 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:623 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/base/CMakeLists.txt:649 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/algorithm/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/algorithm/CMakeLists.txt:42 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/cleanup/CMakeLists.txt:16 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/cleanup/CMakeLists.txt:30 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:91 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:120 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:170 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:186 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:204 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:277 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:313 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:351 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:387 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:423 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:453 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:530 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:556 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:581 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:613 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:625 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:638 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:664 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:679 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:691 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/container/CMakeLists.txt:760 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:16 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:31 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:56 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:97 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:109 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/crc/CMakeLists.txt:150 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:19 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:61 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:115 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:132 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:169 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:191 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:223 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/debugging/CMakeLists.txt:285 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:18 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:34 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:54 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:75 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:96 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:113 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:133 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:151 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:174 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:199 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:224 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:250 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/flags/CMakeLists.txt:269 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/functional/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/functional/CMakeLists.txt:53 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/functional/CMakeLists.txt:81 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/hash/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/hash/CMakeLists.txt:106 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/hash/CMakeLists.txt:134 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:18 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:36 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:56 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:74 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:89 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:103 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:127 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:147 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:163 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:182 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:219 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:248 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:264 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:281 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:363 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:377 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:394 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:409 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:424 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:444 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:463 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:487 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:507 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:526 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:541 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:563 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:580 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:597 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:643 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/log/CMakeLists.txt:658 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/memory/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/meta/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/meta/CMakeLists.txt:45 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/numeric/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/numeric/CMakeLists.txt:44 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/numeric/CMakeLists.txt:79 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/numeric/CMakeLists.txt:89 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/profiling/CMakeLists.txt:15 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/profiling/CMakeLists.txt:40 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/profiling/CMakeLists.txt:67 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:35 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:70 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:161 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:199 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:214 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:517 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:531 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:547 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:561 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:583 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:639 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:657 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:672 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:689 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:705 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:719 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:739 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:757 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:775 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:792 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:810 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:827 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:847 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:864 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/random/CMakeLists.txt:1155 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/status/CMakeLists.txt:16 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/status/CMakeLists.txt:58 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:77 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:396 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:409 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:579 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:620 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:647 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:676 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:691 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:725 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:794 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:833 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/strings/CMakeLists.txt:866 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/synchronization/CMakeLists.txt:18 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/synchronization/CMakeLists.txt:37 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/synchronization/CMakeLists.txt:50 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/time/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/time/CMakeLists.txt:45 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/time/CMakeLists.txt:61 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:16 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:33 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:47 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:106 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:163 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:183 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:293 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:198 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:296 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/types/CMakeLists.txt:332 (absl_cc_library)\r\n\r\n\r\nCMake Warning at build/_deps/absl-src/CMake/AbseilHelpers.cmake:342 (message):\r\n Force CXX_FLAGS flags to cxx_std_17\r\nCall Stack (most recent call first):\r\n build/_deps/absl-src/absl/utility/CMakeLists.txt:17 (absl_cc_library)\r\n\r\n\r\n-- Fetching Abseil-cpp - fetched\r\n-- Fetching Protobuf\r\n-- Populating protobuf\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/protobuf-subbuild\r\n[100%] Built target protobuf-populate\r\n-- \r\n-- 23.3.0\r\n-- Fetching Protobuf - fetched\r\n-- Fetching re2\r\n-- Populating re2\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/re2-subbuild\r\n[100%] Built target re2-populate\r\n-- Fetching re2 - fetched\r\n-- Fetching Eigen3\r\n-- Populating eigen3\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/eigen3-subbuild\r\n[100%] Built target eigen3-populate\r\n-- Performing Test COMPILER_SUPPORT_std=cpp03\r\n-- Performing Test COMPILER_SUPPORT_std=cpp03 - Success\r\n-- Standard libraries to link to explicitly: none\r\n-- Found unsuitable Qt version \"5.15.3\" from /usr/bin/qmake\r\n-- Qt4 not found, so disabling the mandelbrot and opengl demos\r\n-- Could NOT find CHOLMOD (missing: CHOLMOD_INCLUDES CHOLMOD_LIBRARIES) \r\n-- Could NOT find UMFPACK (missing: UMFPACK_INCLUDES UMFPACK_LIBRARIES) \r\n-- Could NOT find KLU (missing: KLU_INCLUDES KLU_LIBRARIES) \r\n-- Could NOT find SuperLU (missing: SUPERLU_INCLUDES SUPERLU_LIBRARIES SUPERLU_VERSION_OK) (Required is at least version \"4.0\")\r\n-- A version of Pastix has been found but pastix_nompi.h does not exist in the include directory. Because Eigen tests require a version without MPI, we disable the Pastix backend.\r\n-- \r\n-- Configured Eigen 3.4.0\r\n-- \r\n-- Available targets (use: make TARGET):\r\n-- ---------+--------------------------------------------------------------\r\n-- Target | Description\r\n-- ---------+--------------------------------------------------------------\r\n-- install | Install Eigen. Headers will be installed to:\r\n-- | /\r\n-- | Using the following values:\r\n-- | CMAKE_INSTALL_PREFIX: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/tools/install/OpenROAD\r\n-- | INCLUDE_INSTALL_DIR: include/eigen3\r\n-- | Change the install location of Eigen headers using:\r\n-- | cmake . -DCMAKE_INSTALL_PREFIX=yourprefix\r\n-- | Or:\r\n-- | cmake . -DINCLUDE_INSTALL_DIR=yourdir\r\n-- doc | Generate the API documentation, requires Doxygen & LaTeX\r\n-- blas | Build BLAS library (not the same thing as Eigen)\r\n-- uninstall| Remove files installed by the install target\r\n-- ---------+--------------------------------------------------------------\r\n-- \r\n-- Fetching Eigen3 - fetched\r\n-- Fetching googletest\r\n-- Populating googletest\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build/_deps/googletest-subbuild\r\n[100%] Built target googletest-populate\r\n-- Fetching googletest - fetched\r\n-- Found long size: 8\r\n-- Found long long size: 8\r\n-- Found int64_t size: 8\r\n-- Found unsigned long size: 8\r\n-- Found unsigned long long size: 8\r\n-- Found uint64_t size: 8\r\n-- Found int * size: 8\r\n-- Adding proto path: $\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/algorithms/samples/knapsack.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/algorithms/samples/knapsack.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/algorithms/samples/simple_knapsack_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/algorithms/samples/simple_knapsack_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/assignment_linear_sum_assignment.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/assignment_linear_sum_assignment.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/assignment_min_flow.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/assignment_min_flow.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/balance_min_flow.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/balance_min_flow.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/simple_max_flow_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/simple_max_flow_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/simple_min_cost_flow_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/graph/samples/simple_min_cost_flow_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/glop/samples/simple_glop_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/glop/samples/simple_glop_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/cp_is_fun_cp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/cp_is_fun_cp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/minimal_jobshop_cp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/minimal_jobshop_cp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/nqueens_cp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/nqueens_cp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/nurses_cp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/nurses_cp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/rabbits_and_pheasants_cp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/rabbits_and_pheasants_cp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_cp_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_cp_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_ls_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_ls_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_routing_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/simple_routing_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_circuit_board.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_circuit_board.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_cities.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_cities.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_cities_routes.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_cities_routes.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_distance_matrix.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/tsp_distance_matrix.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_breaks.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_breaks.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_capacity.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_capacity.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_drop_nodes.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_drop_nodes.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_global_span.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_global_span.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_initial_routes.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_initial_routes.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery_fifo.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery_fifo.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery_lifo.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_pickup_delivery_lifo.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_resources.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_resources.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_routes.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_routes.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_solution_callback.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_solution_callback.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_starts_ends.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_starts_ends.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_time_windows.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_time_windows.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_with_time_limit.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrp_with_time_limit.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrptw_store_solution_data.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/constraint_solver/samples/vrptw_store_solution_data.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_groups_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_groups_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_task_sizes_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_task_sizes_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_teams_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/assignment_teams_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/basic_example.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/basic_example.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/bin_packing_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/bin_packing_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/integer_programming_example.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/integer_programming_example.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/linear_programming_example.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/linear_programming_example.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/mip_var_array.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/mip_var_array.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/multiple_knapsack_mip.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/multiple_knapsack_mip.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/simple_lp_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/simple_lp_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/simple_mip_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/simple_mip_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/stigler_diet.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/linear_solver/samples/stigler_diet.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/pdlp/samples/simple_pdlp_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/pdlp/samples/simple_pdlp_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_groups_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_groups_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_task_sizes_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_task_sizes_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_teams_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assignment_teams_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assumptions_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/assumptions_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/binpacking_problem_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/binpacking_problem_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/bool_or_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/bool_or_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/channeling_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/channeling_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/copy_model_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/copy_model_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/cp_is_fun_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/cp_is_fun_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/cp_sat_example.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/cp_sat_example.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/earliness_tardiness_cost_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/earliness_tardiness_cost_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/interval_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/interval_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/literal_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/literal_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/minimal_jobshop_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/minimal_jobshop_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/multiple_knapsack_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/multiple_knapsack_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/no_overlap_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/no_overlap_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/non_linear_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/non_linear_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/nqueens_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/nqueens_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/nurses_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/nurses_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/optional_interval_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/optional_interval_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/rabbits_and_pheasants_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/rabbits_and_pheasants_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/ranking_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/ranking_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/reified_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/reified_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/schedule_requests_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/schedule_requests_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/search_for_all_solutions_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/search_for_all_solutions_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/simple_sat_program.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/simple_sat_program.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solution_hinting_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solution_hinting_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solve_and_print_intermediate_solutions_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solve_and_print_intermediate_solutions_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solve_with_time_limit_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/solve_with_time_limit_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/step_function_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/step_function_sample_sat.cc: ...DONE\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/stop_after_n_solutions_sample_sat.cc: ...\r\n-- Configuring sample /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/ortools/sat/samples/stop_after_n_solutions_sample_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/constraint_programming_cp.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/constraint_programming_cp.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/costas_array_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/costas_array_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cryptarithm_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cryptarithm_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrp_disjoint_tw.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrp_disjoint_tw.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw_with_resources.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw_with_resources.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw_with_stop_times_and_resources.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/cvrptw_with_stop_times_and_resources.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/flow_api.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/flow_api.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/golomb_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/golomb_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/integer_programming.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/integer_programming.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_assignment_api.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_assignment_api.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_programming.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_programming.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_solver_protocol_buffers.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/linear_solver_protocol_buffers.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/magic_sequence_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/magic_sequence_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/magic_square_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/magic_square_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/max_flow.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/max_flow.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/min_cost_flow.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/min_cost_flow.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/nqueens.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/nqueens.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/qap_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/qap_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/random_tsp.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/random_tsp.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/slitherlink_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/slitherlink_sat.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/uncapacitated_facility_location.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/uncapacitated_facility_location.cc: ...DONE\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/variable_intervals_sat.cc: ...\r\n-- Configuring example /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/cpp/variable_intervals_sat.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/bug_fz1.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/bug_fz1.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/cpp11_test.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/cpp11_test.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/forbidden_intervals_test.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/forbidden_intervals_test.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/init_test.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/init_test.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue1303.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue1303.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue173.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue173.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue57.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/issue57.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/lp_test.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/lp_test.cc: ...DONE\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/min_max_test.cc: ...\r\n-- Configuring test /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/examples/tests/min_max_test.cc: ...DONE\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /home/ikenna/Work/vlsi/tools/OpenROAD-flow-scripts/or-tools/build\r\ngmake: Makefile: No such file or directory\r\ngmake: *** No rule to make target 'Makefile'. Stop.\r\n\r\n```"}, {"assistant": "@idokoike, please file a GitHub Issue and fill out our form which includes you environment and OS, also include which steps did you take, e.g., did you run the DependencyInstaller.sh? If not, any reason why?"}]} +{"messages": [{"user": "Hello,\r\n\r\nI would like to know if there is any way to write the log output from OpenROAD into a file (using a report_ type command). I am using a custom script, not the ORFS flow, so I would like to be able to store every tool report into a file to parse it using a script and find the information that I need.\r\n\r\nI know that the ORFS flow does something similar, but as I am using a custom script I would like to do know if OpenROAD allow to do so or if I need to find another way."}, {"assistant": "The output is a stdout so you can use standard unix file operations to capture it. See https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/6c4437edabdaddde9f100d76cc77b568c6cc073d/flow/Makefile#L539 in ORFS where we use \"2>&1 | tee\""}]} +{"messages": [{"user": "Hello,\r\n\r\nIs there any way I can use just the RTL-MP2 stand alone on either a RTL design or a gate netlist ? Issue is, we use proprietary tools so do not have OpenDB database for our designs.\r\n\r\nThanks & Regards,\r\nArun"}, {"assistant": "You can just read in a DEF, run it, and write it a DEF"}]} +{"messages": [{"user": "Hello,\r\n\r\nI am looking into the utilization of the PAD tool in order to place an IO bump array. I've look into the test scripts that are located in _OpenROAD/src/pad/test/_ to see how to implement IO bumps in a design. \r\n\r\nMy question simply has to do with ASAP7 and the bumps LEF files/object : I see that an IO LEF file containing a DUMMY_BUMP LEF object has been added/created for the Nangate45 PDK as well as for skywater130, but I haven't found anything similar for the ASAP7 PDK (at least in the OpenROAD github repository). \r\n\r\nDoes such a file exist somewhere, or does it need to be created ? "}, {"assistant": "I think it would have to be created."}]} +{"messages": [{"user": "Hi ,\r\nI'm working on tsmc 40nm porting and the flow stops to work on detailed routing with this error:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/24896919/7c4d6959-f126-4b62-940f-2b3ec59e3d26)\r\n\r\nDo you have any suggestion about the problem?\r\n\r\nThanks\r\n\r\nPS: working on not open source PDK I can't submit a testcase"}, {"assistant": "@osamahammad21 any guesses?\r\n"}, {"assistant": "@marcopoles Could you build openroad in DEBUG mode so that I can locate exactly at which line does this happen?"}, {"user": "Hi, here the new output:\r\n\"image\"\r\n"}, {"assistant": "@refaay Could you start a PR to ignore via definitions that include masterslice layers in DRT?"}, {"assistant": "Submitted PR #4149 to ignore masterslice vias in drt.\r\nPR #4149 merged."}]} +{"messages": [{"user": "Hi,\r\nI'm creating a new platform to manage tsmc40nm, but I have problem during routing phase: the flow stops due to \"heap underflow during 3D maze routing\" for the first net to route. The placing phase finish correctly.\r\nI run the flow on gcd and on a very simple verilog with 5 logic ports and on both cases the routing doesn't work.\r\nI've already checked that std cell library pins are aligned with tracks that I defined.\r\n\r\nDo you have any suggestion on how to debug the problem? How is it possible to print the path coordinates during the routing operation to check if it starts correctly?\r\n\r\nThanks"}, {"user": "I found the problem: routing/fastrouting don't manage adjacent metals with the same routing orientation"}]} +{"messages": [{"user": "Can openroad work with multi VT cells ( HVT , LVT , SVT ) and swap between them in a single run ? \r\nalso can openroad work with MultiModeMulti Corner File (mmmc) ?"}, {"assistant": "OR can swap between VT cells. OR supports multi-corner but not multi-mode STA."}, {"assistant": "> can openroad work with MultiModeMulti Corner File (mmmc) ?\r\n\r\nIf you are asking about MMMC files from commercial vendors, those are proprietary formats which we don't support. We support multi-corner analysis as mentioned. You can look in the [OpenSTA manual](https://github.com/The-OpenROAD-Project/OpenSTA/blob/master/doc/OpenSTA.pdf) to find the relevant commands."}]} +{"messages": [{"user": "Hello,\r\n\r\nI have a question to know how does OpenROAD computes the possible IO pin locations, when placed on the top-most metal layer. I use the ASAP7 PDK, I already routed a \"hello world\" design using the ibex core which has 264 IO pins. Now I want to test a bit the capabilities of OpenROAD and start doing increasingly bigger designs. \r\n\r\nRight now I have a design that has 4100 IO pins to place on the top layer. The die size is 20um x 20um more or less which, since I want to place the IO's on the Pad Layer whose track pitch is 0.08um, would give me more or less 62 tracks on which I can place my pins (mind you I place the pins with a minimum width of 0.32um). The M9 metal layer also has a track pitch of 0.08, so I could think that I would also have 62 tracks on which I could have a pin routed (on top). This would give me 62 x 62 = 3844 potential pin locations with this die size, but the tool give me the following error : \r\n\r\n`[ERROR PPL-0024] Number of IO pins (4100) exceeds maximum number of available positions (788).`\r\n\r\nWhich is far less than what I expect, so my questions are as follows : \r\n\r\n1. How does OpenROAD compute those available positions ?\r\n2. Could those locations be linked to an oversight/mistake in my synthesis script ?\r\n3. If I am mistaken in the way to compute the \"potential location\", how does one compute it properly based of the design size (number of cells/die area) ?"}, {"assistant": "@eder-matheus please help"}, {"assistant": "I don't know how the pin capacity is calculated exactly, but I know that the pin placer only works on edges of the die, not across an area. The total pins on the top layer would be around the perimeter, i.e. 62 * 4 = 248.\r\nBut, usually PPL does not want to place pins on edges that do not correspond to the preferred direction of that layer. PAD layers may or may not have a preferred direction. The other pins in the 788 reported may be coming from other layers along the edge of the die.\r\n\r\nBut anyways, you are probably looking at the wrong tool. You want to be looking at the [PAD tool](https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/pad/README.md) which is meant for bump placement on flip-chip designs, which is much closer to what you are trying to do."}, {"assistant": "We support pins over the top of the core area through define_pin_shape_pattern. The number of pins locations will be determined by the region and the x/y step given. If you need to actually place bumps at specific locations that is different than pin placement. What is your goal?"}]} +{"messages": [{"user": "I have tried to build the file again and again and tried troubleshooting but couldn't find the solution.\r\nPlease help me with the same.\r\nThe error ca be seen in the image below.\r\n![1](https://github.com/The-OpenROAD-Project/OpenROAD/assets/62429762/a297f803-b2c0-471a-8cdf-64e08515bcda)\r\n"}, {"assistant": "Hi @mehta-nitin,\r\nWhat you describe is an issue, not a discussion. We need more info on your system, environment, and the steps you have tried / how to reproduce -- please use the link below to file a GitHub Issue and follow our template instructions so we can better help you.\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/issues/new/choose"}]} +{"messages": [{"user": "Hello,\r\nI am quite new to Openroad and have a question regarding the GUI. I have read that it is possible to invoke the GUI with the command `openroad -gui`. But after entering the command, I get the message `openroad: command not found`.\r\nI have already read the instructions from the documentation, but apparently I am missing something essential.\r\nIf anyone has an idea what I am doing wrong, I would appreciate it very much.\r\n\r\n(PS: I have the ORFS installed locally on my machine and use _ubuntu 22.04_)"}, {"assistant": "Run `source env.sh`"}]} +{"messages": [{"user": "Hello, I have been reading documentation and trying stuff with given pdks for about two weeks. My goal was to run OpenRoadFlowScripts but, since there is a lot of stuff, I\u2019ve took its makefile, config files and scripts and just extracted the openroad commands that I really need, so I can exactly know what args and what files i need and create them. Also running the commands 1 by 1 alongside GUI application helps me understanding what\u2019s going on.\r\n\r\nWhen calling the commands tho, I had some issues i could not solve. If you have an idea of any of the following problems I'm facing or any advice let me know.\r\n\r\n**1. I didn\u2019t manage to initialize floorplan with custom die area. It doesn\u2019t matter which values I use as die_are or core_area, it just doesn\u2019t work properly.** \r\n\r\nWhen I run something like the command below, having stdSite size defined as 400 by 400 um it just does nothing. The verilog file provided is a simple inverter already synthesized using yosys into a single NAND cell which size is set in .lef as 200 by 200. \r\n\r\n\"Screenshot\r\n\r\n\r\nMeanwhile, if I just let openroad to decide what size to give it just works for small core utilization value, which kinda makes sense.\r\n\r\n\"Screenshot\r\n\r\n\r\nDo you think I\u2019m forgetting any step? The commands I run before getting to that point are the following:\r\n\r\n```\r\nread_liberty /path/lib/NandCellLibrary.lib\r\nread_lef /path/lef/NandCellLibrary.tech.lef\r\nread_lef /path/lef/NandCellLibrary.macro.lef \r\nread_verilog /path//inverter.v\r\nlink_design inverter\r\nread_sdc /path/constraint.sdc\r\n\r\ninitialize_floorplan -die_area {0 0 10000 10000} -core_area {1000 1000 5000 5000} -site stdSite\r\n```\r\n\r\n**2. I have no macros stored in odb despite having them declared in lef/NandCellLibrary.macro.lef** \r\n\r\nIf I just use utilization_area **floorplan_initialization** and keep running the following commands all seems to be working properly\r\n\r\n```\r\nmake_tracks met1 -x_offset 10 -x_pitch 10 -y_offset 10 -y_pitch 10\r\nmake_tracks met2 -x_offset 10 -x_pitch 10 -y_offset 10 -y_pitch 10\r\nmake_tracks met3 -x_offset 10 -x_pitch 10 -y_offset 10 -y_pitch 10\r\nremove_buffers\r\nplace_pins -hor_layer met2 -ver_layer met3 -random\r\nglobal_placement -density 0.5 -pad_left 0 -pad_right 0\r\n```\r\n\r\n\"Screenshot\r\n\r\nuntil I try to run macro placement\r\n\r\n\"Screenshot\r\n\r\nthe error raised means that when running the following tcl procedure it has not found any macro\r\n```\r\nproc find_macros {} {\r\n set macros \"\"\r\n\r\n set db [ord::get_db]\r\n set block [[$db getChip] getBlock]\r\n foreach inst [$block getInsts] {\r\n\tset inst_master [$inst getMaster]\r\n\r\n\t# BLOCK means MACRO cells\r\n\tif { [string match [$inst_master getType] \"BLOCK\"] } {\r\n \tappend macros \" \" $inst\r\n\t}\r\n }\r\n return $macros\r\n}\r\n```\r\n\r\nthe thing is that I have the NAND macro and another one called FILL defined in my .lefs and .lib . Then why could it be that there is no macro in db ?\r\n\r\n**Some things to be said.**\r\nWhen running **read_liberty**, it prints 1 into terminal. Does it mean that there\u2019s an error? It seems I can keep running things. If so, is there any way to properly debug it?\r\nIt also happens if I run **check_status** command after reading all input files, which I didn\u2019t even find in documentation, so I just ignored it.\r\n\r\nAgain, if you had any idea or advice of what I\u2019m doing wrong, if I skipt some important step, etc. let me know, please.\r\n\r\nIf i manage to make it work i will try to post the whole flow command by command. It may help someone someday\r\n\r\nThank you.\r\n\r\n"}, {"assistant": "What is the size of stdSite? Is this a PDK you can share or is it proprietary?\r\n\r\nDo you have any instances of the macro in your netlist?"}, {"assistant": "```\r\nSITE stdSite\r\n SYMMETRY Y ;\r\n CLASS CORE ;\r\n SIZE 500 BY 500 ;\r\nEND stdSite\r\n```\r\nis a huge site (500um x 500um) - I'm guessing that is a mistake though it doesn't explain the problem."}, {"assistant": "Your LEF is missing the units for \" DATABASE MICRONS \\;\". There is a bug when this is unspecified that I'll fix but you should set it (the LEF default value is very old)."}]} +{"messages": [{"user": "Any ideas in scaling the detailed router to handle circuits with 50 million cells? The memory footprint and runtime will be serious concerns. Blows are suggestions from ChatGPT :) \r\n\r\n1.\tParallelization: Leverage parallel processing techniques to distribute the routing tasks across multiple CPU cores or GPUs. Multithreading and GPU acceleration can significantly speed up the routing process.\r\n2.\tHierarchical Routing: Implement hierarchical routing techniques that break down the routing problem into smaller, more manageable subproblems. This reduces the complexity of routing large circuits.\r\n3.\tIncremental Routing: Instead of routing the entire circuit in one go, use incremental routing where you route smaller sections of the circuit at a time. This can improve efficiency and reduce memory requirements.\r\n4.\tAdvanced Algorithms: Explore advanced routing algorithms that are optimized for large-scale circuits. Some algorithms are specifically designed to handle massive designs efficiently.\r\n5.\tMemory Management: Optimize memory usage by employing data structures and algorithms that reduce memory overhead. Use memory-efficient representations of the circuit.\r\n6.\tDistributed Computing: Consider distributed computing approaches where the routing task is distributed across multiple machines or nodes in a cluster. This can further speed up routing for large circuits.\r\n7.\tMachine Learning: Investigate the use of machine learning techniques to predict and guide the routing process. Machine learning can help in making routing decisions more efficiently.\r\n8.\tResource-Aware Routing: Develop routing algorithms that are aware of available resources (e.g., routing tracks, vias) and can make intelligent decisions to optimize routing.\r\n9.\tAlgorithmic Improvements: Continuously research and implement algorithmic improvements and optimizations specific to global and detailed routing for large-scale circuits.\r\n10.\tHardware Acceleration: Explore the use of specialized hardware accelerators, such as FPGA-based routers, to handle the routing tasks efficiently.\r\n11.\tCircuit Abstraction: Utilize abstraction techniques to reduce the complexity of the circuit during routing without sacrificing the quality of the final solution.\r\n12.\tMemory Hierarchy: Optimize the use of cache and memory hierarchies to minimize data access latencies during the routing process.\r\n13.\tBenchmarking and Profiling: Regularly benchmark and profile the routing tool to identify performance bottlenecks and areas for improvement.\r\n14.\tUser Guidance: Provide options for users to guide the router's behavior, allowing them to make trade-offs between runtime and routing quality.\r\n15.\tIncremental Updates: Implement mechanisms for incremental updates, allowing users to modify parts of the design without rerouting the entire circuit.\r\n"}, {"assistant": "If the goal is detailed routing then you could look at the work we have done for distributed detailed routing. It doesn't solve the memory concern but it does allow you to apply a lot more CPU to the runtime."}, {"assistant": "@osamahammad21 would you run (or have Ahmed run) bsg_chip and mempool_group from [ISPD2024_benchmarks](https://drive.google.com/drive/u/2/folders/1afrsbeS_KuSeHEVfuQOuLWPuuZqlDVlw) on a 96-core machine on GCP to get a runtime & memory baseline. Also run with the distributed router to see how much it helps with runtime as you have before."}, {"assistant": "bsg_chip:\r\n\r\n- Machine: 96-CPU 360GB RAM\r\n- Total RUNTIME: 04:14:16\r\n- Peak Memory: 24.5GB\r\n- Pin Access:\r\n - [INFO DRT-0267] cpu time = 18:12:07, elapsed time = 00:33:37, memory = 8956.00 (MB), peak = 9547.98 (MB)\r\n- Detailed Routing:\r\n - [INFO DRT-0267] cpu time = 80:21:46, elapsed time = 03:26:59, memory = 19989.62 (MB), peak = 24497.96 (MB)\r\n- Converged After 57 Iterations\r\n- Did not set a min/max routing layer"}]} +{"messages": [{"user": "Hello,\r\n\r\nSo I want to implement a Face-to-face 3D flow on OpenROAD. I found that there is the define_pin_shape_pattern function and the documentation says that it could be used to help implement exactly that. \r\n\r\nWhat I did was simply take a small design to begin with (ibex) and place all of its I/O pins on the top layer (so a little more than 250, not a lot), to see what would happen. I tried with both the Skywater PDK and the Asap7 PDK, and in both cases the detailled routing step never converged towards an optimal solution without violations. One thing to know is that I already had a design to route with ONE pin on the top layer, even if the design was a very large and sparely placed ibex core. I haven't tried an \"in between\" case yet.\r\n\r\nI think I noticed (just an observation, I didn't properly tested that yet) that the number of violation increased a lot in \"3D\" (pins on the top layer) compared to the 2D case. To give an idea, using the ASAP7 PDK, the number of violations in 2D at the beginning of the optimisation iteration number one (so the second iteration) was around 6000, while in the 3D case it shot up to 22000 violations. \r\nThe behaviour of the number of violation in 2D was to decrease a lot, maybe then increase a little bit, but go to zero after while, in 3D, it started to \"oscillate\" around a value (that value seems to depend on the placement density and die size).\r\n\r\nI have let the flow run for a few hours in the 3D case (compared to maybe 20 minutes in the 2D case) without the number of violations ever really coming down (especially for such a small design, it seems strange). Usually in 2D the flow stopped after a few optimisation iterations, but in 3D even after 20 iterations (or 50+ with the Skywater PDK) it was still trying.\r\n\r\nMy questions are thus :\r\n\r\n1. Has the detailled routing ever finished in one of your test when multiples IO pins were on the top layer ? If so, was there a specific way that you used to setup the flow, for example reducing routing resources beforehand to prevent some eventual congestion due to the wires going to the I/O pins ?\r\n2. Can the tool become \"overwhelmed\" by the number of violations, and start running in circles while trying to handle them ?\r\n3. More generally, what are the limits of TritonRoute ?\r\n\r\n\r\n"}, {"assistant": "We have routed to top level bumps. This would be better as an issue with a test case showing the problem as this is too vague to say much. "}]} +{"messages": [{"user": "`-skip_io` in global_placement is not documented. What does it do and what are its uses?"}, {"assistant": "It ignore the IO ports when computing wirelength during placement. There is a circular dependency between global placement and io placement. We start the loop in ORFS by ignoring io placement while doing global placement, then do io placement, then re-run global placement considering IOs. Its not perfect but that's the use.\r\n\r\n@vvbandeira @luarss missing doc"}]} +{"messages": [{"user": "`-balance_levels` is not documented. What is does this flag do and what are the uses of it?\r\nEdit: \r\nMore context: It is a flag for `clock_tree_synthesis` command "}, {"assistant": "@luarss\r\ndid we miss this flag?"}, {"assistant": "When you have a non-register in the clock tree (eg clock-gate or inverter) then it attempts to ensure the are similar number of levels in the tree across that object. The idea is captured in this image\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/eddb3913-086a-4c3f-8744-7a3cadc90543)\r\n"}]} +{"messages": [{"user": "Run `make designs/nangate45/gcd/config.mk && make designs/nangate45/gcd/config.mk gui_final` and enable placement heat map.\r\n\r\nThis looks odd. There is less going on in the top and right edges, but it still \"looks wrong\" to me.\r\n\r\nThoughts?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/532929ca-34bd-4bce-b3b2-df547ff91e26)\r\n"}, {"assistant": "It does look a bit odd. @AcKoucher can you take a look?"}, {"assistant": "With nets being draw it's a bit hard to see. I just ran master in nangate45/gcd and as far as I see, everything looks ok.\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/104802710/28693f96-c91d-4b92-a1af-4985741156c5)\r\n\r\n\r\n"}, {"assistant": "I just realized in the discussion name it says Placement Density, but in your image we see Routing Congestion. "}]} +{"messages": [{"user": "I have a foreign PDK which I want to invoke in openroad. But for that I need to develop the setRC.tcl file. How do I accurately input the resistance and capacitance for the setRC.tcl file . \r\n\r\nN.B : I have a captable for the pdk\r\nI can also generate a spef file from Innovus for the PDK"}, {"assistant": "@vvbandeira @luarss do we have any documentation for correlateRC ?\r\n\r\nNote that if you LEF res & cap has values you can use those without a setRC to get started."}, {"assistant": "@faisaladilquadery \r\nWe have a section on the `setRC.tcl` file configuration in our platform bring-up documentation.\r\nhttps://openroad-flow-scripts.readthedocs.io/en/latest/contrib/PlatformBringUp.html#setrc-configuration"}, {"user": "Thankyou! @maliberty @vvbandeira . I have used the lef file in replacement of the setRC.tcl file . But I am getting **net delay** mismatch between the same path with the same cells for Innovus and OpenRoad. Any Idea why ?"}, {"user": "Thankyou @maliberty I have used the the RCX flow you mentioned to generate a rc tech file for my pdk and used the tech file to generate a spef in ORFS to obtain a more accurate RC."}, {"assistant": "> set_wire_rc is used to set a default layer to use when doing placement based parasitic estimation. There is no meaning to multiple layers here as there would be no way to divide up the estimate meaningfully.\r\n\r\nSo I'm confused why it needs to set jsut one layer, do you mean only placement based parasitic estimation is related to `set_wire_rc` ? If there' s no way to divide up the estimate meaningfully, the layer can be set randomly?"}]} +{"messages": [{"user": "While discussion #3856 has leaned to whether there should be a release and how frequent it should be, this discussion thread is to help guide the format and the process we would use to do such releases. We are considering using an automated way to generate \"release notes\" or at least a summary of recent changes. One proposed way to achieve this is to use PR titles and \"Merge commit\" messages. We would define and enforce a style of PR title, e.g., `[] : ` where `[FEAT] drt: added shiny router cmd`. While `` is well defined (i.e., any module under `src/third-party` and `` will depend on the PR, what would be the most relevant values `` to include and their definition? As a starter point:\r\n\r\n- `[FEAT]` or `[NEW]`: for when we add new features, either in the form of Tcl/Python API changes -- e.g., new commands or flags.\r\n- `[DOCS]` or `[DOC]`: for documentation only changes.\r\n- `[BUGF]` or `[FIX]`: when fixing bugs or issues.\r\n- `[UPGR]` or `[ENH]`: upgrade/enhance -- not very sure about this, but it was what I thought with 4/3 letters to keep similar to above, mostly a self-imposed restriction, open to feedback.\r\n\r\n\r\ncc/ @maliberty @dralabeing @luarss @rovinski @QuantamHD "}, {"assistant": "I don't think of it as \"summary of recent changes\" as we still don't plan to do releases. is also optional as some changes may span multiple tools though that should be less common."}, {"assistant": "I like the spirit, but I can foresee a few issues:\r\n\r\n1. A PR might span multiple tools, in which case it's hard to accommodate the format\r\n2. A PR might implement a feature only partially, in which case it's not ready for full use yet\r\n3. A PR might span multiple types (e.g. both feature and enhancement).\r\n4. If we want this scheme to stick, we will likely need a bot to enforce it or at least remind PR authors\r\n\r\nAs such,\r\n\r\n* I think that enhancement and feature should probably just be one tag. I think PRs end up being both too often to distinguish\r\n* We need some sort of mechanism or identifying a feature as not ready for general use yet."}]} +{"messages": [{"user": "in src/frBaseTypes.h , there is a enum class called frBlockObjectEnum, and it has lots of types. I want to know the prefix meanings. Such as `frc`,`drc`,`tac`,`gcc`"}, {"assistant": "The c is for constant. fr = base types, dr = detailed router, ta = track assignment, gc = drc (these correspond to the subdirs of src/).\r\n"}, {"user": "Thank you very much"}]} +{"messages": [{"user": "What is the horizontal axis?\r\n\r\nI would have thought picoseconds, but the horizontal axis is not labeled...\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/9b5c6daa-25f6-42b7-adf4-e11c30bf3234)\r\n\r\nThis is from `make gui_place` in #3910"}, {"user": "Also, when I click on \"Endpoint slack\" upper left corner, it looks like there should have been more than one choice?\r\n\r\nhttps://drive.google.com/file/d/1xCo_SBrhFjxZfQ-IOakjJyKaGkyZcZIP/view?usp=sharing"}, {"assistant": "It looks like \r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/202fee93-b91e-4c1c-a8da-65d0e27a213c)\r\n is in the wrong place @AcKoucher any idea why?"}]} +{"messages": [{"user": "I would like to compile statically the openroad. \r\nIs there any way to do this?\r\n\r\nThank you."}, {"user": "I will try [this](https://github.com/The-OpenROAD-Project/OpenROAD/discussions/1951).\r\nIf it doesn't work, I will re-post this question again.\r\n\r\nThanks."}]} +{"messages": [{"user": "The [mock-alu](https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/tree/master/flow/designs/src/mock-alu) allows studying the speed and area of various typical ALU operations.\r\n\r\nThe mock-alu has two 64 bit inputs and one 64 bit output. The inputs and outputs are registered within the mock-alu. This is to have clear boundary conditions when studying the guts of the mock-alu.\r\n\r\nThe mock-alu implements a number of operations and variants of these operations to study the area and minimum clock period for these operations.\r\n\r\nThe operations fall into a couple of categories:\r\n\r\n- *add, subtract and compare*: ADD, SUB, SETCC_EQ(equal), SETCC_NE (not equal), SETCC_LT (less than), SETT_LE (less than or equal), SETCC_ULT (unsigned less than), SETCC_ULE(unsigned less than or equal)\r\n- *barrel shifter*: SHR(logical shift right), SRA(arithmetic shift right), SHL(shift left)\r\n- *bitwise logic*: OR(bitwise or), AND(bitwise and), XOR(bitwise xor)\r\n- *multiplication*: 64 bit multiply. There are various algorithms used, default Han Carlson. The implementation is PDK specific and comes from https://github.com/antonblanchard/vlsiffra/\r\n- *multiplexor*: MUX1..8. This is not really an ALU operation. All that is happening here is that bits from the input as selected using a mux and put into the output. This allows studying the performance of the mux that sits before the output of an ALU, which is selecting between the various supported operations.\r\n\r\nNext, the mock-alu allows implementing any combination of these operations. This allows implementing an ALU that only supports the shift operations, which can be labelled \"SHR,SHL,SRA\". This shift operation only mock-alu has a single shared barrelshifter. Similarly, a bitwise logic only mock-alu, can be labelled \"OR,AND,XOR\".\r\n\r\nAt this point, we can plot various mock-alu implementations for ASAP7 and sky130hd:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/b9234684-43f4-4a74-98dd-81cf8b74f9ce)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/fefae238-58ed-4bfe-a307-780046acdb83)\r\n\r\nHere 8,16,32 and 64 wide ADD operations are plotted:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/f4a837e6-700c-4436-81ac-221bdfafdb57)\r\n\r\nVarious multiplication algorithms for 64 bit multiplication, 4 pipeline stages:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/0a8d6518-5999-4d18-87fa-38a13857764f)\r\n\r\nPlotting Han Carlson multiply algorithm with 8, 16, 32 and 64 bit bit width:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/97fb01d7-e535-4578-9fe9-cdb80a4e945f)\r\n\r\nThoughts?"}, {"assistant": "Its interesting that the various multiply algorithms have the same delay (excluding ripple).\r\n\r\nI don't see a MULT for sky130"}, {"user": "Here are the `vlsi-adder` algorith, excluding ripple that was ca. 2000+ ps. It would have made the graph harder to read:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/07c8e764-81d1-48fe-858a-39175a1d3c68)\r\n"}, {"assistant": "Do all your runs end in negative slack at the end of the cts & the complete flow? Once we reach zero slack we stop optimizing."}, {"assistant": "One thing worth noting is that asap7 doesn't have a full or half adder cells in the library (sky130 does)."}, {"assistant": "BTW Have you seen Teo's spreadsheet @ https://docs.google.com/spreadsheets/d/1pTGzZo5XYU7iuUryxorfzJwNuE9rM3le5t44wmLohy4/edit#gid=126548956 ?"}, {"assistant": "BTW I would love to get a similar spreadsheet to Teo's for GF180MCU and ASAP7 too. \r\n\r\nSadly, Teo got distracted by the mathematical theory and then was stolen by NVIDIA before he could get to that."}, {"assistant": "@oharboe did you try using set_clock_uncertainty to force the slack to be negative and make the tool work harder.\r\nAs @maliberty mentioned optimization will stop once timing passes. "}, {"assistant": "@oharboe - Any chance you could do a write up of what you discovered?"}, {"user": "> There is a lot bunch of back and forth and I'm unclear what the final results are (and exactly how you produced them).\r\n> \r\n> Various questions include;\r\n> \r\n> * How do I reproduce your results and graphs?\r\n\r\nRun this script: https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/master/flow/designs/src/mock-alu/plot-area-min-clock-period.py\r\n\r\nSome tinkering required.\r\n\r\n> * What settings did you end up using and why did you end up using those settings? (Particularly around making the tool work harder?)\r\n\r\nI didn't study how to make a best possible ALU, I was only interested the relationship between the ALU operations.\r\n\r\n> * How do the various implementations compare? Do you understand why the compare this way?\r\n\r\nThe various implementation of additions and multiplications?\r\n\r\nIt is a mystery why there is essentially no difference between multiplication implementation clock periods...\r\n\r\n> * How do SKY130 and ASAP7 compare in the end here?\r\n\r\nThe lessons learned on the relative size and speed of ALU operations appear to be much the same with SKY130 and ASAP7. Which is surprising. Ca. 15 years separate them...\r\n\r\n> * Do the relative \"positions\" between the implementations hold across SKY130 and ASAP7?\r\n\r\nPretty much.\r\n\r\n> * What was the most interesting / unexpected thing you discovered?\r\n\r\nThat relative size and speed of simple ALU operations are essentially unchanged across process nodes.\r\n\r\nAlso, it would appear that if an ALU operation is 200ps on x86 7nm, yielding 5GHz, then one could choose to divide clock period of ASAP7+OpenROAD by 4 for simple ALU operations when one models and decide to take the lessons learned and apply them to architectural exploration. Further choose to treat the speed of ASAP7+OpenROAD as not terribly important in terms of making architctural choices as the choices will be the same if everything is optimized.\r\n\r\nBy this I mean that to drive your architctural exploration, as a [first order approximation](https://en.wikipedia.org/wiki/Order_of_approximation#First-order), write the RTL in an idiomatic way, run them through ASAP7+OpenROAD and if your design is 4x the desired clock period, your design isn't completely off.\r\n\r\nNobody who have information on commercial tools and PDKs can challenge me here. :-) Not because I'm right, but because PDKs and commercial tools are under strict NDAs... This also explains why there are a lot of unsaid things in this thread...\r\n\r\n> Writing it up as a nice coherent blog post would be pretty awesome but totally understand if you do nt have the time to do so.\r\n\r\nAgreed. At least I summarize a bit here. I'm happy to hear that there are some that are interested in this.\r\n\r\nPerhaps you would like to write a blog-post using the script above?\r\n"}]} +{"messages": [{"user": "Silly question: where do I find the source code for `findInst`?\r\n\r\nI seem unable to find it in the OpenROAD source code.\r\n\r\n```\r\n set inst [$block findInst [format \"ces_%d_%d\" $row $col]]\r\n```\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/f90d853b3705338fa2d142acd20ac57626c71f12/flow/designs/asap7/mock-array/macro-placement.tcl#L10\r\n\r\n"}, {"assistant": "Header: https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/odb/include/odb/db.h#L992\r\nImpl: https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/odb/src/db/dbBlock.cpp#L1790\r\nHidden Impl: https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/odb/src/db/dbBlock.h#L173"}, {"user": "So `findInst` doesn't throw an exception if the element doesn't exist, like https://cplusplus.com/reference/map/map/at/ does.\r\n\r\nThis leads to a lot of repetition and context unique error messages and in tcl very poor error messages like:\r\n\r\n```\r\nError: macro-placement.tcl, 27 invalid command name \"NULL\"\r\n```\r\n\r\n`std::map` has explicit accessors that either creates an element if it doesn't exist(returns empty by default) and another that throws an exception if it doesn't exist.\r\n\r\nThe equivalent here would be that findInst() threw an exception with an error message and the name, and that another hasInst() that doesn't and allows the user to handle it. try/catch is not approperiate because both findInst() that throws exception and hasInst() that checks for presence would both be part of normal exception."}, {"assistant": "The odb code is old and was written without the use of exceptions. I would be fine to change that but it will require testing the full app to see if problems arise and resolving them. There are a number of similar APIs that return nullptr on failure."}, {"user": "I see. I was just curious and surprised: there are LOT of methods in that .h file that are exposed in .tcl.\r\n\r\nNot all of them are obviously compatible with a .tcl calling convention or even intended for .tcl?"}]} +{"messages": [{"user": "Hello,\r\n\r\nI see there is a lot of development going on. I am wondering whether there are any opinions/plans about introducing a release scheme (e.g. once a month or quarterly, or after major feature changes / enhancements) ? Maintaining something like `CHANGES.md` or `NEWS.md` would be also very handy. Once user does not follow the development almost day-to-day, it is easy to get lost.\r\n\r\n"}, {"assistant": "I would be in favor of a news/changes file, but I'm a little bit more hesitant on slow releases. \r\n\r\nPrecision Innovations provides a daily release https://github.com/Precision-Innovations/OpenROAD/releases which I feel like is a good cadence given the fast pace of developement.\r\n\r\nI think slower stable releases make sense when you have an entity that's willing to cherry pick bug fixes into older releases, which we don't have yet. I feel like if we embraced a slower release process at this point in time the net result would be people stuck with bugs for longer.\r\n\r\n"}, {"assistant": "A monthly newsletter might be a good way to let people see the improvements."}, {"assistant": "Daily releases are good to get the best , updated and stable versions especially with prebuilt binaries from the Precision releases. I do think it would be good to add some sort of updates that are not yet in the docs or clear in the commit histories. For e.g mpl2 works well but this is not yet reflected in the default flow or docs but can be flagged in an Updates.md for users to try out --somewhat like a beta version. Similar any new features that are ready for use (partitioning, pin swapping, gate cloning etc.) can be mentioned along with a special release tag .\r\nMonthly update frequency should be good as in special cases when an update is done sooner on a major feature."}, {"assistant": "I really like the [KLayout release notes](https://www.klayout.de/development.html) which have a list of PRs in that release (with hyperlinks) and a one-line description, as well as classifying as a bugfix or enhancement. It doesn't sound like we're moving from daily releases, but it could form a semi-automatically generated monthly newsletter or similar."}]} +{"messages": [{"user": "We wonder whether TritonRoute support all design rules in ISPD 2014/2015 tech files (https://www.ispd.cc/contests/14/web/benchmarks.html)? Example design rules are as follows:\r\n\r\n1. PROPERTY LEF57_MINSTEP \"MINSTEP 0.100 MAXEDGES 1 ;\" ;\r\n2. MINIMUMCUT 2 WIDTH 0.400 ;\r\n3. MINENCLOSEDAREA 0.30 ;\r\n4. PROPERTY LEF57_SPACING \"SPACING 0.13 PARALLELOVERLAP ;\u201d;\r\n"}, {"assistant": "We test with ispd 18&19 but not those. 2 is only relevant for pdn and I know we support 3. @osamahammad21 would you check on 1 & 4"}, {"assistant": "We currently parse for LEF58 rules. We don't parse LEF57 (by looking at /src/odb/src/lefin/lefin.cpp and /src/drt/src/io/io.cpp).\r\nI will start a PR for parsing LEF57.\r\n\r\nAlso, we don't support PARALLELOVERLAP option for LEF58_SPACING in drt according to io.cpp:\r\n\r\n```\r\ncase odb::dbTechLayerCutSpacingRule::CutSpacingType::PARALLELOVERLAP:\r\n logger_->warn(utl::DRT,\r\n 260,\r\n \"Unsupported LEF58_SPACING rule for layer {} of type \"\r\n \"PARALLELOVERLAP.\",\r\n layer->getName());\r\n break;\r\n```\r\n\r\nWe support MAXEDGES for LEF58_MINSTEP as in io.cpp:\r\n\r\n```\r\nfor (auto rule : layer->getTechLayerMinStepRules()) {\r\n auto con = make_unique();\r\n con->setMinStepLength(rule->getMinStepLength());\r\n con->setMaxEdges(rule->isMaxEdgesValid() ? rule->getMaxEdges() : -1);\r\n con->setMinAdjacentLength(\r\n rule->isMinAdjLength1Valid() ? rule->getMinAdjLength1() : -1);\r\n con->setEolWidth(rule->isNoBetweenEol() ? rule->getEolWidth() : -1);\r\n tmpLayer->addLef58MinStepConstraint(con.get());\r\n tech_->addUConstraint(std::move(con));\r\n }\r\n```"}, {"assistant": "We could add support for new rules if there is strong interest"}, {"assistant": "Hi @liangrj2014 , we added support for PROPERTY LEF57_MINSTEP & PROPERTY LEF57_SPACING.\r\nAlso, support for PARALLELOVERLAP will be added soon."}, {"assistant": "@liangrj2014 PARALLELOVERLAP is now supported for LEF57_SPACING &LEF58_SPACING properties."}]} +{"messages": [{"user": "I made a fleeting vain attempt at adding multithreaded rendering and discovered that, near as I can see, it isn't any faster or slower. Perhaps searching for rectangles dominates?\r\n\r\nAny thoughts? Anyone else who wants to have a go? :-)\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/pull/3813\r\n\r\nMy theory, which didn't seem to hold up, was:\r\n\r\nKISS multithreaded rendering: one subrectangle per thread.\r\n\r\nThis means that a search for objects to draw into each subrectangle is done once per thread, so that might be more wasteful than searching for rectangles once and then rendering one layer per thread.\r\n\r\nHowever, in terms of the rendering time this might not matter, because no rendering starts until the search for objects to draw within a rectangle as completed."}, {"assistant": "I started looking at multithreading with one layer per thread. I can only work on this on weekends though, so I won't have a PR ready until the last week of August or first week of September if you can wait that long."}]} +{"messages": [{"user": "\r\n\r\nHello. I want to use how to save the JEPG files during debugging `GPL`.\r\n\r\n[In this code](https://github.com/ApeachM/OpenROAD/blob/c6bd7c29293fd47a23212384267517b213f77293/src/gpl/src/nesterovPlace.cpp#L427C8-L438), there seems to exist the method to make some images during `GPL`. \r\n\r\n```tcl\r\nread_lef ispd18/ispd18_test1/ispd18_test1.input.lef\r\nread_def ispd18/ispd18_test1/ispd18_test1.input.def\r\ngpl::global_placement_debug\r\nglobal_placement -skip_initial_place\r\n```\r\n\r\nI did `gpl::global_placement_debug` before calling `global_placement`. \r\n\r\nI can see the snapshots during `GPL` in `GUI`, but I don't know how to save them automatically for each pause step. How do I do it?\r\n\r\n\r\n\r\nAlso, I want to color for a specific cell, editing c++ code in `gpl` for my debugging. Is this possible?\r\n\r\n"}, {"user": "I solved it with `gui::Gui::get()->saveImage(file_name);`. Thank you."}]} +{"messages": [{"user": "It would make moving around the design a lot easier.\r\n\r\nIs there a way to do this already?\r\n\r\nThe arrow keys is a bit clunky compared to dragging the view with the mouse."}, {"assistant": "OpenRoad will hopefully take hint's from KLayout's layout view controls instead of inventing yet another scheme.\r\n\r\nzoom in/out at the cursor position (mouse wheel zoom in/out)\r\nmake the cursor key \"shift width\" adjustable (40% seem like a better value then the defaults)\r\nhave \"gestures\" for fit, zoom in, zoom out (move mouse right-up, down, left-up), so no \"mouse drag viewpoint\".\r\n\r\nThere doesn't seem to be a consensus for zoom in/out, fit, level down/up keys.\r\nI override the klayout defaults and use z/Z, f, l/L, curious what other people use."}, {"assistant": "I stand corrected, there is dragging the view in Klayout, on a Mac is \"right mouse + shift\""}, {"assistant": "There is no method currently. It could be an enhancement request as could gestures."}, {"user": "Added feature request https://github.com/The-OpenROAD-Project/OpenROAD/issues/3840"}]} +{"messages": [{"user": "Is this amount of slew expected on the clock pin to the SRAM? \r\n\r\n`SRAM2RW16x32_2/CE2` is one of two clocks to the SRAM, the SRAM has one read and one write port.\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/sram-64x16/config.mk\r\n```\r\n\r\n```\r\n>>> report_checks -path_delay max -fields {slew net cap} -to _351_/D\r\nStartpoint: SRAM2RW16x32_2 (rising edge-triggered flip-flop clocked by io_clk)\r\nEndpoint: _351_ (falling edge-triggered flip-flop clocked by io_clk')\r\nPath Group: io_clk\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 clock io_clk (rise edge)\r\n 241.44 241.44 clock network delay (propagated)\r\n 150.83 0.00 241.44 ^ SRAM2RW16x32_2/CE2 (SRAM2RW16x32)\r\n 40.24 202.07 443.51 v SRAM2RW16x32_2/O2[4] (SRAM2RW16x32)\r\n 1 9.73 _SRAM2RW16x32_2_O2[4] (net)\r\n 53.97 5.14 448.65 v _351_/D (DFFLQNx1_ASAP7_75t_R)\r\n 448.65 data arrival time\r\n\r\n 500.00 500.00 clock io_clk' (fall edge)\r\n 186.47 686.47 clock network delay (propagated)\r\n 0.52 686.99 clock reconvergence pessimism\r\n 686.99 v _351_/CLK (DFFLQNx1_ASAP7_75t_R)\r\n -22.88 664.11 library setup time\r\n 664.11 data required time\r\n-----------------------------------------------------------------------------\r\n 664.11 data required time\r\n -448.65 data arrival time\r\n-----------------------------------------------------------------------------\r\n 215.46 slack (MET)\r\n```\r\n"}, {"assistant": "Probably not but without a test case not much more can be said."}, {"user": "`make DESIGN_CONFIG=designs/asap7/sram-64x16/config.mk issue_cts` standalone testcase:\r\n\r\n1. Unzip (note! bzip2 compression so that it would fit into github limit) [slew.zip](https://github.com/The-OpenROAD-Project/OpenROAD/files/12294012/slew.zip)\r\n2. run `./run*.sh`\r\n3. Enter `report_checks -path_delay max -fields {slew net cap} -to _351_/D` in the GUI\r\n\r\nYou should get:\r\n\r\n\r\n```\r\n>>> report_checks -path_delay max -fields {slew net cap} -to _351_/D\r\nStartpoint: SRAM2RW16x32_2 (rising edge-triggered flip-flop clocked by io_clk)\r\nEndpoint: _351_ (falling edge-triggered flip-flop clocked by io_clk')\r\nPath Group: io_clk\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 clock io_clk (rise edge)\r\n 274.66 274.66 clock network delay (propagated)\r\n 186.64 0.00 274.66 ^ SRAM2RW16x32_2/CE2 (SRAM2RW16x32)\r\n 35.53 205.56 480.22 v SRAM2RW16x32_2/O2[4] (SRAM2RW16x32)\r\n 1 7.54 _SRAM2RW16x32_2_O2[4] (net)\r\n 47.76 5.26 485.49 v _351_/D (DFFLQNx1_ASAP7_75t_R)\r\n 485.49 data arrival time\r\n\r\n 500.00 500.00 clock io_clk' (fall edge)\r\n 212.33 712.33 clock network delay (propagated)\r\n 0.00 712.33 clock reconvergence pessimism\r\n 712.33 v _351_/CLK (DFFLQNx1_ASAP7_75t_R)\r\n -21.20 691.13 library setup time\r\n 691.13 data required time\r\n-----------------------------------------------------------------------------\r\n 691.13 data required time\r\n -485.49 data arrival time\r\n-----------------------------------------------------------------------------\r\n 205.64 slack (MET)\r\n\r\n```\r\n\r\n"}, {"assistant": "Converted to an issue https://github.com/The-OpenROAD-Project/OpenROAD/issues/3817"}]} +{"messages": [{"user": "Using https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1322(soon to be merged, but the same issue exists in master), I looked at a path going through Element (no registers, just a signal going from left to right through the Element):\r\n\r\nThere are three buffers in this path: input, a middle buffer inserted by synthesis, and an output buffer. The input and output buffers are introduced by OpenROAD. What motivates synthesis to introduce this middle buffer? Isn't that the job of resizing?\r\n\r\nFrom 1_synth.v we see the middle buffer:\r\n\r\n```\r\n BUFx2_ASAP7_75t_R _776_ (\r\n .A(io_lsbIns_5),\r\n .Y(io_lsbOuts_4)\r\n );\r\n```\r\n\r\nThe buffer is inserted by this code: \r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/4a6fdcebf8361481090acde05d596e8db946c806/flow/scripts/synth.tcl#L96\r\n\r\n```\r\n>>> report_checks -path_delay max -to io_lsbOuts_4 -fields {slew net cap}\r\nStartpoint: io_lsbIns_5 (input port)\r\nEndpoint: io_lsbOuts_4 (output port)\r\nPath Group: path delay\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 v input external delay\r\n 6.80 0.80 0.80 v io_lsbIns_5 (in)\r\n 1 0.83 io_lsbIns_5 (net)\r\n 4.97 12.72 13.52 v input261/Y (BUFx2_ASAP7_75t_R)\r\n 1 0.79 net261 (net)\r\n 13.54 15.20 28.72 v _776_/Y (BUFx3_ASAP7_75t_R)\r\n 1 5.63 net268 (net)\r\n 17.44 23.37 52.09 v output268/Y (BUFx4f_ASAP7_75t_R)\r\n 1 10.23 io_lsbOuts_4 (net)\r\n 17.59 0.91 53.00 v io_lsbOuts_4 (out)\r\n 53.00 data arrival time\r\n\r\n 29.60 29.60 max_delay\r\n 0.00 29.60 output external delay\r\n 29.60 data required time\r\n-----------------------------------------------------------------------------\r\n 29.60 data required time\r\n -53.00 data arrival time\r\n-----------------------------------------------------------------------------\r\n -23.40 slack (VIOLATED)\r\n\r\n```\r\n\r\nOverview:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/bd71b9bc-4f8e-4b36-a922-825c52c25fbd)\r\n\r\nThe two nearly back-to-back buffers on the output:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c5eb763c-10c1-4be0-8b8d-1279242608c7)\r\n\r\n\r\nMoreover: there are two buffers(synthesis introduced buffer + output buffer) nearly back to back at the output. The Element is routed by abutment horizontall, so we get a third input buffer immediately from the Element to the right.\r\n\r\n\r\nIf I disable https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/4a6fdcebf8361481090acde05d596e8db946c806/flow/scripts/synth.tcl#L96, I get no buffers, which was unexpected as OpenROAD, not synthesis inserts input and output buffers...\r\n\r\n```\r\n>>> report_checks -path_delay max -to io_lsbOuts_4 -fields {slew net cap}\r\nStartpoint: io_lsbIns_5 (input port)\r\nEndpoint: io_lsbOuts_4 (output port)\r\nPath Group: path delay\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 ^ input external delay\r\n 31.60 16.96 16.96 ^ io_lsbIns_5 (in)\r\n 1 15.09 io_lsbIns_5 (net)\r\n 42.77 0.00 16.96 ^ io_lsbOuts_4 (out)\r\n 16.96 data arrival time\r\n\r\n 29.60 29.60 max_delay\r\n 0.00 29.60 output external delay\r\n 29.60 data required time\r\n-----------------------------------------------------------------------------\r\n 29.60 data required time\r\n -16.96 data arrival time\r\n-----------------------------------------------------------------------------\r\n 12.64 slack (MET)\r\n```\r\n\r\nAt the mock-array level, I see something unexpected, 0 delay for the in-out paths:\r\n\r\n```\r\n>>> report_checks -path_delay max -through ces_7_1/io_lsbIns_* -fields {net cap slew}\r\nStartpoint: ces_7_0 (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: ces_7_4 (rising edge-triggered flip-flop clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 287.91 287.91 clock network delay (propagated)\r\n 83.67 0.00 287.91 ^ ces_7_0/clock (Element)\r\n 3.44 164.65 452.56 v ces_7_0/io_lsbOuts_7 (Element)\r\n 1 0.00 ces_7_0_io_lsbOuts_7 (net)\r\n 5.80 0.00 452.56 v ces_7_1/io_lsbOuts_6 (Element)\r\n 1 0.00 ces_7_1_io_lsbOuts_6 (net)\r\n 5.80 0.00 452.56 v ces_7_2/io_lsbOuts_5 (Element)\r\n 1 0.00 ces_7_2_io_lsbOuts_5 (net)\r\n 5.80 0.00 452.56 v ces_7_3/io_lsbOuts_4 (Element)\r\n 1 0.69 ces_7_3_io_lsbOuts_4 (net)\r\n 5.80 0.00 452.56 v ces_7_4/io_lsbIns_4 (Element)\r\n 452.56 data arrival time\r\n\r\n 300.00 300.00 clock clock (rise edge)\r\n 238.74 538.74 clock network delay (propagated)\r\n -10.00 528.74 clock uncertainty\r\n 1.40 530.14 clock reconvergence pessimism\r\n 530.14 ^ ces_7_4/clock (Element)\r\n 70.02 600.16 library setup time\r\n 600.16 data required time\r\n-----------------------------------------------------------------------------\r\n 600.16 data required time\r\n -452.56 data arrival time\r\n-----------------------------------------------------------------------------\r\n 147.59 slack (MET)\r\n```\r\n\r\n\r\n"}, {"assistant": "The third buffer buffer looks to have been from yosys. I imagine the incoming netlist was a single buffer (_776_). The other two come from buffer_ports. You could skip that if you want a single buffer."}, {"user": "> The third buffer buffer looks to have been from yosys.\r\n\r\nYep.\r\n\r\n> I imagine the incoming netlist was a single buffer (_776_). The other two come from buffer_ports. You could skip that if you want a single buffer.\r\n\r\nSurprisingly, the input output buffers go away if I disable yosys buffer insertions. Any thoughts about why that is happening?\r\n\r\nIt sounds like you only expected input/output buffers in this case...\r\n\r\nHow can I disable output/input buffers for only in-out paths and is it a good idea in this case?\r\n\r\nAlso, I didn't expect zero propagation time when there are no buffers, is that expected?\r\n\r\n\r\n\r\n\r\n\r\n"}, {"user": "@maliberty One last question, why is this line in synth.tcl? I understand what it does, I just don't know why it is there.\r\n\r\n```\r\ninsbuf -buf {*}$::env(MIN_BUF_CELL_AND_PORTS)\r\n```"}]} +{"messages": [{"user": "What if CTS as a default made a moderate effort to repair hold violations with an option to try harder and then continued on to detailed routing?\r\n\r\nThis would would give the user a result to examine that has hold violations. The user can debug the problem looking at setup and hold timing in the GUI and via OpenSTA commands.\r\n\r\nMy experience is that if hold violations aren't easily fixed(small), then there is a fundamental underlying problem that has to be fixed.\r\n\r\nDebugging global route problems is much tougher and more time consuming than looking up some hold violations in the GUI.\r\n\r\nThoughts?"}, {"assistant": "You can always stop the flow after cts if you want. I'm not sure what is proposed here. You can't go from cts to detailed routing without going through global routing."}]} +{"messages": [{"user": "There must a great number of papers written about CTS, but I found this an interesting series of slides about CTS and easy to read for someone who has only recently learned about CTS: https://www.eng.biu.ac.il/temanad/files/2017/02/Lecture-8-CTS.pdf\r\n\r\nThis made me think about what is it exactly that the CTS should target and how should it target it?\r\n\r\nFirst time I heard about CTS, I thought that zero skew and zero latency was a good optimization target. Of course that can never be realized, it is just an optimization target.\r\n\r\nI just recently tested out some visualization of the clock tree #3788, but this visualization only shows the clock network delay(not accounting for macros, only flip flops). That doesn't tell me anything about how far the clock tree is from the optimization target.\r\n\r\nIf I have very little network latency near the input/output pins and I have timing closure, is there any reason to care about skew and clock network latency in the rest of the design?\r\n\r\nIf that condition is satisfied, isn't the next things to optimize for other things like power, area and signal integrity?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/90e08a5b-ddf6-4ec0-95f8-366ac3be7ebe)\r\n"}, {"user": "No takers :-)"}]} +{"messages": [{"user": "The tooltips in the Clock Tree Viewer contain interesting information: which macro or flip flop has how much clock network latency.\r\n\r\nHowever, the tooltip information is hard to get to and it is not searchable.\r\n\r\nI mocked a text report that is printed when I click update...\r\n\r\nI think perhaps a better approach to this is to have a tcl utility procedure that navigates the clock tree and print out this information. Perhaps that is possible today, but I don't know how to...\r\n\r\nChange I used to mock the report below: https://github.com/Pinata-Consulting/OpenROAD/commit/17283788372d98cafc1e6bbd056f1074a1539bc6\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/1a874efa-2b66-41f2-b365-7990f3ed5399)\r\n"}, {"user": "Mocking a heatmap of arrival times. I only have location information for the Elements. Got the idea here. https://www.eng.biu.ac.il/temanad/files/2017/02/Lecture-8-CTS.pdf\r\n\r\n```\r\nimport re\r\nimport matplotlib.pyplot as plt\r\nimport numpy as np\r\n\r\n# Extracting data from the text\r\ntext = \"\"\"\r\n# Your log content goes here\r\n\"\"\"\r\n\r\nlines = text.strip().split('\\n')\r\nfiltered_lines = [line for line in lines if \"ces\" in line]\r\n\r\n# Finding the maximum indices for rows and columns\r\nmax_row = max_col = 0\r\ndata_dict = {}\r\nfor line in filtered_lines:\r\n match = re.search(r\"ces_(\\d+)_(\\d+)/clock\\s*Arrival:\\s*(\\d+\\.\\d+)\", line)\r\n if match:\r\n row, col, value = map(int, map(float, match.groups()))\r\n max_row = max(max_row, row)\r\n max_col = max(max_col, col)\r\n data_dict[(row, col)] = value\r\n\r\n# Constructing the data matrix\r\ndata_matrix = np.zeros((max_row + 1, max_col + 1))\r\nfor (row, col), value in data_dict.items():\r\n data_matrix[row, col] = value\r\n\r\n# Plotting the heatmap\r\nplt.imshow(data_matrix, origin='upper', cmap='viridis', aspect='auto')\r\nplt.colorbar(label='Arrival (ps)')\r\nplt.title('Heatmap of Arrival Times')\r\nplt.xlabel('Column')\r\nplt.ylabel('Row')\r\nplt.show()\r\n```\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/aceb47d0-d673-461d-a0f0-e0b3df96a8d6)\r\n"}, {"user": "Adding some 3d bling...\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/ad5b4839-f77e-4643-89d8-4426b4137f89)\r\n\r\n\r\n```\r\n# Sample data\r\ntext = \"\"\"\r\n[INFO GUI-0088] Register _131_/CLK Arrival: 258.115 ps\r\n[INFO GUI-0088] Register _132_/CLK Arrival: 257.882 ps\r\n[INFO GUI-0088] Register _133_/CLK Arrival: 258.944 ps\r\n[INFO GUI-0088] Register _134_/CLK Arrival: 258.636 ps\r\n[INFO GUI-0088] Register _135_/CLK Arrival: 258.069 ps\r\n[INFO GUI-0088] Register _137_/CLK Arrival: 257.527 ps\r\n[INFO GUI-0088] Register _139_/CLK Arrival: 246.072 ps\r\n[INFO GUI-0088] Register _143_/CLK Arrival: 245.541 ps\r\n[INFO GUI-0088] Register _145_/CLK Arrival: 245.360 ps\r\n[INFO GUI-0088] Register ces_0_7/clock Arrival: 232.150 ps\r\n[INFO GUI-0088] Register ces_1_7/clock Arrival: 225.713 ps\r\n[INFO GUI-0088] Register _136_/CLK Arrival: 250.476 ps\r\n[INFO GUI-0088] Register _138_/CLK Arrival: 250.337 ps\r\n[INFO GUI-0088] Register _140_/CLK Arrival: 246.845 ps\r\n[INFO GUI-0088] Register _141_/CLK Arrival: 246.075 ps\r\n[INFO GUI-0088] Register _142_/CLK Arrival: 246.461 ps\r\n[INFO GUI-0088] Register _144_/CLK Arrival: 246.885 ps\r\n[INFO GUI-0088] Register _146_/CLK Arrival: 245.560 ps\r\n[INFO GUI-0088] Register ces_0_6/clock Arrival: 235.587 ps\r\n[INFO GUI-0088] Register _147_/CLK Arrival: 239.633 ps\r\n[INFO GUI-0088] Register _148_/CLK Arrival: 238.903 ps\r\n[INFO GUI-0088] Register _149_/CLK Arrival: 239.580 ps\r\n[INFO GUI-0088] Register _150_/CLK Arrival: 238.791 ps\r\n[INFO GUI-0088] Register _151_/CLK Arrival: 239.418 ps\r\n[INFO GUI-0088] Register _152_/CLK Arrival: 239.304 ps\r\n[INFO GUI-0088] Register _153_/CLK Arrival: 238.755 ps\r\n[INFO GUI-0088] Register _154_/CLK Arrival: 238.495 ps\r\n[INFO GUI-0088] Register _155_/CLK Arrival: 250.283 ps\r\n[INFO GUI-0088] Register _156_/CLK Arrival: 250.061 ps\r\n[INFO GUI-0088] Register _157_/CLK Arrival: 250.546 ps\r\n[INFO GUI-0088] Register _158_/CLK Arrival: 250.032 ps\r\n[INFO GUI-0088] Register _159_/CLK Arrival: 250.760 ps\r\n[INFO GUI-0088] Register _160_/CLK Arrival: 249.826 ps\r\n[INFO GUI-0088] Register _161_/CLK Arrival: 250.433 ps\r\n[INFO GUI-0088] Register _162_/CLK Arrival: 249.956 ps\r\n[INFO GUI-0088] Register ces_2_7/clock Arrival: 233.829 ps\r\n[INFO GUI-0088] Register ces_3_6/clock Arrival: 243.645 ps\r\n[INFO GUI-0088] Register ces_3_7/clock Arrival: 239.027 ps\r\n[INFO GUI-0088] Register ces_0_0/clock Arrival: 290.815 ps\r\n[INFO GUI-0088] Register ces_0_1/clock Arrival: 287.224 ps\r\n[INFO GUI-0088] Register ces_0_2/clock Arrival: 276.359 ps\r\n[INFO GUI-0088] Register ces_1_0/clock Arrival: 262.155 ps\r\n[INFO GUI-0088] Register ces_1_1/clock Arrival: 258.349 ps\r\n[INFO GUI-0088] Register ces_1_2/clock Arrival: 248.148 ps\r\n[INFO GUI-0088] Register ces_0_3/clock Arrival: 226.049 ps\r\n[INFO GUI-0088] Register ces_1_3/clock Arrival: 224.760 ps\r\n[INFO GUI-0088] Register ces_0_4/clock Arrival: 242.883 ps\r\n[INFO GUI-0088] Register ces_0_5/clock Arrival: 247.124 ps\r\n[INFO GUI-0088] Register ces_1_4/clock Arrival: 237.497 ps\r\n[INFO GUI-0088] Register ces_1_5/clock Arrival: 249.241 ps\r\n[INFO GUI-0088] Register ces_1_6/clock Arrival: 253.384 ps\r\n[INFO GUI-0088] Register ces_2_0/clock Arrival: 253.191 ps\r\n[INFO GUI-0088] Register ces_2_1/clock Arrival: 248.850 ps\r\n[INFO GUI-0088] Register ces_2_2/clock Arrival: 236.498 ps\r\n[INFO GUI-0088] Register ces_3_0/clock Arrival: 261.042 ps\r\n[INFO GUI-0088] Register ces_3_1/clock Arrival: 257.075 ps\r\n[INFO GUI-0088] Register ces_3_2/clock Arrival: 244.640 ps\r\n[INFO GUI-0088] Register ces_2_3/clock Arrival: 225.582 ps\r\n[INFO GUI-0088] Register ces_2_4/clock Arrival: 239.450 ps\r\n[INFO GUI-0088] Register ces_2_5/clock Arrival: 251.290 ps\r\n[INFO GUI-0088] Register ces_2_6/clock Arrival: 255.456 ps\r\n[INFO GUI-0088] Register ces_3_3/clock Arrival: 227.135 ps\r\n[INFO GUI-0088] Register ces_3_4/clock Arrival: 243.496 ps\r\n[INFO GUI-0088] Register ces_3_5/clock Arrival: 248.000 ps\r\n[INFO GUI-0088] Register _163_/CLK Arrival: 253.020 ps\r\n[INFO GUI-0088] Register _164_/CLK Arrival: 253.796 ps\r\n[INFO GUI-0088] Register _165_/CLK Arrival: 254.691 ps\r\n[INFO GUI-0088] Register _166_/CLK Arrival: 254.356 ps\r\n[INFO GUI-0088] Register _167_/CLK Arrival: 254.200 ps\r\n[INFO GUI-0088] Register _168_/CLK Arrival: 253.308 ps\r\n[INFO GUI-0088] Register _169_/CLK Arrival: 252.967 ps\r\n[INFO GUI-0088] Register _170_/CLK Arrival: 253.566 ps\r\n[INFO GUI-0088] Register ces_4_6/clock Arrival: 236.291 ps\r\n[INFO GUI-0088] Register ces_4_7/clock Arrival: 232.063 ps\r\n[INFO GUI-0088] Register _171_/CLK Arrival: 231.291 ps\r\n[INFO GUI-0088] Register _172_/CLK Arrival: 231.543 ps\r\n[INFO GUI-0088] Register _173_/CLK Arrival: 231.174 ps\r\n[INFO GUI-0088] Register _174_/CLK Arrival: 230.426 ps\r\n[INFO GUI-0088] Register _175_/CLK Arrival: 231.306 ps\r\n[INFO GUI-0088] Register _176_/CLK Arrival: 231.412 ps\r\n[INFO GUI-0088] Register _177_/CLK Arrival: 231.484 ps\r\n[INFO GUI-0088] Register _178_/CLK Arrival: 231.182 ps\r\n[INFO GUI-0088] Register _179_/CLK Arrival: 244.957 ps\r\n[INFO GUI-0088] Register _180_/CLK Arrival: 242.174 ps\r\n[INFO GUI-0088] Register _181_/CLK Arrival: 244.902 ps\r\n[INFO GUI-0088] Register _182_/CLK Arrival: 242.804 ps\r\n[INFO GUI-0088] Register _183_/CLK Arrival: 244.575 ps\r\n[INFO GUI-0088] Register _184_/CLK Arrival: 243.857 ps\r\n[INFO GUI-0088] Register _185_/CLK Arrival: 242.949 ps\r\n[INFO GUI-0088] Register _186_/CLK Arrival: 244.352 ps\r\n[INFO GUI-0088] Register _187_/CLK Arrival: 253.289 ps\r\n[INFO GUI-0088] Register _189_/CLK Arrival: 253.454 ps\r\n[INFO GUI-0088] Register _193_/CLK Arrival: 253.757 ps\r\n[INFO GUI-0088] Register _194_/CLK Arrival: 253.377 ps\r\n[INFO GUI-0088] Register _188_/CLK Arrival: 249.940 ps\r\n[INFO GUI-0088] Register _190_/CLK Arrival: 250.214 ps\r\n[INFO GUI-0088] Register _191_/CLK Arrival: 250.193 ps\r\n[INFO GUI-0088] Register _192_/CLK Arrival: 250.440 ps\r\n[INFO GUI-0088] Register ces_6_6/clock Arrival: 237.794 ps\r\n[INFO GUI-0088] Register ces_6_7/clock Arrival: 237.428 ps\r\n[INFO GUI-0088] Register ces_7_6/clock Arrival: 248.387 ps\r\n[INFO GUI-0088] Register ces_7_7/clock Arrival: 243.904 ps\r\n[INFO GUI-0088] Register ces_4_0/clock Arrival: 269.870 ps\r\n[INFO GUI-0088] Register ces_4_1/clock Arrival: 265.959 ps\r\n[INFO GUI-0088] Register ces_4_2/clock Arrival: 254.121 ps\r\n[INFO GUI-0088] Register ces_4_3/clock Arrival: 227.621 ps\r\n[INFO GUI-0088] Register ces_5_0/clock Arrival: 260.539 ps\r\n[INFO GUI-0088] Register ces_5_1/clock Arrival: 256.515 ps\r\n[INFO GUI-0088] Register ces_5_2/clock Arrival: 245.174 ps\r\n[INFO GUI-0088] Register ces_5_3/clock Arrival: 225.957 ps\r\n[INFO GUI-0088] Register ces_5_4/clock Arrival: 233.418 ps\r\n[INFO GUI-0088] Register ces_5_5/clock Arrival: 250.130 ps\r\n[INFO GUI-0088] Register ces_5_6/clock Arrival: 260.323 ps\r\n[INFO GUI-0088] Register ces_5_7/clock Arrival: 263.816 ps\r\n[INFO GUI-0088] Register ces_4_4/clock Arrival: 219.267 ps\r\n[INFO GUI-0088] Register ces_4_5/clock Arrival: 223.542 ps\r\n[INFO GUI-0088] Register ces_7_0/clock Arrival: 287.112 ps\r\n[INFO GUI-0088] Register ces_7_1/clock Arrival: 283.560 ps\r\n[INFO GUI-0088] Register ces_7_2/clock Arrival: 273.081 ps\r\n[INFO GUI-0088] Register ces_7_3/clock Arrival: 272.904 ps\r\n[INFO GUI-0088] Register ces_6_0/clock Arrival: 250.403 ps\r\n[INFO GUI-0088] Register ces_6_1/clock Arrival: 246.424 ps\r\n[INFO GUI-0088] Register ces_6_2/clock Arrival: 235.488 ps\r\n[INFO GUI-0088] Register ces_6_3/clock Arrival: 230.871 ps\r\n[INFO GUI-0088] Register ces_6_4/clock Arrival: 234.553 ps\r\n[INFO GUI-0088] Register ces_6_5/clock Arrival: 238.808 ps\r\n[INFO GUI-0088] Register ces_7_4/clock Arrival: 240.051 ps\r\n[INFO GUI-0088] Register ces_7_5/clock Arrival: 244.454 ps\r\n\"\"\"\r\n\r\nimport re\r\nimport matplotlib.pyplot as plt\r\nimport numpy as np\r\n\r\nlines = text.strip().split('\\n')\r\nfiltered_lines = [line for line in lines if \"ces\" in line]\r\n\r\n# Finding the maximum indices for rows and columns\r\nmax_row = max_col = 0\r\ndata_dict = {}\r\nfor line in filtered_lines:\r\n match = re.search(r\"ces_(\\d+)_(\\d+)/clock\\s*Arrival:\\s*(\\d+\\.\\d+)\", line)\r\n if match:\r\n row, col, value = map(int, map(float, match.groups()))\r\n max_row = max(max_row, row)\r\n max_col = max(max_col, col)\r\n data_dict[(row, col)] = value\r\n\r\n# Constructing the data matrix\r\ndata_matrix = np.zeros((max_row + 1, max_col + 1))\r\nfor (row, col), value in data_dict.items():\r\n data_matrix[row, col] = value\r\n\r\n# Plotting the heatmap\r\nplt.imshow(data_matrix, origin='upper', cmap='viridis', aspect='auto')\r\nplt.colorbar(label='Arrival (ps)')\r\nplt.title('Heatmap of Arrival Times')\r\nplt.xlabel('Column')\r\nplt.ylabel('Row')\r\nplt.show()\r\n```\r\n\r\n"}, {"user": "The reason I was interested in the skew heatmap as a function of location, is that for the mock-array, it is more important to have low skew at the edges, where the input/output pins are, than in the center... If I understand the presentation correctly...\r\n\r\nFrom the heatmap, I can see that I get the \"inverse\" of what I am looking for: I get high latency/skew at the edges and lowest clock network latency in the middle of the array.\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/2a02ed4e-16d1-40cf-87cb-b356f6942acb)\r\n"}, {"user": "Export to yaml everywhere? Then ask ChatGPT to write a program to graph whatever you want :-)"}, {"user": "One more round of tinkering, extracting leaf latency (macros & flip flops) for mock-array:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/f9324f3c-9b7d-4186-b202-73ddd958e478)\r\n\r\n```\r\nimport numpy as np\r\nimport matplotlib.pyplot as plt\r\nfrom scipy.interpolate import griddata\r\nfrom mpl_toolkits.mplot3d import Axes3D\r\n\r\n# Extract data from the table\r\ndata = \"\"\"\r\n[INFO GUI-0090] 353016 31894 _131_/CLK 2.5811525e-10\r\n[INFO GUI-0090] 353610 32704 _132_/CLK 2.578819e-10\r\n[INFO GUI-0090] 353448 29734 _133_/CLK 2.589441e-10\r\n[INFO GUI-0090] 353232 30004 _134_/CLK 2.5863567e-10\r\n[INFO GUI-0090] 353232 32164 _135_/CLK 2.5806945e-10\r\n[INFO GUI-0090] 353232 33514 _137_/CLK 2.5752672e-10\r\n[INFO GUI-0090] 352962 73474 _139_/CLK 2.4607233e-10\r\n[INFO GUI-0090] 353070 75094 _143_/CLK 2.455407e-10\r\n[INFO GUI-0090] 353232 74554 _145_/CLK 2.4536023e-10\r\n[INFO GUI-0090] 325488 49596 ces_0_7/clock 2.3215012e-10\r\n[INFO GUI-0090] 325488 97116 ces_1_7/clock 2.2571323e-10\r\n[INFO GUI-0090] 353070 30274 _136_/CLK 2.504758e-10\r\n[INFO GUI-0090] 353232 32974 _138_/CLK 2.5033728e-10\r\n[INFO GUI-0090] 353988 74824 _140_/CLK 2.468455e-10\r\n[INFO GUI-0090] 353070 74284 _141_/CLK 2.4607524e-10\r\n[INFO GUI-0090] 353124 73744 _142_/CLK 2.4646146e-10\r\n[INFO GUI-0090] 353718 74014 _144_/CLK 2.4688515e-10\r\n[INFO GUI-0090] 353070 75364 _146_/CLK 2.455602e-10\r\n[INFO GUI-0090] 282288 49596 ces_0_6/clock 2.3558674e-10\r\n[INFO GUI-0090] 354312 120724 _147_/CLK 2.396328e-10\r\n[INFO GUI-0090] 353070 120184 _148_/CLK 2.389033e-10\r\n[INFO GUI-0090] 353070 120724 _149_/CLK 2.3958044e-10\r\n[INFO GUI-0090] 353070 120454 _150_/CLK 2.3879088e-10\r\n[INFO GUI-0090] 352908 120994 _151_/CLK 2.3941804e-10\r\n[INFO GUI-0090] 354150 120994 _152_/CLK 2.3930402e-10\r\n[INFO GUI-0090] 353070 121264 _153_/CLK 2.387552e-10\r\n[INFO GUI-0090] 353070 121534 _154_/CLK 2.3849495e-10\r\n[INFO GUI-0090] 354312 167704 _155_/CLK 2.5028343e-10\r\n[INFO GUI-0090] 353070 167434 _156_/CLK 2.5006122e-10\r\n[INFO GUI-0090] 354312 167974 _157_/CLK 2.5054644e-10\r\n[INFO GUI-0090] 353070 167704 _158_/CLK 2.5003247e-10\r\n[INFO GUI-0090] 353502 168244 _159_/CLK 2.5076013e-10\r\n[INFO GUI-0090] 353070 167974 _160_/CLK 2.4982605e-10\r\n[INFO GUI-0090] 353070 168514 _161_/CLK 2.504333e-10\r\n[INFO GUI-0090] 353070 168784 _162_/CLK 2.4995647e-10\r\n[INFO GUI-0090] 325488 144636 ces_2_7/clock 2.3382915e-10\r\n[INFO GUI-0090] 282288 192156 ces_3_6/clock 2.4364535e-10\r\n[INFO GUI-0090] 325488 192156 ces_3_7/clock 2.3902733e-10\r\n[INFO GUI-0090] 23088 49596 ces_0_0/clock 2.908152e-10\r\n[INFO GUI-0090] 66288 49596 ces_0_1/clock 2.8722372e-10\r\n[INFO GUI-0090] 109488 49596 ces_0_2/clock 2.7635877e-10\r\n[INFO GUI-0090] 23088 97116 ces_1_0/clock 2.6215496e-10\r\n[INFO GUI-0090] 66288 97116 ces_1_1/clock 2.5834934e-10\r\n[INFO GUI-0090] 109488 97116 ces_1_2/clock 2.481484e-10\r\n[INFO GUI-0090] 152688 49596 ces_0_3/clock 2.2604922e-10\r\n[INFO GUI-0090] 152688 97116 ces_1_3/clock 2.2475981e-10\r\n[INFO GUI-0090] 195888 49596 ces_0_4/clock 2.4288263e-10\r\n[INFO GUI-0090] 239088 49596 ces_0_5/clock 2.4712393e-10\r\n[INFO GUI-0090] 195888 97116 ces_1_4/clock 2.3749708e-10\r\n[INFO GUI-0090] 239088 97116 ces_1_5/clock 2.492415e-10\r\n[INFO GUI-0090] 282288 97116 ces_1_6/clock 2.5338398e-10\r\n[INFO GUI-0090] 23088 144636 ces_2_0/clock 2.5319144e-10\r\n[INFO GUI-0090] 66288 144636 ces_2_1/clock 2.488505e-10\r\n[INFO GUI-0090] 109488 144636 ces_2_2/clock 2.3649802e-10\r\n[INFO GUI-0090] 23088 192156 ces_3_0/clock 2.6104152e-10\r\n[INFO GUI-0090] 66288 192156 ces_3_1/clock 2.5707544e-10\r\n[INFO GUI-0090] 109488 192156 ces_3_2/clock 2.4463978e-10\r\n[INFO GUI-0090] 152688 144636 ces_2_3/clock 2.2558208e-10\r\n[INFO GUI-0090] 195888 144636 ces_2_4/clock 2.394501e-10\r\n[INFO GUI-0090] 239088 144636 ces_2_5/clock 2.5129004e-10\r\n[INFO GUI-0090] 282288 144636 ces_2_6/clock 2.5545635e-10\r\n[INFO GUI-0090] 152688 192156 ces_3_3/clock 2.271353e-10\r\n[INFO GUI-0090] 195888 192156 ces_3_4/clock 2.4349614e-10\r\n[INFO GUI-0090] 239088 192156 ces_3_5/clock 2.4800043e-10\r\n[INFO GUI-0090] 353070 215224 _163_/CLK 2.5301994e-10\r\n[INFO GUI-0090] 354150 215764 _164_/CLK 2.5379573e-10\r\n[INFO GUI-0090] 352908 215764 _165_/CLK 2.546915e-10\r\n[INFO GUI-0090] 353016 215494 _166_/CLK 2.543563e-10\r\n[INFO GUI-0090] 352908 216034 _167_/CLK 2.5420016e-10\r\n[INFO GUI-0090] 353016 216304 _168_/CLK 2.53308e-10\r\n[INFO GUI-0090] 353070 216844 _169_/CLK 2.529667e-10\r\n[INFO GUI-0090] 353070 216574 _170_/CLK 2.5356642e-10\r\n[INFO GUI-0090] 282288 239676 ces_4_6/clock 2.362913e-10\r\n[INFO GUI-0090] 325488 239676 ces_4_7/clock 2.3206259e-10\r\n[INFO GUI-0090] 353556 262474 _171_/CLK 2.312914e-10\r\n[INFO GUI-0090] 353070 263014 _172_/CLK 2.3154262e-10\r\n[INFO GUI-0090] 353070 263284 _173_/CLK 2.3117369e-10\r\n[INFO GUI-0090] 353070 262744 _174_/CLK 2.3042566e-10\r\n[INFO GUI-0090] 353070 263824 _175_/CLK 2.3130639e-10\r\n[INFO GUI-0090] 353070 263554 _176_/CLK 2.3141243e-10\r\n[INFO GUI-0090] 353124 264094 _177_/CLK 2.3148382e-10\r\n[INFO GUI-0090] 354312 263554 _178_/CLK 2.3118188e-10\r\n[INFO GUI-0090] 353502 308644 _179_/CLK 2.4495708e-10\r\n[INFO GUI-0090] 353232 308914 _180_/CLK 2.421735e-10\r\n[INFO GUI-0090] 353394 309184 _181_/CLK 2.449023e-10\r\n[INFO GUI-0090] 352962 309454 _182_/CLK 2.428038e-10\r\n[INFO GUI-0090] 354204 309454 _183_/CLK 2.4457464e-10\r\n[INFO GUI-0090] 353664 309994 _184_/CLK 2.4385688e-10\r\n[INFO GUI-0090] 353070 309724 _185_/CLK 2.4294902e-10\r\n[INFO GUI-0090] 353664 310264 _186_/CLK 2.443524e-10\r\n[INFO GUI-0090] 353934 351844 _187_/CLK 2.53289e-10\r\n[INFO GUI-0090] 353016 353734 _189_/CLK 2.5345356e-10\r\n[INFO GUI-0090] 353016 354274 _193_/CLK 2.5375743e-10\r\n[INFO GUI-0090] 353556 352114 _194_/CLK 2.533773e-10\r\n[INFO GUI-0090] 353880 349684 _188_/CLK 2.4994018e-10\r\n[INFO GUI-0090] 353286 351574 _190_/CLK 2.502142e-10\r\n[INFO GUI-0090] 354042 349414 _191_/CLK 2.501929e-10\r\n[INFO GUI-0090] 353016 354004 _192_/CLK 2.5043992e-10\r\n[INFO GUI-0090] 282288 334716 ces_6_6/clock 2.3779426e-10\r\n[INFO GUI-0090] 325488 334716 ces_6_7/clock 2.374277e-10\r\n[INFO GUI-0090] 282288 382236 ces_7_6/clock 2.4838717e-10\r\n[INFO GUI-0090] 325488 382236 ces_7_7/clock 2.4390354e-10\r\n[INFO GUI-0090] 23088 239676 ces_4_0/clock 2.6987032e-10\r\n[INFO GUI-0090] 66288 239676 ces_4_1/clock 2.6595942e-10\r\n[INFO GUI-0090] 109488 239676 ces_4_2/clock 2.5412097e-10\r\n[INFO GUI-0090] 152688 239676 ces_4_3/clock 2.2762146e-10\r\n[INFO GUI-0090] 23088 287196 ces_5_0/clock 2.6053942e-10\r\n[INFO GUI-0090] 66288 287196 ces_5_1/clock 2.5651453e-10\r\n[INFO GUI-0090] 109488 287196 ces_5_2/clock 2.451736e-10\r\n[INFO GUI-0090] 152688 287196 ces_5_3/clock 2.2595725e-10\r\n[INFO GUI-0090] 195888 287196 ces_5_4/clock 2.334176e-10\r\n[INFO GUI-0090] 239088 287196 ces_5_5/clock 2.501299e-10\r\n[INFO GUI-0090] 282288 287196 ces_5_6/clock 2.6032337e-10\r\n[INFO GUI-0090] 325488 287196 ces_5_7/clock 2.6381633e-10\r\n[INFO GUI-0090] 195888 239676 ces_4_4/clock 2.1926745e-10\r\n[INFO GUI-0090] 239088 239676 ces_4_5/clock 2.2354223e-10\r\n[INFO GUI-0090] 23088 382236 ces_7_0/clock 2.871124e-10\r\n[INFO GUI-0090] 66288 382236 ces_7_1/clock 2.8355954e-10\r\n[INFO GUI-0090] 109488 382236 ces_7_2/clock 2.7308103e-10\r\n[INFO GUI-0090] 152688 382236 ces_7_3/clock 2.729042e-10\r\n[INFO GUI-0090] 23088 334716 ces_6_0/clock 2.504028e-10\r\n[INFO GUI-0090] 66288 334716 ces_6_1/clock 2.464243e-10\r\n[INFO GUI-0090] 109488 334716 ces_6_2/clock 2.3548827e-10\r\n[INFO GUI-0090] 152688 334716 ces_6_3/clock 2.3087125e-10\r\n[INFO GUI-0090] 195888 334716 ces_6_4/clock 2.3455274e-10\r\n[INFO GUI-0090] 239088 334716 ces_6_5/clock 2.388076e-10\r\n[INFO GUI-0090] 195888 382236 ces_7_4/clock 2.4005137e-10\r\n[INFO GUI-0090] 239088 382236 ces_7_5/clock 2.4445432e-10\r\n\"\"\"\r\nrows = data.strip().split(\"\\n\")\r\nx = []\r\ny = []\r\nz = []\r\nfor row in rows:\r\n _, _, x_val, y_val, _, z_val = row.split()\r\n x.append(float(x_val))\r\n y.append(float(y_val))\r\n z.append(float(z_val)/1E-12)\r\n\r\n# Prepare grid for interpolation\r\nxi = np.linspace(min(x), max(x), 100)\r\nyi = np.linspace(min(y), max(y), 100)\r\nxi, yi = np.meshgrid(xi, yi)\r\n\r\n# Interpolate the z values\r\nzi = griddata((x, y), z, (xi, yi), method='linear')\r\n\r\n# Plot the 3D heatmap\r\nfig = plt.figure()\r\nax = fig.add_subplot(111, projection='3d')\r\nsurf = ax.plot_surface(xi, yi, zi, rstride=1, cstride=1, cmap=plt.cm.jet,\r\n linewidth=0, antialiased=False)\r\n\r\nfig.colorbar(surf)\r\n\r\nplt.show()\r\n```\r\n"}, {"user": "asap7/sha3 using python snippet above...\r\n\r\nAnimation: https://drive.google.com/file/d/1k64ew7QkB9AeRaFs9ZOX09EqzeMZupMG/view\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/01ef0594-b8dd-4188-b35d-1978d9ec762e)\r\n"}, {"assistant": "@precisionmoon any thoughts here as I know you want more visualization as well."}]} +{"messages": [{"user": "I'm looking for an arm64 OpenROAD architecture release to install on Linux AWS EC2 arm64.\r\nCan anyone give me a link or suggest how to compile?"}, {"assistant": "We don't test or release on arm64 but you can probably build from source."}, {"assistant": "https://openroad.readthedocs.io/en/latest/user/Build.html"}, {"assistant": "https://openroad-flow-scripts.readthedocs.io/en/latest/user/BuildLocally.html for ORFS"}]} +{"messages": [{"user": "Hi. I want to report an error with `odb`. If a net is connected with a `dbIterm` which is in another block, then something happens in an unexpected way.\r\n\r\nThis is the test code.\r\n\r\nYou can reproduce this error with this [commit](https://github.com/ApeachM/OpenROAD/commit/79a0c542fd4d1facbd65ea0bb717a71d54196d0c).\r\n\r\n```cpp\r\n#include \r\n\r\n#include \"db.h\"\r\n#include \"defin.h\"\r\n#include \"lefin.h\"\r\n#include \"lefout.h\"\r\n\r\nusing namespace odb; // NOLINT(*-build-using-namespace)\r\nusing namespace std; // NOLINT(*-build-using-namespace)\r\nint main()\r\n{\r\n dbDatabase* db_database = dbDatabase::create();\r\n dbTech* tech1 = dbTech::create(db_database, \"top_tech\");\r\n dbTech* tech2 = dbTech::create(db_database, \"bottom_tech\");\r\n auto* layer1\r\n = dbTechLayer::create(tech1, \"top_layer\", dbTechLayerType::MASTERSLICE);\r\n auto* layer2\r\n = dbTechLayer::create(tech2, \"bottom_layer\", dbTechLayerType::ROUTING);\r\n dbLib* lib1 = dbLib::create(db_database, \"top_lib\", tech1);\r\n dbLib* lib2 = dbLib::create(db_database, \"bottom_lib\", tech2);\r\n dbChip* chip = dbChip::create(db_database);\r\n dbBlock* block1 = dbBlock::create(chip, \"top\", tech1);\r\n dbBlock* block2 = dbBlock::create(block1, \"bottom\", tech2);\r\n // die size setting\r\n Rect die_rect(0, 0, 1000, 1000);\r\n block1->setDieArea(die_rect);\r\n block2->setDieArea(die_rect);\r\n\r\n vector inst_collector_top;\r\n vector inst_collector_bottom;\r\n\r\n // Example Library cell construction - top\r\n int top_lib_cell_num = 3;\r\n for (int i = 0; i < top_lib_cell_num; ++i) {\r\n int width = 100 + i * 10;\r\n int height = 200;\r\n dbMaster* master\r\n = dbMaster::create(lib1, (\"top_cell_\" + to_string(i)).c_str());\r\n master->setWidth(width);\r\n master->setHeight(height);\r\n master->setType(dbMasterType::CORE);\r\n\r\n int pin_num = 2 + i;\r\n for (int j = 0; j < pin_num; ++j) {\r\n dbSigType sig_type = dbSigType::SIGNAL;\r\n dbIoType io_type;\r\n if (j < pin_num - 1)\r\n io_type = dbIoType::INPUT;\r\n else\r\n io_type = dbIoType::OUTPUT;\r\n string pin_name = \"top_pin_\" + to_string(j);\r\n dbMTerm* master_terminal\r\n = dbMTerm::create(master, pin_name.c_str(), io_type, sig_type);\r\n dbMPin* master_pin = dbMPin::create(master_terminal);\r\n dbBox::create(master_pin, layer1, j * 2, j * 2, j * 2 + 1, j * 2 + 1);\r\n }\r\n master->setFrozen();\r\n }\r\n\r\n // Example Instance cells for top\r\n int instance_num = 10;\r\n // pick random number between 0 and top_lib_cell_num - 1, with fixed seed.\r\n srand(0); // NOLINT(*-msc51-cpp)\r\n for (int i = 0; i < instance_num; ++i) {\r\n int lib_cell_id = rand() % top_lib_cell_num; // NOLINT(*-msc50-cpp)\r\n int x, y;\r\n // set the x and y coordinate of the instance in the die area randomly.\r\n x = rand() % 1000; // NOLINT(*-msc50-cpp)\r\n y = rand() % 1000; // NOLINT(*-msc50-cpp)\r\n string inst_name = \"top_inst_\" + to_string(i);\r\n dbMaster* master = db_database->findMaster(\r\n (\"top_cell_\" + to_string(lib_cell_id)).c_str());\r\n auto inst = dbInst::create(block1, master, inst_name.c_str());\r\n inst->setLocation(x, y);\r\n inst_collector_top.push_back(inst);\r\n }\r\n\r\n // Example Library cell construction - bottom\r\n int bottom_lib_cell_num = 4;\r\n for (int i = 0; i < bottom_lib_cell_num; ++i) {\r\n int width = 200 + i * 20;\r\n int height = 300;\r\n dbMaster* master\r\n = dbMaster::create(lib2, (\"bottom_cell_\" + to_string(i)).c_str());\r\n master->setWidth(width);\r\n master->setHeight(height);\r\n master->setType(dbMasterType::CORE);\r\n\r\n int pin_num = 3 + i;\r\n for (int j = 0; j < pin_num; ++j) {\r\n dbSigType sig_type = dbSigType::SIGNAL;\r\n dbIoType io_type;\r\n if (j < pin_num - 1)\r\n io_type = dbIoType::INPUT;\r\n else\r\n io_type = dbIoType::OUTPUT;\r\n string pin_name = \"bottom_pin_\" + to_string(j);\r\n dbMTerm* master_terminal\r\n = dbMTerm::create(master, pin_name.c_str(), io_type, sig_type);\r\n dbMPin* master_pin = dbMPin::create(master_terminal);\r\n dbBox::create(master_pin, layer2, j * 2, j * 2, j * 2 + 1, j * 2 + 1);\r\n }\r\n master->setFrozen();\r\n }\r\n\r\n // Example Instance cells for bottom\r\n for (int i = 0; i < instance_num; ++i) {\r\n int lib_cell_id = rand() % top_lib_cell_num; // NOLINT(*-msc50-cpp)\r\n int x, y;\r\n // set the x and y coordinate of the instance in the die area randomly.\r\n x = rand() % 1000; // NOLINT(*-msc50-cpp)\r\n y = rand() % 1000; // NOLINT(*-msc50-cpp)\r\n string inst_name = \"bottom_inst_\" + to_string(i);\r\n dbMaster* master = db_database->findMaster(\r\n (\"bottom_cell_\" + to_string(lib_cell_id)).c_str());\r\n auto inst = dbInst::create(block2, master, inst_name.c_str());\r\n inst->setLocation(x, y);\r\n inst_collector_bottom.push_back(inst);\r\n }\r\n\r\n int inst_id1 = 5;\r\n int inst_id2 = 4;\r\n\r\n // intersected net test\r\n dbNet* net = dbNet::create(block1, (\"net_\" + to_string(inst_id1)).c_str());\r\n dbInst* inst1_top = inst_collector_top.at(inst_id1);\r\n dbInst* inst2_top = inst_collector_top.at(inst_id2);\r\n dbInst* inst1_bottom = inst_collector_bottom.at(inst_id1);\r\n dbITerm* i_term_top1 = inst1_top->findITerm(\"top_pin_0\");\r\n dbITerm* i_term_top2 = inst2_top->findITerm(\"top_pin_0\");\r\n dbITerm* i_term_bottom = inst1_bottom->findITerm(\"bottom_pin_0\");\r\n i_term_top1->connect(net);\r\n i_term_top2->connect(net);\r\n i_term_bottom->connect(net);\r\n\r\n cout << \"inst1_top: \" << inst1_top->getName() << '\\n';\r\n cout << \"inst2_top: \" << inst2_top->getName() << '\\n';\r\n cout << \"inst1_bottom: \" << inst1_bottom->getName() << '\\n' << '\\n';\r\n\r\n cout << \"connected instance number: \" << net->getITermCount() << '\\n';\r\n for (auto i_term : net->getITerms()) {\r\n cout << i_term->getInst()->getName() << '\\n';\r\n }\r\n\r\n /**\r\n * Console result:\r\n * \\code\r\n inst1_top: top_inst_5\r\n inst2_top: top_inst_4\r\n inst1_bottom: bottom_inst_5\r\n\r\n connected instance number: 1\r\n top_inst_6\r\n * */\r\n}\r\n```\r\n\r\nThe expected result should be below,\r\n\r\n```\r\ninst1_top: top_inst_5\r\ninst2_top: top_inst_4\r\ninst1_bottom: bottom_inst_5\r\n\r\nconnected instance number: 3\r\ntop_inst_5\r\ntop_inst_4\r\nbottom_inst_5\r\n```\r\n\r\nbut the console result is here.\r\n\r\n```\r\ninst1_top: top_inst_5\r\ninst2_top: top_inst_4\r\ninst1_bottom: bottom_inst_5\r\n\r\nconnected instance number: 1\r\ntop_inst_6\r\n```\r\n\r\nIf I erase the line of code below, then it seems to work well in the right way.\r\n\r\n```cpp\r\n // i_term_bottom->connect(net);\r\n```\r\n"}, {"assistant": "That's not supported. In general the multi-block connectivity model still needs work. The usage will be to have a dbBTerm on each block and at the top level to connect the corresponding dbITerms. You can't connect laterally across the hierarchy (same as Verilog)."}]} +{"messages": [{"user": "With `make DESIGN_CONFIG=designs/asap7/sram-64x16/config.mk` I get a lot of slew and I heard about `set_max_transition` and found it used in some designs in ORFS, so I thought I would see what it did...\r\n\r\n\r\n```\r\n==========================================================================\r\nresizer pre report_checks -path_delay max\r\n--------------------------------------------------------------------------\r\nStartpoint: _358_ (falling edge-triggered flip-flop clocked by io_clk')\r\nEndpoint: io_ram_dout2[43] (output port clocked by io_clk)\r\nPath Group: io_clk\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 0.00 clock io_clk' (fall edge)\r\n 0.00 0.00 clock network delay (ideal)\r\n 0.00 0.00 0.00 v _358_/CLK (DFFLQNx1_ASAP7_75t_R)\r\n 95.79 123.37 123.37 v _358_/QN (DFFLQNx1_ASAP7_75t_R)\r\n 1 6.79 _038_ (net)\r\n 96.33 4.05 127.42 v _173_/A (INVx3_ASAP7_75t_R)\r\n 45.29 35.23 162.65 ^ _173_/Y (INVx3_ASAP7_75t_R)\r\n 1 3.94 io_ram_dout2[43] (net)\r\n 45.43 1.45 164.10 ^ io_ram_dout2[43] (out)\r\n 164.10 data arrival time\r\n\r\n 0.00 500.00 500.00 clock io_clk (rise edge)\r\n 0.00 500.00 clock network delay (ideal)\r\n 0.00 500.00 clock reconvergence pessimism\r\n -100.00 400.00 output external delay\r\n 400.00 data required time\r\n-----------------------------------------------------------------------------\r\n 400.00 data required time\r\n -164.10 data arrival time\r\n-----------------------------------------------------------------------------\r\n 235.90 slack (MET)\r\n```\r\n\r\n\r\n0.050 ns seems to be a good place to start to bring down the slew from 95.79 above.\r\n\r\nWhen I add `set_max_transition 0.05 [current_design]` to the constraints.sdc, the flow seems to get stuck:\r\n\r\n```\r\nPerform port buffering...\r\n[INFO RSZ-0027] Inserted 79 input buffers.\r\n[INFO RSZ-0028] Inserted 128 output buffers.\r\nPerform buffer insertion...\r\n[INFO RSZ-0058] Using max wire length 232um.\r\n[no further output after 10 minutes or so]\r\n```\r\n\r\nmaybe the units are picoseconds? `set_max_transition 50 [current_design]`, same result, resizing doesn't seem to complete.\r\n\r\nCreated a draft pull request to check if it completes... https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1315\r\n"}, {"assistant": "You are setting it 0.05ps not ns which is an impossibly fast target."}, {"user": "`set_max_transition 80 [current_design]` is as low as I could get and `make cts` completing in a reasonable amount of time.\r\n\r\nLots of violations:\r\n\r\n```\r\n==========================================================================\r\ncts final report_check_types -max_slew -max_cap -max_fanout -violators\r\n--------------------------------------------------------------------------\r\nmax slew\r\n\r\nPin Limit Slew Slack\r\n------------------------------------------------------------\r\n_8_44/A 80.00 330.31 -250.31 (VIOLATED)\r\n_8_46/A 80.00 309.18 -229.18 (VIOLATED)\r\nclkbuf_4_4_0_io_clk/Y 80.00 294.55 -214.55 (VIOLATED)\r\nSRAM2RW16x32_2/CE1 80.00 249.22 -169.22 (VIOLATED)\r\nSRAM2RW16x32_2/CE2 80.00 249.17 -169.17 (VIOLATED)\r\nSRAM2RW16x32/CE1 80.00 224.86 -144.86 (VIOLATED)\r\nSRAM2RW16x32/CE2 80.00 224.83 -144.83 (VIOLATED)\r\n_58_73/A 80.00 193.42 -113.42 (VIOLATED)\r\n_58_74/A 80.00 193.40 -113.40 (VIOLATED)\r\n_8_52/A 80.00 193.35 -113.35 (VIOLATED)\r\n_8_51/A 80.00 193.32 -113.32 (VIOLATED)\r\n_8_48/A 80.00 193.25 -113.25 (VIOLATED)\r\n_8_53/A 80.00 193.22 -113.22 (VIOLATED)\r\n_8_50/A 80.00 193.03 -113.03 (VIOLATED)\r\n_58_66/A 80.00 192.96 -112.96 (VIOLATED)\r\n_58/A 80.00 192.91 -112.91 (VIOLATED)\r\n_58_71/A 80.00 192.76 -112.76 (VIOLATED)\r\n_58_60/A 80.00 192.65 -112.65 (VIOLATED)\r\n_58_67/A 80.00 192.64 -112.64 (VIOLATED)\r\n_8_17/A 80.00 192.28 -112.28 (VIOLATED)\r\n_8_18/A 80.00 192.23 -112.23 (VIOLATED)\r\nclkbuf_4_11_0_io_clk/Y 80.00 191.85 -111.85 (VIOLATED)\r\n_8_55/A 80.00 154.73 -74.73 (VIOLATED)\r\n_8_24/A 80.00 154.72 -74.72 (VIOLATED)\r\n_58_70/A 80.00 154.72 -74.72 (VIOLATED)\r\n_58_77/A 80.00 154.71 -74.71 (VIOLATED)\r\n_8_54/A 80.00 154.67 -74.67 (VIOLATED)\r\n_8_49/A 80.00 154.66 -74.66 (VIOLATED)\r\n_8_57/A 80.00 154.55 -74.55 (VIOLATED)\r\n_58_75/A 80.00 154.42 -74.42 (VIOLATED)\r\n_58_63/A 80.00 154.36 -74.36 (VIOLATED)\r\nclkbuf_4_10_0_io_clk/Y 80.00 153.74 -73.74 (VIOLATED)\r\nSRAM2RW16x32_3/CE1 80.00 148.30 -68.30 (VIOLATED)\r\n_8_19/A 80.00 142.96 -62.96 (VIOLATED)\r\n_8_36/A 80.00 142.96 -62.96 (VIOLATED)\r\nclkbuf_4_2_0_io_clk/Y 80.00 142.96 -62.96 (VIOLATED)\r\nclkbuf_4_9_0_io_clk/A 80.00 140.76 -60.76 (VIOLATED)\r\nclkbuf_4_8_0_io_clk/A 80.00 140.75 -60.75 (VIOLATED)\r\nclkbuf_4_10_0_io_clk/A 80.00 139.69 -59.69 (VIOLATED)\r\nclkbuf_4_4_0_io_clk/A 80.00 139.66 -59.66 (VIOLATED)\r\nclkbuf_4_5_0_io_clk/A 80.00 139.65 -59.65 (VIOLATED)\r\nclkbuf_4_11_0_io_clk/A 80.00 139.64 -59.64 (VIOLATED)\r\nclkbuf_4_6_0_io_clk/A 80.00 139.22 -59.22 (VIOLATED)\r\nclkbuf_4_7_0_io_clk/A 80.00 139.19 -59.19 (VIOLATED)\r\nclkbuf_4_0_0_io_clk/A 80.00 138.58 -58.58 (VIOLATED)\r\nclkbuf_4_1_0_io_clk/A 80.00 138.12 -58.12 (VIOLATED)\r\nclkbuf_4_15_0_io_clk/A 80.00 137.02 -57.02 (VIOLATED)\r\nclkbuf_4_14_0_io_clk/A 80.00 137.02 -57.02 (VIOLATED)\r\nclkbuf_4_13_0_io_clk/A 80.00 137.01 -57.01 (VIOLATED)\r\nclkbuf_4_12_0_io_clk/A 80.00 136.99 -56.99 (VIOLATED)\r\nclkbuf_4_3_0_io_clk/A 80.00 136.86 -56.86 (VIOLATED)\r\nclkbuf_4_2_0_io_clk/A 80.00 136.22 -56.22 (VIOLATED)\r\nclkbuf_0_io_clk/Y 80.00 132.32 -52.32 (VIOLATED)\r\nSRAM2RW16x32_2/O2[23] 0.23 45.42 -45.19 (VIOLATED)\r\nSRAM2RW16x32_2/O2[24] 0.23 45.26 -45.04 (VIOLATED)\r\nSRAM2RW16x32_2/O2[16] 0.23 41.77 -41.54 (VIOLATED)\r\nSRAM2RW16x32_3/CE2 80.00 120.37 -40.37 (VIOLATED)\r\nSRAM2RW16x32_2/O2[30] 0.23 40.24 -40.01 (VIOLATED)\r\nSRAM2RW16x32_2/O2[26] 0.23 38.87 -38.65 (VIOLATED)\r\nSRAM2RW16x32_2/O2[29] 0.23 38.54 -38.31 (VIOLATED)\r\nSRAM2RW16x32_2/O2[12] 0.23 38.16 -37.93 (VIOLATED)\r\nSRAM2RW16x32_2/O2[17] 0.23 36.78 -36.55 (VIOLATED)\r\nSRAM2RW16x32_2/O2[7] 0.23 36.69 -36.46 (VIOLATED)\r\n```"}, {"user": "This PR uses set_max_transition. I have an example to study now, so closing.\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1311"}]} +{"messages": [{"user": "Is there any way to generate a report for max cap, max fanout and max slew after \u201crepair_design\u201d is applied?"}, {"assistant": "If you are using ORFS then we already do that in 3_4_place_resized.log. If any flow you can insert the relevant commands."}, {"user": "I am not using ORFS."}, {"assistant": "You can add ``` report_check_types -max_slew -max_capacitance -max_fanout``` to whatever you are using then"}, {"user": "OK, I am using this, if after using this command nothing is shown does that means all the violations are cleared? \r\n"}]} +{"messages": [{"user": "I can see a function of `dbDatabase`, which is \r\n\r\n`dbSet dbDatabase::getChips()`.\r\n\r\nHowever, in `dbChip* dbChip::create(dbDatabase* db_)` function,\r\n```cpp\r\n///\r\n/// Create a new chip.\r\n/// Returns nullptr if a chip already exists.\r\n/// Returns nullptr if there is no database technology.\r\n///\r\ndbChip* dbChip::create(dbDatabase* db_)\r\n{\r\n _dbDatabase* db = (_dbDatabase*) db_;\r\n\r\n if (db->_chip != 0)\r\n return nullptr;\r\n\r\n _dbChip* chip = db->_chip_tbl->create();\r\n db->_chip = chip->getOID();\r\n return (dbChip*) chip;\r\n}\r\n```\r\nit prevents making several Chip object.\r\nIs `getChips()` are deprecated one and there's no way to make several chip in current odb version?\r\nOr is there any way to use `dbSet dbDatabase::getChips()` function and handle several Chip object?\r\n\r\n\r\n\r\nI appreciate for spending your precious time reading my question. Thank you."}, {"assistant": "The dbChip is a pretty useless class. You can only create one but you can create multiple dbBlock in one dbChip. I expect to model all the die/tier/stack as dbBlock and mostly ignore dbChip."}]} +{"messages": [{"user": "Silly question...\r\n\r\n```\r\n>>> report_checks -path_delay max -through [get_pins foo*] -format full_clock_expanded -fields {net slew cap}\r\nStartpoint: yyy (positive level-sensitive latch clocked by clock)\r\nEndpoint: zzz (output port clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock source latency\r\n 0.00 0.00 0.00 ^ clock (in)\r\n[deleted]\r\n 580.10 4606.57 time given to startpoint\r\n[deleted]\r\n\u00b4\u00b4\u00b4\r\n"}, {"assistant": "I think you want to resolve \"positive level-sensitive latch\" first. I think it relates to latch transparency."}, {"user": "Fixed in #3762"}]} +{"messages": [{"user": "I want to set a false path for two pins on a macro, but not at the macro's level, but rather at the containing macros level.\r\n\r\nI looked at\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/bf9f1e81bfabb85c0bfe794d18a4ea82dda83872/flow/designs/tsmc65lp/vanilla5/constraint.sdc#L724\r\n\r\nand thought it was supported. Though when I read https://github.com/The-OpenROAD-Project/OpenSTA/blob/3275a304e17092895b7d7721148edc7dc67ba3aa/search/Sta.cc#L2080, it looks like I can only use the ports of the macro for the constraints.sdc file as `-to` and `-from`. \r\n\r\nNo changes are intended for mock-array w.r.t. this, I'm only using mock-array to illustrate what I'm trying to find the syntax for:\r\n\r\n```\r\n>>> set_false_path -from [get_pins ces_6_6/io_ins_right*] -to [get_pins ces_6_6/io_outs_right*]\r\n[WARNING STA-0018] 'ces_6_6/io_ins_right[0]' is not a valid start point.\r\n[WARNING STA-0018] 'ces_6_6/io_ins_right[10]' is not a valid start point.\r\n[WARNING STA-0018] 'ces_6_6/io_ins_right[11]' is not a valid start point.\r\n[WARNING STA-0018] 'ces_6_6/io_ins_right[12]' is not a valid start point.\r\n```\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/65c8550d-3187-4503-a1b7-2e35c81ccba6)\r\n"}, {"assistant": "@oharboe \r\nI got this from OpenSTA user guide:\r\n```\r\nfrom_list A list of clocks, instances, ports or pins.\r\nthrough_list A list of instances, pins or nets.\r\nto_list A list of clocks, instances, ports or pins.\r\n```\r\nSo as per this you can provide `pins` also.\r\n```\r\nThe **set_false_path** command disables timing along a path from, through and to a group of design objects.\r\n\r\nObjects in **from_list** can be clocks, register/latch instances, or register/latch clock pins. The -rise_from\r\nand -fall_from keywords restrict the false paths to a specific clock edge.\r\n\r\nObjects in **through_list** can be nets, instances, instance pins, or hierarchical pins,. The -rise_through\r\nand -fall_through keywords restrict the false paths to a specific path edge that traverses through the\r\nobject.\r\n\r\nObjects in **to_list** can be clocks, register/latch instances, or register/latch clock pins. The -rise_to and -\r\nfall_to keywords restrict the false paths to a specific transition at the path end.\r\n```"}, {"assistant": "You probably need to use -through as those points are not the beginning or end of a timing path."}, {"assistant": "I suspect you want \r\n\r\nset_false_path -through [get_pins ces_6_6/io_ins_right*] -through [get_pins ces_6_6/io_outs_right*]\r\n\r\n"}]} +{"messages": [{"user": "Is there a way to search for a net or a port in the Clock Tree Viewer in the GUI?\r\n\r\nI can zoom in then hover on one of the leafs and I can see what it connects to, very time-consuming though...\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/dfbdfa85-61df-4671-a6d5-c81714e3de16)\r\n"}, {"assistant": "Not to my knowledge (@gadfort )"}]} +{"messages": [{"user": "I would like to understand the .lib file format a bit better. It is my understanding that I should be able to calculate the delay of the macro output based on what is in the .lib file.\r\n\r\nFor the mock-array, we have 183.19 ps delay for driving the io_outs_left[0] output. Looking at the .lib file, I can't figure out where 183.19ps comes from.\r\n\r\n```\r\n 183.19 486.43 ^ ces_7_0/io_outs_left[0] (Element)\r\n```\r\n\r\nFrom mock-array:\r\n\r\n```\r\n>>> report_checks -path_delay max -to io_outs_left_7[0] -format full -format full_clock_expanded\r\nStartpoint: ces_7_0 (rising edge-triggered flip-flop clocked by clock)\r\nEndpoint: io_outs_left_7[0] (output port clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock source latency\r\n 0.00 0.00 ^ clock (in)\r\n 38.29 38.29 ^ wire65/Y (BUFx16f_ASAP7_75t_R)\r\n 43.22 81.50 ^ clkbuf_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 39.84 121.35 ^ clkbuf_1_1_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 29.43 150.78 ^ clkbuf_2_2_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 32.00 182.78 ^ clkbuf_3_5_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 39.23 222.00 ^ clkbuf_4_10_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 16.70 238.70 ^ max_length67/Y (BUFx12f_ASAP7_75t_R)\r\n 30.80 269.51 ^ max_length66/Y (BUFx12f_ASAP7_75t_R)\r\n 33.73 303.24 ^ ces_7_0/clock (Element)\r\n 183.19 486.43 ^ ces_7_0/io_outs_left[0] (Element)\r\n 18.46 504.89 ^ output3073/Y (BUFx2_ASAP7_75t_R)\r\n 0.88 505.77 ^ io_outs_left_7[0] (out)\r\n 505.77 data arrival time\r\n\r\n1000.00 1000.00 clock clock (rise edge)\r\n 0.00 1000.00 clock network delay (propagated)\r\n 0.00 1000.00 clock reconvergence pessimism\r\n-200.00 800.00 output external delay\r\n 800.00 data required time\r\n---------------------------------------------------------\r\n 800.00 data required time\r\n -505.77 data arrival time\r\n---------------------------------------------------------\r\n 294.23 slack (MET)\r\n```\r\n\r\nIf I look in the Element, I can get a full report of what is driving that pin. However, my understanding is that some detail(I don't know what) is lost in the Element.lib representation:\r\n\r\n```\r\n>>> report_checks -path_delay max -to io_outs_left[0]\r\nStartpoint: _749_ (falling edge-triggered flip-flop clocked by clock')\r\nEndpoint: io_outs_left[0] (output port clocked by clock)\r\nPath Group: clock\r\nPath Type: max\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock' (fall edge)\r\n 108.94 108.94 clock network delay (propagated)\r\n 0.00 108.94 v _749_/CLK (DFFLQNx2_ASAP7_75t_R)\r\n 47.39 156.33 v _749_/QN (DFFLQNx2_ASAP7_75t_R)\r\n 12.65 168.98 ^ _496_/Y (INVx3_ASAP7_75t_R)\r\n 18.89 187.86 ^ _777_/Y (BUFx2_ASAP7_75t_R)\r\n 18.21 206.07 ^ output336/Y (BUFx2_ASAP7_75t_R)\r\n 0.75 206.82 ^ io_outs_left[0] (out)\r\n 206.82 data arrival time\r\n\r\n1000.00 1000.00 clock clock (rise edge)\r\n 0.00 1000.00 clock network delay (propagated)\r\n -20.00 980.00 clock uncertainty\r\n 0.00 980.00 clock reconvergence pessimism\r\n -50.00 930.00 output external delay\r\n 930.00 data required time\r\n---------------------------------------------------------\r\n 930.00 data required time\r\n -206.82 data arrival time\r\n---------------------------------------------------------\r\n 723.18 slack (MET)\r\n```\r\n\r\nHere the latency is 206.82, so that's not the same as 183.19 above...\r\n\r\n\r\nHere is the pin from the .lib file... Since the above is a rising transition, I think something in the \"rise\" part should add up to 183.19?\r\n\r\n```\r\nlibrary (Element) {\r\n comment : \"\";\r\n delay_model : table_lookup;\r\n simulation : false;\r\n capacitive_load_unit (1,fF);\r\n leakage_power_unit : 1pW;\r\n current_unit : \"1A\";\r\n pulling_resistance_unit : \"1kohm\";\r\n time_unit : \"1ps\";\r\n voltage_unit : \"1v\";\r\n library_features(report_delay_calculation);\r\n\r\n input_threshold_pct_rise : 50;\r\n input_threshold_pct_fall : 50;\r\n output_threshold_pct_rise : 50;\r\n output_threshold_pct_fall : 50;\r\n slew_lower_threshold_pct_rise : 10;\r\n slew_lower_threshold_pct_fall : 10;\r\n slew_upper_threshold_pct_rise : 90;\r\n slew_upper_threshold_pct_fall : 90;\r\n slew_derate_from_library : 1.0;\r\n\r\n\r\n nom_process : 1.0;\r\n nom_temperature : 0.0;\r\n nom_voltage : 0.77;\r\n\r\n lu_table_template(template_1) {\r\n variable_1 : total_output_net_capacitance;\r\n index_1 (\"1.44000, 2.88000, 5.76000, 11.52000, 23.04000, 46.08000, 92.16000\");\r\n }\r\n[deleted]\r\n type (\"io_outs_left\") {\r\n base_type : array;\r\n data_type : bit;\r\n bit_width : 64;\r\n bit_from : 63;\r\n bit_to : 0;\r\n }\r\n[deleted]\r\n pin(\"io_outs_left[0]\") {\r\n direction : output;\r\n capacitance : 0.0000;\r\n timing() {\r\n related_pin : \"clock\";\r\n timing_type : rising_edge;\r\n\tcell_rise(template_1) {\r\n values(\"179.22894,181.54152,185.64272,193.40265,208.65739,239.04976,299.74982\");\r\n\t}\r\n\trise_transition(template_1) {\r\n values(\"7.61338,11.68247,19.95989,36.84301,71.06670,139.93100,277.88907\");\r\n\t}\r\n\tcell_fall(template_1) {\r\n values(\"176.95767,179.16806,182.98384,189.92587,203.38441,230.16859,283.65878\");\r\n\t}\r\n\tfall_transition(template_1) {\r\n values(\"6.99804,10.42909,17.26771,31.14958,59.35967,116.35495,230.77396\");\r\n\t}\r\n }\r\n }\r\n```\r\n\r\nWhen I look at mock-array, I see that the wire is highlighted in yellow when I clock on the Element delay.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/092fe3d1-a379-4937-b6b3-408fa28d3000)\r\n\r\nBut when I click on the next line, that wire segment is also highlighted.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/5c812814-acfc-4093-9238-6ef7af09c91b)\r\n\r\n\r\nSo I guess the wire segments are associated with some of the lines in the timing list, but I can't see what the delay is due to the wire and I don't know which item that delay is associated with. I have seen separate \"wire\" lines in the timing report for `make gui_final`, but not in this case...\r\n\r\n"}, {"assistant": "You might try report_dcalc. Also ```report_checks -path_delay min -fields {slew cap input nets fanout} ``` helps to break out the gate and net delay.\r\n\r\nIn general it isn't a simple calculation when there are wire parasitics. With a simple capacitive load you just look at the table and interpolate.\r\n\r\nIn this case I would suspect input slews might be different between block and top level."}, {"assistant": "Maybe take a read of this article to help understand the non-linear delay model (NLDM) for .lib:\r\nhttps://www.physicaldesign4u.com/2020/05/non-linear-delay-model-nldm-in-vlsi.html\r\n\r\nThe \"exact number\" will never appear in the .lib file. The .lib file creates a series of lookup tables. The inputs to those lookup tables are the capacitance of the wiring on the output and the input slew. If the inputs are not exactly one of the keys in the lookup table (which they usually aren't because of floating point numbers) then the output is interpolated. You will almost never see the \"exact\" delay value appear in the .lib file itself."}, {"assistant": "```report_dcalc -from output3073/A -to output3073/Y```\r\nworks but the report is not simple to interpret "}, {"assistant": "What is your goal in this process? Likely there is more calculation in the interconnect side of the delay.\r\n\r\nYou can only use it on a single arc and not along a path."}, {"user": "I am looking at some numbers that are concerning and I wanted to understand this well enough that I can find out if OpenROAD/STA are probably working correctly or if the numbers are off and it is worth digging in to.\r\n\r\nI think I do now."}]} +{"messages": [{"user": "I'm curious as to why the placement gives so different results for a situation that should be identical.\r\n\r\nThe rows in mock-array are identical and there are io_lsbs_* on the right of mock-array that are fed flip flops.\r\n\r\nA snapshot from `make gui_place`:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/91c718ad-7392-4af6-8ed4-ce2184e6ef80)\r\n\r\nIf I zoom in on the upper right row, I see that the io_lsbs_*, fed by a flipflop that is placed right next to the outputs are somewhat spread out:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/25d2393c-d316-4ca0-a50c-9bdeef629066)\r\n\r\nIf I look at the row below and to the right, I see that the io_lsbs_* are clustered together, which looks neat.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/f5530a21-1135-4ad3-9f60-3304f2538d2f)\r\n\r\nAt the bottom row to the right, the io_lsbs_* are mixed into the other pins:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/5b4d25a7-567f-480f-bf58-736cb65bb0e3)\r\n\r\n\r\n\r\nSide-note: make foo_issue doesn't work out of the box on mock-array because the size of the tar.gz file is ca. 100mBytes. This complicates filing bug reports and feature requests.\r\n\r\nSide-note: the io_lsbs_* are driven by a flip flop, then go to an output cell and are finally buffered before they go to the pin of the macro. Silly question: what does an output cell do and why does it need to be buffered? Can't the flip-flop drive the output pin directly?\r\n"}, {"assistant": "Global placement isn't a process that will produce identical results in all areas, even if they have symmetry. We could look at specific areas if they seem to be suboptimal.\r\n\r\nYou can put the issue in google drive and put a link in the issue.\r\n\r\nWe buffer the inputs and outputs by default but it isn't strictly mandatory. FF often don't have a large amount of drive strength for driving output signals. However with no output loading in the sdc it probably doesn't matter but is a bit unrealistic.\r\n\r\nBtw, I still find there is too much hold buffering due to the unrealistically io constraints."}, {"user": "> Global placement isn't a process that will produce identical results in all areas, even if they have symmetry. We could look at specific areas if they seem to be suboptimal.\r\n\r\nI was just curious how much difference is considered pathological. If, looking at the pictures, this variation is expected, then I don't think there is anything more to investigate here.\r\n\r\n`make global_place_issue` generated a 120mByte .tar.gz file, but zipping just the 3_place.odb file gave me 2 mByte .zip file: [place.zip](https://github.com/The-OpenROAD-Project/OpenROAD/files/12225008/place.zip)\r\n\r\nTo generate it locally, run `make DESIGN_CONFIG=designs/asap7/mock-array/config.mk place`\r\n\r\nIf there is something interesting here, then this discussion can be converted to a feature request with the click of a button...\r\n\r\n> You can put the issue in google drive and put a link in the issue.\r\n> \r\n> We buffer the inputs and outputs by default but it isn't strictly mandatory. FF often don't have a large amount of drive strength for driving output signals. However with no output loading in the sdc it probably doesn't matter but is a bit unrealistic.\r\n\r\nI imagine that a flip flop with a lot of drive strength would be bigger and slower... seems sensible to create a small, fast and weak flip flop and leave buffering to buffers and inverters...\r\n\r\n> \r\n> Btw, I still find there is too much hold buffering due to the unrealistically io constraints.\r\n\r\nYes... I've got changes locally removes that, but I need to understand the clock tree generation better first. That's separate concern to placement though."}, {"assistant": "If I look at the current mock array the areas around the IOs are so filled with hold cells that the variation isn't as interesting as you show above as they are packed with cell, eg\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/85c19478-10dc-4e52-98e0-79af467df0f0)\r\n\r\nAlso the IOs are not placed symmetrically with respect to the macros which will influence global placement."}, {"user": "If this behavior exists when the hold cells are gone, then it's worth a second look."}]} +{"messages": [{"user": "Hello,\r\n\r\nI am wondering if there is a way to generate .rpt files for timing report?\r\n\"report_worst_slack\" directly shows the report in my terminal, but I want to record and compare different time slacks I get with different architecture for a design. \r\nI tried to use openroad -log to catch the reports but sometimes the log file is incomplete, is there any better way to do so?\r\n\r\nThanks\r\n\r\n"}, {"assistant": "In what way is the log incomplete? "}]} +{"messages": [{"user": "Silly question: I can find the input and outputs listed under ITerms for a macro, but where can I find the list of inputs and outputs for the top level design?\r\n\r\nIs there somewhere I can find ITerms for the top level design in the GUI?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/10437d70-44fd-4d47-8e7b-ade917810eab)\r\n"}, {"assistant": "On the block:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/3c5f0606-31ec-4be6-ae11-aa3212281780)\r\n\r\nYou can follow the link on any net or instance to inspect the block."}]} +{"messages": [{"user": "Hello.\r\n\r\nLooking at the document in `docs/contrib/DeveloperGuide.md`, following the `Example of Adding a Tool to OpenROAD` section, I would like to patch [`docs/misc/AddTool.patch`](https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/docs/misc/AddTool.patch) file but the error message has occurred. \r\n\r\n```shell\r\nminjae@minjae-desktop:~/OpenROAD3DFlow/docs/misc$ patch -p < AddTool.patch\r\npatch: option requires an argument -- 'p'\r\npatch: Try 'patch --help' for more information.\r\n```\r\n\r\n\r\n\r\nI am not familiar with patch files, so I can't assume what is the problem.\r\n\r\nIf you let me know then I would be very appreciated.\r\n\r\n\r\n\r\nThank you."}, {"assistant": "Hi\r\n\r\nPlease see\r\nhttps://openroad.readthedocs.io/en/latest/contrib/DeveloperGuide.html#example-of-adding-a-tool-to-openroad\r\n\r\nThe patch file itself is a bit old so some updating might be needed. What\r\nnew tool are you adding?\r\n\r\nMatt\r\n\r\nOn Thu, Jul 27, 2023 at 12:35\u202fPM MinJae Kim ***@***.***>\r\nwrote:\r\n\r\n> Hello.\r\n>\r\n> Looking at the document in docs/contrib/DeveloperGuide.md, following the Example\r\n> of Adding a Tool to OpenROAD section, I would like to patch\r\n> docs/misc/AddTool.patch\r\n> \r\n> file but the error message has occurred.\r\n>\r\n> ***@***.***:~/OpenROAD3DFlow/docs/misc$ patch -p < AddTool.patch\r\n> patch: option requires an argument -- 'p'\r\n> patch: Try 'patch --help' for more information.\r\n>\r\n> I am not familiar with patch files, so I can't assume what is the problem.\r\n>\r\n> If you let me know then I would be very appreciated.\r\n>\r\n> Thank you.\r\n>\r\n> \u2014\r\n> Reply to this email directly, view it on GitHub\r\n> ,\r\n> or unsubscribe\r\n> \r\n> .\r\n> You are receiving this because you are subscribed to this thread.Message\r\n> ID: ***@***.***>\r\n>\r\n"}]} +{"messages": [{"user": "For mock-array, I ran `make cts && make gui_cts` and pasted the clock tree below.\r\n\r\nI'm curious: why is there an inverter in front of every flip-flop and no invertor in front of the macros?\r\n \r\nI checked by hovering over a number of the pink dots at the leaf of the clock tree that the flip-flops are the leaf points with an invertor in front.\r\n\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/9a268a21-6f3b-4777-b10d-940090081cbb)\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/8a96024d-9038-445b-8826-c13354ca9264)\r\n\r\n\r\nThe clock period is 1000ps and the skew is 50ps, by gleaning at the clockd tree.\r\n\r\n"}, {"user": "I have tried to find some documentation on the `report_checks` output format, but lacking that I'm making some guesses....\r\n\r\nThe below is a report from mock-array/Element, where I notice the `clock clock' (fall edge)`, but mock-array is positive edge triggered, so why falling edge?\r\n\r\nCould it be that my design is positive edge triggered, but that the flip-flop is in fact negative edge triggered?\r\n\r\nThat would explain the inverter in front of every flip-flop in the clock-tree above too...\r\n\r\nI beleve the first path below is the data required path from macro input pin to the flip flop input pin and that the second path is the clock input pin on the macro to the flip flop input pin.\r\n\r\nWhat does `(propagated)` mean?\r\n\r\nI find `data required time` a bit confusing for the clock propagation path, but my guess that's just the chosen terminology and that the `data required time` for the clock is in fact the clock required time in my mind of thinking.\r\n\r\n```\r\n>>> report_checks -path_delay min -from io_ins_right[0]\r\nStartpoint: io_ins_right[0] (input port clocked by clock)\r\nEndpoint: _557_ (falling edge-triggered flip-flop clocked by clock')\r\nPath Group: clock\r\nPath Type: min\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (propagated)\r\n 50.00 50.00 ^ input external delay\r\n 2.24 52.24 ^ io_ins_right[0] (in)\r\n 11.98 64.22 ^ hold1749/Y (BUFx2_ASAP7_75t_R)\r\n 11.38 75.59 ^ hold745/Y (BUFx2_ASAP7_75t_R)\r\n 11.43 87.02 ^ hold1750/Y (BUFx2_ASAP7_75t_R)\r\n 11.95 98.97 ^ input129/Y (BUFx2_ASAP7_75t_R)\r\n 12.69 111.66 ^ hold1751/Y (BUFx2_ASAP7_75t_R)\r\n 12.88 124.54 ^ hold746/Y (BUFx2_ASAP7_75t_R)\r\n 12.83 137.37 ^ hold1752/Y (BUFx2_ASAP7_75t_R)\r\n 0.18 137.55 ^ _557_/D (DFFLQNx2_ASAP7_75t_R)\r\n 137.55 data arrival time\r\n\r\n 0.00 0.00 clock clock' (fall edge)\r\n 99.73 99.73 clock network delay (propagated)\r\n 20.00 119.73 clock uncertainty\r\n 0.00 119.73 clock reconvergence pessimism\r\n 119.73 v _557_/CLK (DFFLQNx2_ASAP7_75t_R)\r\n 10.65 130.38 library hold time\r\n 130.38 data required time\r\n---------------------------------------------------------\r\n 130.38 data required time\r\n -137.55 data arrival time\r\n---------------------------------------------------------\r\n 7.16 slack (MET)\r\n\r\n```\r\n"}, {"assistant": "Is this at the top or in the element?"}, {"assistant": "propagated means you are post-cts and \"set_propagated_clock [all_clocks]\" has been used. The delay is calculated from the actual clock network. The opposite is ideal clocks from before CTS."}, {"assistant": "If you look at DFFLQNx2_ASAP7_75t_R you'll see\r\n```\r\n ff (IQN,IQNN) {\r\n clocked_on : \"!CLK\";\r\n next_state : \"!D\";\r\n power_down_function : \"(!VDD) + (VSS)\";\r\n }\r\n```\r\nso it is on the negative edge. The ff choice is made during synthesis"}]} +{"messages": [{"user": "I am inserting buffers to my design. How can I find that buffers are being inserted? I cannot find anything in my design's netlist."}, {"assistant": "How are you inserting the buffers?"}, {"assistant": "There is no such command in OR:\r\n```\r\nopenroad> insert_buffer\r\ninvalid command name \"insert_buffer\"\r\nwhile evaluating insert_buffer\r\n```"}, {"assistant": "@AayushiRV \r\n`insert_buffer` is maintained by OpenLane. Check this example: https://github.com/The-OpenROAD-Project/OpenLane/blob/master/tests/1007/interactive.tcl\r\nSo OpenROAD nothing to do with that."}]} +{"messages": [{"user": "Hello everyone,\r\nI am new to the project but I have some experience with with PDK and enablement PDK in design flow.\r\n\r\nI was wondering how is structured the interface between the PDK file and the flow.\r\n\r\n>Do you know if there is a kind of **meta file/format** to describe the PDK and maybe \"explain\" to the flow where to pick the right file/tools?\r\nLike a kind of python `requirement.txt` file so it could be easy to integrate new PDK and switch from one technology to an other?\r\n\r\nToday, my impression is that it is still kind of challenging to have all the pieces or components of a PDK working together with the right version and right place to pick the files.\r\n\r\nThanks \r\n"}, {"assistant": "I don't know of any specific standard for PDK distribution. The main issue is that tools / formats are continuously coming in and out of vogue based on the process technology. Many PDKs may be \"incomplete\" due to lack of enablement for certain tools.\r\n\r\nhttps://github.com/RTimothyEdwards/open_pdks tries to create a standardized directory structure and format for PDKs, but of course there is effort in taking what the vendor provides and trying to fit it into that model because every PDK vendor is different.\r\n\r\n[ORFS](https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts) simply uses Make variables to point at the necessary files."}, {"assistant": "I think it is better to accept the PDK as provided than to mess with it as open_pdks requires. PDKs should be read-only."}]} +{"messages": [{"user": "I'm facing this error during global routing: \r\n`[ERROR DRT-0085] Valid access pattern combination not found for `\r\n`pipe_mu3_mul_18_52_g4568`\r\n`@@@ dead end inst`\r\n\r\nWhat does this mean exactly and what could be causing it?"}, {"assistant": "The router is having some trouble figuring out how it can access all the pins of the instance. Can you provide a test case? If so please open an issue."}]} +{"messages": [{"user": "I am getting this error during pin_access command. Unfortunately, I can't share the tech file to reproduction. Tech file is correct and this via is defined between two layers. Tech file is used in production chips. My question is how layer numbers are assigned? Is it something to do with order in which layers are defined in tech file?\r\n\r\npin_access -bottom_routing_layer $min_routing_layer \\\r\n -top_routing_layer $max_routing_layer\r\n\r\n[ERROR DRT-0126] Non-consecutive layers for via VV_XX_450_450_450_450_VV.\r\n"}, {"assistant": "The layer order is defined by their appearance in the tech lef. The expectation for a via is that the cut layer and the two adjacent routing layers are the only layers used in the via."}]} +{"messages": [{"user": "I'm focusing on macro placement task and familiar to bookshelf format data processing.\r\nBookshelf format provides convenience for extracting macros and netlist information.\r\nI do know there are scripts converting .lef.def files into bookshelf format, but how about the inserted datasets in the OpenROAD proj? Like ariane133 using nangate45 platform."}, {"assistant": "You would have to convert to lef/def. I don't know of a tool to do so automatically. Alternatively you could parse and build the db in TCL if that's easier."}]} +{"messages": [{"user": "I have run the following script:\r\n```\r\nread_lef ispd19_test6.input.lef\r\nread_def ispd19_test6.input.def\r\nset thread_count 8\r\nglobal_route\r\ndetailed_route\r\nwrite_db route.db\r\nreport wns\r\n>> wns 0\r\nreport tns\r\n>> tns 0\r\nreport worst_slack\r\n>> worst slack INF\r\n```\r\nDid anything go wrong? How can I get correct metrics? Thanks a lot!"}, {"assistant": "Do estimate parasitic and then report the metrics. Refer here: https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/test/flow.tcl#L264-L280 @xiaosinju "}, {"assistant": "This is a routing test case and has no timing information (no .lib or .sdc). What are you trying to accomplish?"}]} +{"messages": [{"user": "For `designs/asap7/gcd/config.mk` (default), I ran `make synth` and then `make gui_synth`.\r\n\r\nWhat is the significance and origin of the falling and rising edges in the GUI?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/977abf34-29d6-4e0e-b5cf-49ce396ed1e2)\r\n"}, {"assistant": "It tells you whether the signal is rising or falling in the path being shown."}]} +{"messages": [{"user": "I need to make some sort of change to my design, because the global placement doesn't complete.\r\n\r\nHow can I get some visibility into what is going on?\r\n\r\n```\r\n[INFO GPL-0075] Routability numCall: 1 inflationIterCnt: 1 bloatIterCnt: 0\r\n[doesn't seem to complete]\r\n```"}, {"user": "I added:\r\n\r\n```\r\nexport GPL_ROUTABILITY_DRIVEN=0\r\nexport GPL_TIMING_DRIVEN=0\r\n```\r\n\r\nSo now it completes... Perhaps I can glean something from this result downstream?\r\n\r\nYep.\r\n\r\nThe problem is that io placement falls back because there are too many pins so instead of wires going horizontally or vertically out of the macro, it is crisscrossing. I zoom in on one of those things and find a wire, then find the buffer tree and I can clearly see that IO pin placement had to fall back.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/1d94c3ad-c689-4d5e-b614-6a7380879dd8)\r\n\r\n\r\n"}]} +{"messages": [{"user": "Is there any plan for adding multirow standard cell support ?"}, {"assistant": " The code is written but it could use more real world testing. It would be great if you could try it out. The open PDKs don't have such cells today."}]} +{"messages": [{"user": "```c++\r\n// master setting\r\ndbMaster *master = dbMaster::create(db_lib, lib_cell_name.c_str());\r\nmaster->setWidth(width);\r\nmaster->setHeight(height);\r\nmaster->setType(dbMasterType::CORE);\r\n...\r\nmaster->setFrozen();\r\n// connect inst to the master\r\n \r\ndbInst* inst = dbInst::create(db_block, master, instance_info->inst_name.c_str());\r\n\r\n// now I want to change the size of inst, by unfrozen master and resize width and height\r\n// Is my intention of the below pseudo-code possible?\r\nmaster->setUnFrozen();\r\nmaster->setWidth(new_width);\r\nmaster->setHeight(new_height);\r\nmaster->setFrozen();\r\n```\r\n\r\n**I would like to know whether the above pseudo-code is possible.**\r\n\r\n**I want to resize the cell size** after the cell size is already determined. (For example, after parsing lef and def).\r\nBut it seems like not to exist function for unfreezing.\r\n\r\nIf I want to change the cell size, then should I \r\n1. re-construct the instance,\r\n2. re-construct the new dbMaster, \r\n3. deleting the original instance, \r\n4. and re-connecting the new dbInst to the nets, which was connected with the original one?\r\n\r\nI would like to know whether **is there another way, which is more simple**.\r\n\r\n\r\nThanks for the time for reading my question.\r\n\r\nSincerely."}, {"assistant": "Why are you freezing it in the first place?"}, {"assistant": "setWidth & setHeight don't care about the frozen status afaik. The key thing is that the port list is frozen. You can't add a dbMTerm to a frozen master."}]} +{"messages": [{"user": "I am writing some code for 3D Placer with ODB. \r\nHere, the technology of the two dies will differ. \r\n\r\nHowever, ODB is not currently supporting the 3D placer data structure.\r\n\r\nIf I want to read two technologies, then should I make different two dbDatabase objects for parsing two different lef file?\r\nOr is there another way to parse two lef files just using one dbDatabase object?\r\n\r\nThanks for the time for reading my question.\r\n\r\nSincerely.\r\n"}, {"assistant": "There is no way currently to support two lef files. That's an enhancement we would make as part of the Darpa 3d-ic program if we are funded."}]} +{"messages": [{"user": "Hello everyone,\r\n\r\nTo support drawing scan chains in OpenROAD in the gui and CTL ([Core Test Language](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=966626)) parser/generator we need to make the scan info available in odb. Here I describe a DB schema to represent CTLs in odb.\r\n\r\n## Objective\r\n\r\n* Make scan chains available to the gui to be able to highlight scan structures and display information related to scan.\r\n* Provide a common source of true for other commands to query and find scan structures on the design.\r\n* Provide support for a future parser for CTLs files.\r\n\r\n## Out of scope\r\n\r\n* Parsing and writing a CTL file at this time.\r\n* Handling test patterns.\r\n\r\n## CTLs\r\n\r\nCTLs are files based on the [STIL standard](https://grouper.ieee.org/groups/1450/dot1/p1450.1-D14.pdf) that allow us to share information between DFT tools for optimizations and interoperability between different vendors. They describe the internal scan structures and they are useful too to share information between internal commands inside OpenROAD, like scan insertion and the GUI.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/1619948/b513ec9c-4575-45c4-bac0-0401ab164da2)\r\n\r\nSource: CTL for Test Information of Digital ICs, Rohit Kapur\r\n\r\n**The schema described here is not a 1:1 map of a CTL file but should be enough to create one or to store the information coming from a CTL.**\r\n\r\n## dbScanChain\r\n\r\n* name: string\r\n* length: uint\r\n* cells: list\\\r\n* scanIn: dbScanPin\r\n* scanOut: dbScanPin\r\n* scanClock: dbScanPin\r\n* scanEnable: dbScanPin\r\n* testMode: string\r\n* partitions: list\\\r\n* scanInsts: list\\\r\n\r\n## dbScanPin\r\n\r\nWrapper to handle either dbBTerm or dbITerm:\r\n\r\n* bterm: dbBTerm\r\n* iterm: dbITerm\r\n\r\n## dbScanPartition\r\n\r\n* start: dbScanPin\r\n* stop: dbScanPin\r\n* name: string\r\n\r\n## dbScanInst\r\n\r\n* scanIn: dbScanPin\r\n* scanOut: dbScanPin\r\n* bits: uint\r\n* type: enum [OneBit, ShiftRegister, BlackBox]\r\n\r\n\r\n## Flow\r\n\r\nAt the end of *insert_dft* we will be storing the scan chain information into odb using the created dbCTL object. The gui will be able to query this information and display it. dbScanChain will be attached to the dbBlock that contains the scan chains that are inside it.\r\n\r\n\r\n## Open Questions\r\n\r\n* Where can I add a new dbObject (dbCTL) to dbBlock? \r\n* How can I represent maps (will std::map work?) string-> dbObject in the json db format?\r\n* I am creating a wrapper for dbBTerm and dbITerm for cases where the scan pins are not coming from the block, is there any way to handle this in the json db format? \r\n\r\n"}, {"user": "Hi @maliberty , who do you think is the right person to review this? Specially the open questions at the end.\r\n\r\nThanks!"}, {"assistant": "Scan chain is used in both CTL and in DEF. Can dbScanChain accommodate both or do we need to consider having two classes? If the later, how would you suggest naming them ?"}, {"assistant": "Looking at DEF:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/6a7a39c4-e9b0-44e5-8beb-0fe450c7928d)\r\n\r\nIt looks like the dbScanPartition needs a way to store MAXBITS. \r\n\r\nEach element of the chain also has a BITS field which seems hard to represent here. Perhaps we need a dbScanInst?\r\n\r\nHow would you infer FLOATING or ORDERED from the design?"}, {"user": "Hi @maliberty ,\r\n\r\nDo you think we are ready to start the implementation?\r\n\r\nThanks!,\r\nFelipe"}, {"assistant": "LGTM. Thanks for the contirbution @fgaray "}]} +{"messages": [{"user": "It want to find and view nets that cause hold violations.\r\n\r\nToday I have to wait and hope for a global routing failure to be able to view the nets that cause hold violations in DRC viewer there.\r\n\r\n```\r\nRepair setup and hold violations...\r\nTNS end percent 5\r\n[INFO RSZ-0041] Resized 2 instances.\r\n[WARNING RSZ-0062] Unable to repair all setup violations.\r\n[INFO RSZ-0046] Found 2957 endpoints with hold violations.\r\n[INFO RSZ-0032] Inserted 40106 hold buffers.\r\nPlacement Analysis\r\n```\r\n"}, {"assistant": "```tcl\r\nfind_timing_paths -path_delay min -slack_max 0\r\n```\r\n@oharboe, Would this work for you?\r\nNote that RSZ just said it had found `2957` hold violations; after inserting the `40106` buffers, there's no warning.\r\nSo it is likely that all have been fixed -- see the warning in the line above for a contrast about setup violations.\r\n\r\nFor setup you would do:\r\n```tcl\r\nfind_timing_paths -path_delay max -slack_max 0\r\n```"}, {"user": "Found an approach... Here is what I did:\r\n\r\n1. create some hold failures by reducing the clock period from 2000 to 1000ps in mock-array, using diff below.\r\n2. There are no timing violations in placement, the timing violations happen after CTS.\r\n3. Modify cts.tcl to write out an ODB file *before* hold cells are inserted and the design is repair. Post repair in CTS there are no violations.\r\n\r\nNow I can run commands to examine minimum hold time violations, which will lead to hold cells being inserted.\r\n\r\n\r\n```\r\nreport_checks -path_delay min\r\nStartpoint: io_insRight_0[61] (input port clocked by clock)\r\nEndpoint: ces_0_0 (rising edge-triggered flip-flop clocked by clock)\r\nPath Group: clock\r\nPath Type: min\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (propagated)\r\n 200.00 200.00 ^ input external delay\r\n 0.00 200.00 ^ io_insRight_0[61] (in)\r\n 10.45 210.45 ^ input1082/Y (BUFx2_ASAP7_75t_R)\r\n 0.04 210.48 ^ ces_0_0/io_ins_right[61] (Element)\r\n 210.48 data arrival time\r\n\r\n 0.00 0.00 clock clock (rise edge)\r\n 337.72 337.72 clock network delay (propagated)\r\n 0.00 337.72 clock reconvergence pessimism\r\n 337.72 ^ ces_0_0/clock (Element)\r\n 102.40 440.11 library hold time\r\n 440.11 data required time\r\n---------------------------------------------------------\r\n 440.11 data required time\r\n -210.48 data arrival time\r\n---------------------------------------------------------\r\n -229.63 slack (VIOLATED)\r\n```\r\n\r\n```\r\nforeach path [find_timing_paths -slack_max 0 -group_count 10 -path_delay min] {puts \"[get_property $path slack] [get_property [get_property $path endpoint] full_name]\"}\r\n-229.630280 ces_0_0/io_ins_right[61]\r\n-229.599152 ces_0_0/io_ins_right[3]\r\n-229.596451 ces_0_0/io_ins_right[56]\r\n-229.570663 ces_0_0/io_ins_right[51]\r\n-229.570786 ces_0_0/io_ins_right[53]\r\n-229.568649 ces_0_0/io_ins_right[1]\r\n-229.561371 ces_0_0/io_ins_right[14]\r\n-229.517380 ces_0_0/io_ins_right[30]\r\n-229.512604 ces_0_0/io_ins_right[5]\r\n-229.509186 ces_7_0/io_ins_right[61]\r\n```\r\n\r\n\r\n\r\n```\r\ndiff --git a/flow/designs/asap7/mock-array/Element/constraints.sdc b/flow/designs/asap7/mock-array/Element/constraints.sdc\r\nindex be545b8f..0a66e62e 100644\r\n--- a/flow/designs/asap7/mock-array/Element/constraints.sdc\r\n+++ b/flow/designs/asap7/mock-array/Element/constraints.sdc\r\n@@ -4,7 +4,7 @@ set cols [expr {[info exists ::env(MOCK_ARRAY_COLS)] ? $::env(MOCK_ARRAY_COLS) :\r\n \r\n set clk_name clock\r\n set clk_port_name clock\r\n-set clk_period 2000\r\n+set clk_period 1000\r\n \r\n set clk_port [get_ports $clk_port_name]\r\n create_clock -period $clk_period -waveform [list 0 [expr $clk_period / 2]] -name $clk_name $clk_port\r\ndiff --git a/flow/designs/asap7/mock-array/constraints.sdc b/flow/designs/asap7/mock-array/constraints.sdc\r\nindex 5d33c792..46b20e5b 100644\r\n--- a/flow/designs/asap7/mock-array/constraints.sdc\r\n+++ b/flow/designs/asap7/mock-array/constraints.sdc\r\n@@ -1,6 +1,6 @@\r\n set sdc_version 2.0\r\n \r\n-set clk_period 2000\r\n+set clk_period 1000\r\n create_clock [get_ports clock] -period $clk_period -waveform [list 0 [expr $clk_period/2]]\r\n \r\n set clk_name clock\r\ndiff --git a/flow/scripts/cts.tcl b/flow/scripts/cts.tcl\r\nindex 0b7c56b8..2c0c6fef 100644\r\n--- a/flow/scripts/cts.tcl\r\n+++ b/flow/scripts/cts.tcl\r\n@@ -45,6 +45,8 @@ estimate_parasitics -placement\r\n report_metrics \"cts pre-repair\"\r\n utl::pop_metrics_stage\r\n \r\n+write_db $::env(RESULTS_DIR)/4_1_cts_pre_repair.odb\r\n+\r\n repair_clock_nets\r\n \r\n utl::push_metrics_stage \"cts__{}__post_repair\"\r\n```\r\n"}, {"user": "`make gui_cts` ctrl-f and searching for instance `*hold*` is helpful. :-)\r\n\r\nFrom there I can go to the buffer tree, then find the endpoints.\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/bcfc601b-55b6-4a91-aa4c-e58f630c647e)\r\n"}, {"assistant": "Various useful patterns at https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/2734e98ee7c0f6888a686c2ef2445c0bb837ed0f/flow/scripts/save_images.tcl#L59"}]} +{"messages": [{"user": "If I try to bump mock-array frequency from 8000ps to 1000ps, I get detailed placement errors.\r\n\r\nHow do I find out which nets detailed placement is failing for?\r\n\r\n```\r\n[INFO DPL-0035] hold7527\r\n[INFO DPL-0035] hold7527\r\n[INFO DPL-0035] hold19172\r\n[INFO DPL-0035] hold33345\r\n[INFO DPL-0035] hold33345\r\n[INFO DPL-0035] hold33346\r\n[INFO DPL-0035] hold1805\r\n[INFO DPL-0035] hold19173\r\n[INFO DPL-0035] hold7528\r\n[INFO DPL-0035] input2044\r\n[ERROR DPL-0036] Detailed placement failed.\r\nError: cts.tcl, 90 DPL-0036\r\nCommand exited with non-zero status 1\r\nElapsed time: 1:53.31[h:]min:sec. CPU time: user 113.09 sys 0.19 (99%). Peak memory: 792296KB.\r\nmake: *** [Makefile:579: results/asap7/mock-array/base/4_1_cts.odb] Error 1\r\n```\r\n"}, {"user": "Change I tried:\r\n\r\n```\r\n$ git show\r\ncommit be3fd43658747fa25b16fd7fb7317a36e92d7362 (HEAD)\r\nAuthor: \u00d8yvind Harboe \r\nDate: Tue Jul 11 09:01:30 2023 +0200\r\n\r\n mock-array: reduce clock period to 1000ps from 8000ps\r\n \r\n Signed-off-by: \u00d8yvind Harboe \r\n\r\ndiff --git a/flow/designs/asap7/mock-array/Element/constraints.sdc b/flow/designs/asap7/mock-array/Element/constraints.sdc\r\nindex 1d817bb8..0a66e62e 100644\r\n--- a/flow/designs/asap7/mock-array/Element/constraints.sdc\r\n+++ b/flow/designs/asap7/mock-array/Element/constraints.sdc\r\n@@ -4,7 +4,7 @@ set cols [expr {[info exists ::env(MOCK_ARRAY_COLS)] ? $::env(MOCK_ARRAY_COLS) :\r\n \r\n set clk_name clock\r\n set clk_port_name clock\r\n-set clk_period 8000\r\n+set clk_period 1000\r\n \r\n set clk_port [get_ports $clk_port_name]\r\n create_clock -period $clk_period -waveform [list 0 [expr $clk_period / 2]] -name $clk_name $clk_port\r\ndiff --git a/flow/designs/asap7/mock-array/constraints.sdc b/flow/designs/asap7/mock-array/constraints.sdc\r\nindex ad66e12c..7370cc7f 100644\r\n--- a/flow/designs/asap7/mock-array/constraints.sdc\r\n+++ b/flow/designs/asap7/mock-array/constraints.sdc\r\n@@ -1,6 +1,6 @@\r\n set sdc_version 2.0\r\n \r\n-set clk_period 8000\r\n+set clk_period 1000\r\n create_clock [get_ports clock] -period $clk_period -waveform [list 0 [expr $clk_period/2]]\r\n \r\n set clk_name clock\r\n```\r\n"}, {"assistant": "Was this after the abutment PR? If so you should retry again after https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1221 as that opens up rows in the core."}]} +{"messages": [{"user": "Using https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1211 and https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1212, I've plotted detailed routing times for the same Verilog 8x8 8 bit datapath mock-array, changing only the size of the element macros.\r\n\r\nAny thoughts on these running times for the mock-array for detailed routing? Expected? Unexpected?\r\n\r\nThe algorithm seems to be MUCH faster for smaller areas\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c2e92b32-302f-4ac5-9381-1178c6520b76)\r\n\r\n\r\nBiggest array:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/a7ca8cb1-030d-488a-99c7-c80809e46529)\r\n\r\nThe element-element wires are not straight, lots of little deviations from horizontal/vertical:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/67bb32ef-cd99-4369-bd27-becaabd73e8d)\r\n\r\nSmallest array:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/8b5ce6e6-c647-4623-9fa9-26420ec0d7a8)\r\n\r\n\r\n\"All\" element to element wires are horizontal/vertical (didn't check exhaustively):\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/4e3f7f0e-ae10-451e-bb61-a012a48c28bd)\r\n\r\n"}, {"assistant": "How do the number of routing iterations and iter0 DRCs compare between datapoints? "}, {"user": "I wasn't able to follow up on this in a timely manner."}]} +{"messages": [{"user": "I've been fixing some problems in mock-array in positioning of macros and pins not being aligned and now things are working well.\r\n\r\nHowever, I found this curious thing when inspecting, a detailed routing loop :-)\r\n\r\nI don't see any reason why a horizontal wire wouldn't work here...\r\n\r\nAny ideas or insights?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/381a3158-6635-452c-a270-247df28a6dae)\r\n\r\n\r\nThe above can be found if creating a `flow/settings.mk` file:\r\n\r\n```\r\nexport DESIGN_CONFIG?=designs/asap7/mock-array/config.mk\r\nexport MOCK_ARRAY_DATAWIDTH?=8\r\nexport MOCK_ARRAY_TABLE?=8 8 4 4 5 5\r\nexport MOCK_ARRAY_SCALE?=80\r\n```\r\n\r\nand running `make verilog` and `make`\r\n\r\n\r\nVarious interesting things can be seen in detailed routing:\r\n\r\n- almost all the wires are vertical/horizontal between \"Element\" macros. The loop above is untypical, usually it's just a slight horizontal/vertical deviation.\r\n- there are hold cells in the middle to the right\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/e9bca2da-5e41-4ee6-b279-e7ca375bb26a)\r\n\r\n\r\n\r\nHold cells have to be placed *outside* to the right of the array, hence many non-vertical vertical wires between those two elements.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/3a17be46-8604-498c-901f-ce375cbed5cc)\r\n"}, {"assistant": "@osamahammad21 any thoughts on the loop?"}, {"user": "A feature request filed: https://github.com/The-OpenROAD-Project/OpenROAD/issues/3634"}]} +{"messages": [{"user": "Using https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1211 and executing `python util/plot-running-times.py`, I've plotted some running times against area:\r\n\r\n`6_report` running time in seconds below. Note that the x axis is um^2, but that it is multiplied by 1e6 (as can be seen in the lower right corner).\r\n\r\nAs can be seen, the running time is worse than proportional to area and I imagine that there could be some low hanging fruit as I would expect reporting not to be on the order of detailed routing times.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/499880aa-0e07-4772-9e10-73dddcf9ef51)\r\n\r\n\r\n```\r\ncat /proc/cpuinfo | grep processor | wc -l \r\n12\r\n```"}, {"user": "Same for `2_6_pdn`, here running time is proportional to area:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/12bf57a3-9670-47d3-a19e-98c35f023ac1)\r\n"}, {"user": "`5_2_TritonRoute` running times are misleading as there's some sort of problem with DRC errors #3592\r\n\r\nHowever, since I have the data, I include the plot here anyway.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/80e6d705-994a-408d-9847-461b75cfaa37)\r\n"}, {"user": "A feature request has been filed to improve reporting times #3599"}]} +{"messages": [{"user": "After 64 iterations DRT stopped on my design a generated a DRC report. It turns out that most of the DRC are related to METAL1 spacing (with net VSS) and Metal SpacingTableTw. The design is not very congested so I wonder why the tool could not fix these rules. Could it be that I am missing something here (maybe something in my platform definition)? Is there a way to fix these violations? \r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/56942214/af73acfe-92fb-4590-baaf-31be8548e95e)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/56942214/4ed7f795-fef7-4d49-9f78-76b85c9cae37)\r\n\r\n"}, {"assistant": "Can you provide a test case? "}, {"assistant": "You have very wide METAL1 power stripes:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/ec146977-bcb3-4725-8140-4bef3c0137ef)\r\n\r\nThe pin is less than the min space (0.19 < 0.23) from the stripe so there is always going to be a DRC error here. You need to adjust your PDN definition to be resolve this."}]} +{"messages": [{"user": "Is there a simple way to see design ports information in hierarchy browser? Right now the only way I found is to go through the inspector and click on the Bterms of top level module. I had hope that in the hierarchy browser, besides leaf instances entries there would be something like ports\r\n```\r\n\r\n Ports\r\n Inputs\r\n Outputs\r\n IO\r\n Leaf instances\r\n Buffer/inverter\r\n Sequential\r\n Combinational\r\n ```"}, {"assistant": "@gadfort any thoughts? "}]} +{"messages": [{"user": "Hi, guys\r\n\r\nAfter reading the paper and browsing the source codes, I cannot figure out which parts of the codes reflect the local density penalty described in the paper, could you please suggest where can I find that in the implementation?\r\n\r\nThanks a lot for the nice work.\r\n\r\nBo"}, {"assistant": "@mgwoo can you answer this?"}, {"assistant": "A method related density computation seems to be removed in the CL https://github.com/The-OpenROAD-Project/OpenROAD/commit/0f82f83049733938c2fb5d6141b291409aa4678f , in which the original design calls updateDensityForceBin inside NesterovPlace::doNesterovPlace. (not sure if this can be related)\r\n\r\n@ahmadelrouby could you help understand the changes? thanks"}, {"assistant": "I didn't decipher the local density features because of unstable issues. \r\nPlease check the standalone repo for the local density calculation: https://github.com/The-OpenROAD-Project/RePlAce/blob/7c07cffdf419c4dbd315c73c235ec5d670fb0240/src/ns.cpp#L1011"}]} +{"messages": [{"user": "Excuse me, I'm installing the OpenDB(https://github.com/The-OpenROAD-Project/OpenDB), following the installation guide like this:\r\n```\r\ngit clone https://github.com/The-OpenROAD-Project/OpenDB.git \r\ncd OpenDB \r\nmkdir build\r\ncd build\r\ncmake ..\r\nmake\r\n```\r\n\r\nBut I met some problem when executing `cmake..`:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/39954153/054e75ce-9e89-4443-887a-0a81cb99b912)\r\nDoes anyone knows how to handle this problem?\r\n"}, {"assistant": "You need to install spdlog. The standalone OpenDB is not getting active development if that matters. Changes are made to the integrated version in OpenRoad."}]} +{"messages": [{"user": "Is https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/upf a work in progress (it doesn't have documentation). If it is, is it planned to have it supported? "}, {"assistant": "UPF support is a work in progress. The reader in upf/ works but the rest of the tool needs to support it."}]} +{"messages": [{"user": "I recall seeing commit relating to Hierarchical DEF views. Is it something currently, or planned to be, supported in OpenROAD now? "}, {"assistant": "> I recall seeing commit relating to Hierarchical DEF views. Is it something currently, or planned to be, supported in OpenROAD now?\r\n\r\nLike this?\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/issues/1176#issuecomment-1605301917\r\n"}]} +{"messages": [{"user": "make route\r\nfailed:\r\n[ERROR GRT-0119] Routing congestion too high. Check the congestion heatmap in the GUI and load ./reports/nangate45/gcd/base/congestion.rpt in the DRC viewer.\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/131429249/5d9762ec-a99c-4c9a-8276-554859a25148)\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/131429249/091f5f59-b368-4678-9be4-306a0f37beed)\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/131429249/a51f6252-73b0-496c-8af2-0ca00dce52ed)\r\n\r\n\r\n\r\n**During the routing phase, congestion occurs. Upon checking the Design Rule Check (DRC) report, I noticed that the congestion is occurring within the module itself. This is expected because there are several obstruction (obs) regions in that area, and congestion is normal when attempting to route in such congested areas. However, ABC_GPIO should be treated as an independent module where internal routing is not necessary. It should only require connections from its pins to other modules. Why is this issue occurring?**\r\n\r\nIn my own design, I made the following additions:\r\n\r\ntcl file:\r\nplace_pad -master ABC_GPIO -row IO_SOUTH -location 420 {U_GPIOA_2}\r\n\r\nv file:\r\n ABC_GPIO U_GPIOA_2 (\r\n .C(reset_io ),\r\n .I(1'b0 ),\r\n .IE(1'b1 ),\r\n .OEN(1'b1 ),\r\n .PAD(reset_pad )\r\n );\r\n\r\nlef file:\r\nMACRO ABC_GPIO\r\n CLASS PAD ;\r\n FOREIGN ABC_GPIO 0.000 0.000 ;\r\n ORIGIN 0.000 0.000 ;\r\n SIZE 30.000 BY 177.000 ;\r\n SYMMETRY R90 ;\r\n SITE IOSite ;\r\n PIN IE\r\n DIRECTION INPUT ;\r\n PORT\r\n LAYER M5 ;\r\n RECT 19.095 176.460 21.055 177.000 ;\r\n LAYER M4 ;\r\n RECT 19.095 176.460 21.055 177.000 ;\r\n LAYER M3 ;\r\n RECT 19.095 176.460 21.055 177.000 ;\r\n LAYER M2 ;\r\n RECT 19.095 176.460 21.055 177.000 ;\r\n RECT 19.780 170.220 19.900 177.000 ;\r\n RECT 18.905 170.220 19.900 170.340 ;\r\n LAYER M1 ;\r\n RECT 19.095 176.460 21.055 177.000 ;\r\n END\r\n AntennaGateArea 1 ;\r\n AntennaDiffArea 0.590 ;\r\n END IE\r\n PIN C\r\n DIRECTION OUTPUT ;\r\n PORT\r\n LAYER M5 ;\r\n RECT 26.860 176.460 28.820 177.000 ;\r\n LAYER M4 ;\r\n RECT 26.860 176.460 28.820 177.000 ;\r\n LAYER M3 ;\r\n RECT 26.860 176.460 28.820 177.000 ;\r\n LAYER M2 ;\r\n RECT 26.860 176.460 28.820 177.000 ;\r\n ***************\r\n RECT 21.790 170.505 21.910 172.690 ;\r\n LAYER M1 ;\r\n RECT 26.860 176.460 28.820 177.000 ;\r\n END\r\n AntennaGateArea 0 ;\r\n AntennaDiffArea 0.590 ;\r\n END C\r\n PIN I\r\n DIRECTION INPUT ;\r\n PORT\r\n LAYER M5 ;\r\n RECT 1.180 176.460 3.140 177.000 ;\r\n LAYER M4 ;\r\n RECT 1.180 176.460 3.140 177.000 ;\r\n LAYER M3 ;\r\n RECT 1.180 176.460 3.140 177.000 ;\r\n LAYER M2 ;\r\n RECT 5.440 170.210 5.720 170.330 ;\r\n ********************\r\n RECT 2.080 170.210 2.200 177.000 ;\r\n LAYER M1 ;\r\n RECT 1.180 176.460 3.140 177.000 ;\r\n END\r\n AntennaGateArea 0.5 ;\r\n AntennaDiffArea 0.590 ;\r\n END I\r\n PIN PAD\r\n DIRECTION INOUT ;\r\n PORT\r\n LAYER TM2 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER TM1 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER M7 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER M6 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER M5 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER M4 ;\r\n RECT 2.000 0.000 28.000 3.000 ;\r\n LAYER M3 ;\r\n RECT 25.125 106.150 27.475 136.480 ;\r\n *************\r\n RECT 2.525 106.130 4.845 136.490 ;\r\n LAYER M2 ;\r\n RECT 25.125 106.150 27.475 136.480 ;\r\n ************\r\n RECT 2.525 106.130 4.845 136.490 ;\r\n END\r\n END PAD\r\n PIN OEN\r\n DIRECTION INPUT ;\r\n PORT\r\n LAYER M5 ;\r\n RECT 4.500 176.460 6.460 177.000 ;\r\n LAYER M4 ;\r\n RECT 4.500 176.460 6.460 177.000 ;\r\n LAYER M3 ;\r\n RECT 4.500 176.460 6.460 177.000 ;\r\n LAYER M2 ;\r\n RECT 4.500 176.460 6.460 177.000 ;\r\n RECT 3.910 170.210 5.300 170.330 ;\r\n RECT 4.680 170.210 4.800 177.000 ;\r\n LAYER M1 ;\r\n RECT 4.500 176.460 6.460 177.000 ;\r\n END\r\n AntennaGateArea 0.4 ;\r\n AntennaDiffArea 0.590 ;\r\n END OEN\r\n OBS \r\n LAYER TM2 ;\r\n RECT 0.000 0.000 1.290 177.000 ;\r\n RECT 28.710 0.000 30.000 177.000 ;\r\n RECT 0.000 3.710 30.000 177.000 ;\r\n LAYER TV2 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER M7 ;\r\n RECT 0.000 0.000 1.415 177.000 ;\r\n RECT 28.585 0.000 30.000 177.000 ;\r\n RECT 0.000 3.585 30.000 177.000 ;\r\n LAYER M6 ;\r\n RECT 0.000 0.000 1.415 177.000 ;\r\n RECT 28.585 0.000 30.000 177.000 ;\r\n RECT 0.000 3.585 30.000 177.000 ;\r\n LAYER TM1 ;\r\n RECT 0.000 0.000 1.270 177.000 ;\r\n RECT 28.730 0.000 30.000 177.000 ;\r\n RECT 0.000 3.730 30.000 177.000 ;\r\n LAYER M5 ;\r\n RECT 0.000 0.000 1.415 175.875 ;\r\n *************\r\n RECT 29.405 0.000 30.000 177.000 ;\r\n LAYER M4 ;\r\n RECT 0.000 0.000 1.415 175.875 ;\r\n ***************\r\n RECT 29.405 0.000 30.000 177.000 ;\r\n LAYER M3 ;\r\n RECT 1.150 108.100 1.955 136.480 ;\r\n *****************\r\n RECT 26.815 0.000 30.000 95.235 ;\r\n LAYER V6 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER V5 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER V4 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER TV1 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER V3 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER V2 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n LAYER M2 ;\r\n RECT 1.350 170.210 1.630 170.330 ;\r\n ****************\r\n RECT 29.405 173.275 30.000 177.000 ;\r\n LAYER M1 ;\r\n RECT 0.000 0.000 30.000 175.875 ;\r\n RECT 0.000 0.000 0.595 177.000 ;\r\n RECT 3.725 0.000 3.915 177.000 ;\r\n RECT 7.045 0.000 18.510 177.000 ;\r\n RECT 21.640 0.000 26.275 177.000 ;\r\n RECT 29.405 0.000 30.000 177.000 ;\r\n LAYER V1 ;\r\n RECT 0.000 0.000 30.000 177.000 ;\r\n END \r\nEND ABC_GPIO\r\n"}, {"assistant": "This is an issue, not a discussion, and needs to have a test case attached."}]} +{"messages": [{"user": "There has been a lot of activity concerning build errors, but I tried with latest master merged with #3512\r\n\r\nIs it enough to update to latest master or do I need to purge something or other locally?\r\n\r\n```\r\n./build_openroad.sh --local --openroad-args \"-DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_CXX_FLAGS=-g\"\r\n```\r\n\r\n```\r\n[ 25%] Building CXX object src/odb/test/cpp/CMakeFiles/TestGuide.dir/TestGuide.cpp.o\r\n/home/oyvind/OpenROAD-flow-scripts/tools/OpenROAD/src/odb/test/cpp/TestAbstractLef.cc:13:10: fatal error: gmock/gmock.h: No such file or directory\r\n 13 | #include \"gmock/gmock.h\"\r\n | ^~~~~~~~~~~~~~~\r\ncompilation terminated.\r\ngmake[2]: *** [src/odb/test/cpp/CMakeFiles/OdbGTests.dir/build.make:90: src/odb/test/cpp/CMakeFiles/OdbGTests.dir/TestAbstractLef.cc.o] Error 1\r\ngmake[1]: *** [CMakeFiles/Makefile2:2331: src/odb/test/cpp/CMakeFiles/OdbGTests.dir/all] Error 2\r\ngmake[1]: *** Waiting for unfinished jobs...\r\n```\r\n"}, {"assistant": "This ones my bad. It seems that some installations of libgtest-dev don't include google mock. If you uninstall your system gtest it will fix this error, but I'll see if there's something else we could do to fix this."}, {"assistant": "Fixed on #3514 "}]} +{"messages": [{"user": "[ 12%] Building abc/abc-bafd2a7\r\nDebug: ABCREV=bafd2a7\r\n[ 22%] Building passes/techmap/filterlib.o\r\n[ 22%] Building yosys-smtbmc\r\nERROR: ABC contains local modifications! Set ABCREV=default in Yosys Makefile!\r\nmake: *** [Makefile:749: abc/abc-bafd2a7] Error 1\r\n\r\nin Centos, I have set ABCREV = default, but the debug info is bafd2a7\r\n"}, {"assistant": "Is this installation issue?\r\nCan you provide steps to reproduce the same?"}, {"assistant": "@Simonliudan, this looks more like an issue than a discussion. Please file an Issue and follow the Issue template, the template give us important information to help you."}]} +{"messages": [{"user": "I have been wondering if there is a flow that allows the connection between OR or ORFS and be able to use the synthesized/placed .def files to be used as an input for the Deep Reinforcement Learning placement algorithm created by Google (Circuit Training)?"}, {"assistant": "I don't know of such a flow but I think you could build one."}]} +{"messages": [{"user": "Hello! I would like to ask a question about the connection between OR and ORFS. Does ORFS contain an OR app? What is the difference between OR and ORFS apart from the fact that the latest one also contains Yosys and can create a gds file, i.e. provides the entire RTL-GDSII flow. I understand that ORFS contains ready-made scripts to run the flow and only need to set some variables, but what are the global differences?\r\nAlso, I asked a question about ORFS features. I was interested in the possibility of multi-corner analysis. I was told that only OR can be configured for such analysis. Unfortunately, I haven't found a clear answer to my question in the documentation, could you please tell me how to do it or where I can find information.\r\n\r\nThank you for responding!"}, {"assistant": "OR is the application. ORFS is a flow that runs yosys, OR, and klayout to implement a design.\r\n\r\nYou can find the STA manual at https://github.com/The-OpenROAD-Project/OpenSTA/blob/master/doc/OpenSTA.pdf. OpenLane uses multi-corner analysis and can also serve as an example."}]} +{"messages": [{"user": "I am opening this discussion to record some properties that were not included in the dbTech and dbBlock inspection implemented in #3458 and to make it easier to make future questions related to these properties.\r\n\r\nAs @maliberty did not want to overload the PR, I left out some of the properties that @gadfort asked to include in the inspection. The ones I did not implement are the ones available through the following methods:\r\n\r\ndbBlock:\r\n`getTopModule()`\r\n`getChildren()`\r\n`getVias()`\r\n\r\ndbTech:\r\n`getViaRules()`"}, {"user": "@maliberty I am working in the remaining properties and I have the following doubt:\r\n\r\nAccording to db.h, A TechViaLayerRule is the element that represents a LEF VIARULE LAYER.\r\n\r\nThe type dbTechViaLayerRule has methods such as:\r\n`bool hasEnclosure();`\r\n`void getEnclosure(int& overhang1, int& overhang2);`\r\n`bool hasOverhang();`\r\n`int getOverhang();`\r\n`...`\r\n\r\n\r\nBut in the LEF/DEF reference the VIARULE LAYER can have only a WIDTH range and a DIRECTION. Dummy example:\r\n```\r\nVIARULE Via1Array-0\r\n LAYER via1 ;\r\n DIRECTION HORIZONTAL ;\r\n WIDTH 0.035 TO 0.035 ;\r\n LAYER via2 ;\r\n DIRECTION VERTICAL ;\r\n WIDTH 0.035 TO 0.035 ;\r\n VIA via1_0 ;\r\n VIA via1_1 ;\r\nEND Via1Array-0\r\n```\r\n\r\nSo are these other methods correct? When inspecting a TechViaLayerRule just the WIDTH and DIRECTION should appear?"}]} +{"messages": [{"user": "I have a timing path in the OpenROAD GUI that I want to understand.\r\n\r\nHow can I go from the timing report in the GUI to the Verilog?"}, {"assistant": "https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1129 should help with naming once merged.\r\n\r\nThere is no direct link today so you'll have to work back from the names. @QuantamHD has some work to store line numbers that is hopefully going to land but has been tied up in OSS licensing issues."}, {"user": "@maliberty Here is an example of how it is hard to get from the static timing report to the Verilog:\r\n\r\nBuild the design with ` make DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk`, then look at the Element `make DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk gui_final`.\r\n\r\nHow, in general, do I find my way to the Verilog code?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/840713c0-f33a-484f-b156-9a79e4aad50d)\r\n\r\n\r\n"}, {"assistant": "If you use the rename PR I mentioned then the register should have a name matching the Element.v to some degree. Does that work here?"}, {"user": "What I've heard is that tracking from timing reports back to RTL is an \"unsolved problem in EDA tools\", so https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1129 is probably as good as it gets for now.\r\n\r\nTo go beyond this, I suppose Yosys has to grow some sophistication w.r.t. tracking back to the original Verilog.\r\n\r\nOne of the goals of https://circt.llvm.org/ is to provide an improved infrastructure for RTL as it goes through a number of tools in a flow. Perhaps, one day, yosys will support https://circt.llvm.org/. Ideally this would give Yosys more input languages and better \"debug information\" through synthesis and technology mapping..."}]} +{"messages": [{"user": "I have `USE_FILL = NO` and I still see that the `density_fill.tcl` script is run and it result into the following error \r\n```\r\n[ERROR STA-0511] cannot open './results/myplatform/mydesign/base/5_route.sdc'.\r\nError: density_fill.tcl, 2 STA-0511\r\nCommand exited with non-zero status 1\r\n```\r\nThere is no other info in the log that could help me figure out what is going on.\r\nIs there a way to temporarily disable this step? "}, {"assistant": "The check is\r\n```\r\nifneq ($(USE_FILL),)\r\n```\r\nso set it to nothing rather than NO"}]} +{"messages": [{"user": "Hello! I have a few questions about ORFS capabilities.\r\n\r\n1)\tDoes OpenROAD support libraries with CCS driver model?\r\n2)\tIs incremental flow supported?\r\n3)\tDoes OpenSTA in OpenROAD support all sdc commands?\r\n4)\tIs SystemVerilog support limited to the constructs that Yosys supports?\r\n5)\tDoes OpenROAD do only DRC analysis or also DRV and DFM? Of the DFM analysis I have only seen an antenna rule check.\r\n6)\tDoes OpenROAD provide corner-based optimisation, or it can only show us the characteristics, like wns, for different corners?\r\n7)\tAre OCVs supported?\r\n8)\tDoes OpenROAD support crosstalk delay/noise analysis?\r\n\r\nThank you for your answers!"}, {"assistant": "> Hello! I have a few questions about ORFS capabilities.\r\n> \r\n> 1. Does OpenROAD support libraries with CCS driver model?\r\n\r\nOnly NLDM is currently supported but CCS is under development.\r\n\r\n> 2. Is incremental flow supported?\r\n\r\nThat can have a lot of meanings. We do support restarting the flow at a given step.\r\n\r\n> 3. Does OpenSTA in OpenROAD support all sdc commands?\r\n\r\nYes afaik but be careful that there are many proprietary commands that are not in SDC.\r\n\r\n> 4. Is SystemVerilog support limited to the constructs that Yosys supports?\r\n\r\nYes. The is the surelog plugin that has a good amount of SV support\r\n\r\n> 5. Does OpenROAD do only DRC analysis or also DRV and DFM? Of the DFM analysis I have only seen an antenna rule check.\r\n\r\nOR does max slew/cap/fanout if that's what you mean by DRV. There is no DFM.\r\n\r\n> 6. Does OpenROAD provide corner-based optimisation, or it can only show us the characteristics, like wns, for different corners?\r\n\r\nOR can be setup for multi-corner analysis. ORFS doesn't take advantage of that today.\r\n\r\n> 7. Are OCVs supported?\r\n\r\nYes but see 6\r\n\r\n> 8. Does OpenROAD support crosstalk delay/noise analysis?\r\n\r\nNo. Once we have CCS for delay it would be natural to tackle this next.\r\n\r\n> \r\n> Thank you for your answers!\r\n\r\n"}, {"assistant": "> @dralabeing. Should we curate this and ask Jack to add it to OR and ORFS FAQs?\r\n\r\nYes, this is a good idea. Let's add this to the FAQs"}]} +{"messages": [{"user": "I would like to temporarily suppress some warnings like `[WARNING STA-0122]`. Is there a way to do that? Is there a place to look for the full meaning of warnings and error messages? Some of them are cryptic. "}, {"assistant": "There is no suppression mechanism. There is no catalog of messages though you can always look at the source code to get more ideas. Is there a particular message that you are finding cryptic?"}, {"assistant": "I forgot we had that. I wrote it with unit tests in mind but I guess it works here too."}]} +{"messages": [{"user": "Hello! I need to calculate per-lenght capacitance for \"set_layer_rc\" in setRC.tcl. It doesn't present at PDK and I am trying to calculate it from the data presented at tech.lef file. Can someone describe me how can I do it?"}, {"assistant": "Refer sky130hd [setRC.tcl](https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/master/flow/platforms/sky130hd/setRC.tcl).\r\nRefer the document [here](https://github.com/The-OpenROAD-Project/OpenROAD/blob/2f3991101c2414dac9040684a822f16fe19e825f/src/rsz/README.md?plain=1#L32)"}]} +{"messages": [{"user": "I'm running OpenROAD v2.0-8374-g5235ee26c, but I can't find the endpoint slack histogram. I thought it would be in the Windows menu...\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/pull/3344\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/d979d815-5fee-4951-b4c4-dfb58c45e7a7)\r\n"}, {"assistant": "Do you have Qt5 charts installed? Your CMake log should have:\r\n```\r\n-- Charts widget is enabled\r\n```\r\nIt requires a new optional dependency. On Ubuntu you should be able to do `apt install libqt5charts5-dev`."}, {"user": "Very cool!\r\n\r\nSome nits:\r\n\r\nNo legend on horizontal axis and I have to undock it and increase the size to see what's going on(no numbers visible when it is a tiny chartlet in the default position).\r\n\r\nAlso, I think the scripting window could leave space for the vertical column where the timing report is, instead of taking the full width of the window.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/cbe9a37a-0eba-4cf6-8e5d-df51c58e2457)\r\n"}]} +{"messages": [{"user": "I'm interested in selecting all nets in `make gui_place` to see if there are any pathological routes. A pathological route in my case can be if buffers are placed in the wrong location. I have vertical/horizontal routes and a buffer must be placed between the macros, not outside of them. Example from mock-array-big below.\r\n\r\nIf I select \"*\", I get a solid yellow...\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/c7648a88-4509-4514-ad56-581cc41df938)\r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/fe5ffbab-125b-4609-bebf-123140995bdd)\r\n"}, {"assistant": "You can use Windows -> Selected/Highlighted Shapes and in the window you can deselect VDD & VSS."}]} +{"messages": [{"user": "I'm doing some quick tests using the scripts in OpenROAD/test to build a design. Using those, I get a surprisingly low utilization, around 50%. Playing around a bit, I realized that decreasing global_place_pad gave me a lot more reasonable results. My question now is if I'm allowed to change that, or if that is a property defined by the PDK and should be left as is. And am I supposed to use the flow script in OpenROAD/test at all, or is that for a particular example? I found that script to be the most self-contained and easiest to extend compared to e.g. ORFS or OpenLANE that relies on a lot of environment variables and custom Python scripts."}, {"assistant": "You can change it but you might want to start with global_place_density which is the target density.\r\n\r\nNote that flow.tcl is for testing and a more complete flow is in ORFS. If it meets your needs that's ok but it isn't our recommended production flow."}]} +{"messages": [{"user": "How can I trace global routing congestion to the net that is causing the problem?\r\n\r\nI have routing congestion on top of my macro, but I'm struggling to find out which net is causing the problem.\r\n\r\nI *think* the problem is that some pin is on the wrong side of the macro and that a net is being routed around the macro.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/29c9571b-1fe1-48a0-b70c-b73b151f7d3f)\r\n\r\nClicking on the routing congestion doesn't leave me with much of a clue to track down the net that is causing the problem:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/8b060f66-f907-4707-8841-9772ffa5f7a5)\r\n"}, {"assistant": "Short term I would select all nets and see if you can spot the one crossing the macro. Then go to one end and see what pin it is coming from\r\n\r\n@eder-matheus @luis201420 can we add the set of nets in the gcell to the congestion marker?"}, {"user": "Some tips and some ideas for new features to improve this experience, so I think this is answered."}]} +{"messages": [{"user": "when read_def I have this error. I don't know how to fix it.\r\n[WARNING ODB-0126] error: TECHNOLOGY is unsupported\r\nERROR (DEFPARS-6010): An error has been reported in callback. Error in file /home/qjj/CodeFile/OpenROAD/qjj/test/threestage/ThreeStage_4cbe5670900884f3.def at line 5, on token ;.\r\nUpdate the def file before parsing the file again.\r\n\r\n[ThreeStage_def.zip](https://github.com/The-OpenROAD-Project/OpenROAD/files/11600994/ThreeStage_def.zip)\r\n"}, {"assistant": "This should have been opened as an issue with the full set of data. I believe you are on an old version of OR as the current message is a warning \"TECHNOLOGY is ignored\". If you see the same with the head of master please open an issue."}]} +{"messages": [{"user": "I would have expected the placement heatmap to extend to the top and to the right, but it seems like the heatmap stops at the grey area to the top and right...\r\n\r\nIs OpenROAD doing the expected thing here? If yes, what is the grey area?\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/5bcf1742-f124-41d4-a28e-05daf9fdfcf8)\r\n\r\nThe routing heatmap extends to the top and to the right, as I expected:\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/b99e0e03-55d6-4e1a-b5dc-a58708830736)\r\n\r\nThe DRC errors are routing congestion, not relevant to the question above, but it is what I was working on when I discovered the placement heatmap oddity. I think I need to run gui_cts and track down the buffer trees to see what is going on w.r.t routing concestion, though I think the pins could be spaced out and centered in the macro by the looks of it."}, {"assistant": "The gray area is 0, and isn't strictly gray, it just looks that way since you have instance outlines on. Zero is a fully transparent box.\r\n\r\nYou get zero when an area is only filler/physical cells"}]} +{"messages": [{"user": "Did the psm module refer to any academic research? If so, it would be better to cite the paper for us to learn the ir-solver and make some improvement. If not, any recommendation for freshmen to understand the whole ir-drop thing? Appreciate it!"}, {"assistant": "@Pzy-ss \r\nHave you referred [this](https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/psm)?\r\nhttps://theopenroadproject.org/an-ml-based-iccad-contest-for-static-ir-drop-estimation/"}, {"assistant": "@VidyaChhabria is the author - would you comment."}, {"assistant": "@VidyaChhabria provided the doc in #3405 "}, {"assistant": "Look at PR: https://github.com/The-OpenROAD-Project/OpenROAD/pull/3428 should update the document to have the citations."}]} +{"messages": [{"user": "As the default flow, there is no coordinate information in `*CONN` following each `PORT` in the generated `6_final.spef`, which is not in coincidence with a normal SPEF format.\r\n\r\nE.g., no `*C` bolow,\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/8579640/488691da-2217-4dae-980b-da833f9bbf79)\r\n\r\n```\r\n...\r\n\r\n*CONN\r\n*I *572:B I *D sky130_fd_sc_hd__nand2_1\r\n*I *571:Y O *D sky130_fd_sc_hd__nand2_1\r\n\r\n...\r\n```\r\n\r\nCompared with another example in a book,\r\n\r\n```\r\n*D_NET *5423 2.69358 \r\n\r\n*CONN \r\n*I *14207:D I *C 21.7450 94.3150 \r\n*I *14205:D I *C 21.7450 90.4900 \r\n*I *14211:Q O *C 21.4900 83.8800 *D DFFQX1 \r\n\r\n*CAP \r\n1 *5423:10107 *547:12722 0.202686 \r\n2 *5423:10107 *5116:10594 0.104195\r\n\r\n....\r\n```\r\n\r\n\r\nAny boss help me?"}, {"assistant": "Coordinates are optional in spef so this is valid. There is code to generate coordinates but we've never used it. We could try enabling but I can't make any guarantees about what it will produce. Do you have a use model for these or are you just comparing to what a book shows?"}, {"assistant": "I've added a -coordinates option to write_spef in https://github.com/The-OpenROAD-Project/OpenROAD/pull/3434"}]} +{"messages": [{"user": "Hello\r\nWhen I check lvs for sky130hd/gcd, I have an error about cdl file. \r\n\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/134496656/49ad14ce-fa0c-408e-b0b4-37fa17d5a6d5)\r\n\r\nPlease help me to solve this problem!\r\n"}, {"assistant": "Please file an issue with a reproducible test case."}]} +{"messages": [{"user": "Just got the OpenROAD gui running natively on my machine and built the award-winning SERV, the world's smallest RISC-V CPU, with the tools.\r\n\r\nOne thing I always wanted to do is to colorize the cells according to the verilog module they came from so that I can get a visual of how much space each part of the design takes up. Is this possible to do with the GUI?"}, {"assistant": "You'll want the Hierarchy Browser:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/66b5d519-45e8-42a4-913e-f908e1f1cea8)\r\n\r\nAs you expand the hierarchy it will color the layout. A simple example with gcd:\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/761514/cdadd438-a011-490f-918e-c17e998912ab)\r\n"}]} +{"messages": [{"user": "Fastroute is a great global routing algorithm that can complete the routing of millions of two-pin nets in such a short time. However, after reading the Fastroute paper, it does not mention how the program allocates threads for the millions of two-pin nets. Does Fastroute divide all the two-pin nets into multiple portions and assign a thread to each portion? How are these threads synchronized to update the capacity of the whole global routing grid? Thank you!"}, {"assistant": "FR is not multi-threaded."}]} +{"messages": [{"user": "Hello,\r\nI am trying to integrate a FreePDK45 platform and get an error on global route stage:\r\n![\u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0435](https://github.com/The-OpenROAD-Project/OpenROAD/assets/131533616/9fe83ce2-8516-4796-b9da-9471ec1e6ca2)\r\n\r\nA FreePDK45 platform and Nangate45 are similar to each other, excepting tha geometry of standard cells (in FreePDK45 they are polygon). I am making config.mk based on Nangate45 config.mk.\r\nOpenROAD Flow version: v2.0-7988-g20b907452 \r\n\r\nHelp me please to solve this problem.\r\n\r\n[global_route_PWM_freepdk45nm_base_2023-05-23_00-37.tar.gz](https://github.com/The-OpenROAD-Project/OpenROAD/files/11537324/global_route_PWM_freepdk45nm_base_2023-05-23_00-37.tar.gz)\r\n"}, {"assistant": "A crash should be filed as an issue rather than a test case. I've opened https://github.com/The-OpenROAD-Project/OpenROAD/issues/3369"}]} +{"messages": [{"user": "I want to debug it, but I searched the code and couldn't find this error message in the source.\r\n\r\n```\r\n[INFO GPL-0003] SiteSize: 54 270\r\n[INFO GPL-0004] CoreAreaLxLy: 2160 2160\r\n[INFO GPL-0005] CoreAreaUxUy: 25922160 25922160\r\nError: tdms_place.tcl, 35 cannot create std::vector larger than max_size()\r\nCommand exited with non-zero status 1\r\n```\r\n"}, {"assistant": "My guess is this is an STL exception and not in the OR code. In gdb try 'catch throw' to see when it is being thrown."}, {"user": "This is odd... 48000*96000 = 4608000000. Ah. overflow.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/ca384a53-04da-42fd-9039-014b3bdd89f9)\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/a0156546-48aa-4c6c-84a1-ee9b89647226)\r\n\r\n\r\n```\r\nD$ git diff\r\ndiff --git a/src/gpl/src/placerBase.cpp b/src/gpl/src/placerBase.cpp\r\nindex 30ff82771..4f2c10b4e 100644\r\n--- a/src/gpl/src/placerBase.cpp\r\n+++ b/src/gpl/src/placerBase.cpp\r\n@@ -1002,8 +1002,8 @@ void PlacerBase::initInstsForUnusableSites()\r\n {\r\n dbSet rows = db_->getChip()->getBlock()->getRows();\r\n \r\n- int siteCountX = (die_.coreUx() - die_.coreLx()) / siteSizeX_;\r\n- int siteCountY = (die_.coreUy() - die_.coreLy()) / siteSizeY_;\r\n+ long siteCountX = (die_.coreUx() - die_.coreLx()) / siteSizeX_;\r\n+ long siteCountY = (die_.coreUy() - die_.coreLy()) / siteSizeY_;\r\n \r\n enum PlaceInfo\r\n {\r\n```\r\n\r\ngives me:\r\n\r\n```\r\n[INFO GPL-0002] DBU: 1000\r\n[INFO GPL-0003] SiteSize: 54 270\r\n[INFO GPL-0004] CoreAreaLxLy: 2160 2160\r\n[INFO GPL-0005] CoreAreaUxUy: 25922160 25922160\r\nError: out of memory.\r\n```"}]} +{"messages": [{"user": "I saw the conversation in #3330, #3342, #3348, etc. and started thinking about how the rendering time might be improved aside from not drawing objects that aren't useful.\r\n\r\nIt seems that the rendering, for the most part, is embarrassingly parallel. In `LayoutViewer::drawInstanceOutlines()` for example (the most expensive layer measured in #3348), a function is applied to every instance in a vector to determine how / if it gets drawn, and then it makes a draw call.\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/6920ac530b6959f742e75b7f55062b1642730b14/src/gui/src/layoutViewer.cpp#L2041-L2091\r\n\r\nThis is essentially a [map reduce](https://en.wikipedia.org/wiki/MapReduce) paradigm which should be extremely parallel, except that Qt painter objects aren't thread safe. There was discussion in #3279 that the database is not \"thread safe\", but I think that was in the context of read/write operations and not read-only operations.\r\n\r\nBeyond that, each layer is independently but sequentially rendered:\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/6920ac530b6959f742e75b7f55062b1642730b14/src/gui/src/layoutViewer.cpp#L2555-L2599\r\n\r\nThere may or may not be ordering required on draw calls to these layers, I'm not sure.\r\n\r\nI looked at a few [Qt guides](https://doc.qt.io/qt-5/qtcore-threads-mandelbrot-example.html) and they all recommend separating computation from rendering in separate threads for better performance (and interactivity).\r\n\r\nI think some of these things were mentioned by @QuantamHD in #1930 but the PR itself seems to be unrelated (and abandoned).\r\n\r\nI have some interest in looking into this, but I wonder what the best approach would be for this? Qt has [QThread](https://doc.qt.io/qt-5/qthread.html) and [QThreadPool](https://doc.qt.io/qt-5/qthreadpool.html) for this exact purpose. There's also [QtConcurrent](https://doc.qt.io/qt-5/qtconcurrent.html) which may have some uses.\r\n\r\nIn an ideal world, it seems like there should be a thread pool with `getThreadCount()-1` threads and the main thread. The main thread has a render queue which atomically pops the queue for draw calls and does nothing else until all worker threads yield. The worker threads can parallelize at the granularity of layer or instance/shape depending on what's optimal. But this could take a lot of refactoring, possibly be overkill, or possibly be difficult to tune the amount of threading correctly.\r\n\r\nAn intermediate step could be to simply parallelize some of the heavy-weight tasks that block the GUI thread, such as using `std::transform(std::execution::par)` or `std::for_each(std::execution::par)` and separating the draw calls from the filtering. But also these functions don't seem to be well supported on old versions of GCC/Clang (it requires Intel `libtbb` and may error or just use a serial version if it isn't linked, but I think it also think it doesn't work on Apple silicon). Maybe using OpenMP would work?\r\n\r\nAny thoughts or opinions?\r\n@gadfort @maliberty @oharboe @QuantamHD "}, {"assistant": "After the recent performance improvement, the biggest performance problem currently for us, is that all intermediate zoom levels are rendered https://github.com/The-OpenROAD-Project/OpenROAD/issues/3278\r\n\r\nSo if that could be fixed FIRST... :-)\r\n\r\nAfterwards, the suggestions that you propose sound wicked!\r\n\r\nIt is true that Qt nor the database is thread safe, then on the other hand, this means that the GUI is single threaded, so I suppose that you are right that you can use as many or few threads as you like as long as Qt nor the database functions are non-the-wiser. Rendering should be especially amenable to this since it is a read only operation...\r\n\r\nAlso, rendering doesn't have to be perfect. I have been thinking that a draft could be rendered while zooming and then when the user stops giving input, more detail can be rendered.\r\n"}, {"assistant": "@rovinski I've considered all these ideas but lack the time to implement them all. Right now I'm looking at moving the rendering to a separate thread and making it interruptible. The main challenge is figuring out how to trigger the right events at the right time to make Qt happy. It is very particular that you can only paint in paintEvent.\r\n\r\nAssuming I can land this then it is more straightforward to split that worker thread into multiple threads. KLayout works in a similar fashion where they render per layer in each thread and composite in the main thread."}]} +{"messages": [{"user": "@nerriav It looks like minimum pin distance is only availble globally for a macro, not per set_io_pin_constraint?\r\n\r\nhttps://openroad.readthedocs.io/en/latest/main/src/ppl/README.html\r\n\r\nWe would like pins to use the entire(initially) width/height of the macro edge to minimize contention at the top level where the macro is used. Currently we add extra horizontal distance in the example below to handle routing congestion at the top level. Routing congestion happens even with horizontal routes, because the horizontal routes will intersect a bit with the PDN.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/83012711-df0f-4b41-bdae-d05d3e3fbc8b)\r\n"}, {"assistant": "I don't understand what you are asking here. Are you talking about -corner_avoidance ?"}, {"user": "@nerriav discovered that `-region:*` and `-region:0-100` to is not identical if the regions is 100 wide. The pins are spread evenly when a range is specified (latter) and bunched together more closely if `*` is specified.\r\n\r\n@maliberty Is this intentional?"}]} +{"messages": [{"user": "There is no question here, just a demonstration of the use of the build time summary for a design that has one top level macro and 5 macros at the top level. What is being built here are mock abstracts for the macros at the top level as we are only interested in regression testing the top level on our build servers.\r\n\r\nThe top level is the slowest in detailed routing and we have 5 macros at the top level.\r\n\r\nWe are not currently building the macros at the top level in parallel, though we intend to, but it would only cut the running time by 50%.\r\n\r\n![image](https://github.com/The-OpenROAD-Project/OpenROAD/assets/2798822/4cf1cdad-6896-4d2f-9ad2-af2944e50761)\r\n\r\n\r\nThis is the command I run to build a summary of all the build times `find -regex ./logs/.*/base -type d -exec python3 util/genElapsedTime.py -d {} \\; | sort -hr -k2`\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\nStage | time/s\r\n-- | --\r\n5_2_TritonRoute | 21313\r\n5_2_TritonRoute | 7284\r\n5_2_TritonRoute | 4744\r\n5_2_TritonRoute | 2964\r\n5_2_TritonRoute | 1825\r\n5_2_TritonRoute | 1482\r\n3_3_place_gp | 1274\r\n4_1_cts | 1158\r\n3_3_place_gp | 666\r\n1_1_yosys | 617\r\n4_1_cts | 379\r\n6_report | 332\r\n3_3_place_gp | 312\r\n5_2_TritonRoute | 294\r\n3_5_opendp | 293\r\n1_1_yosys | 287\r\n5_2_TritonRoute | 282\r\n3_3_place_gp | 278\r\n4_1_cts | 273\r\n3_4_resizer | 224\r\n4_1_cts | 203\r\n5_1_fastroute | 198\r\n6_report | 164\r\n5_1_fastroute | 164\r\n1_1_yosys | 160\r\n5_1_fastroute | 142\r\n3_1_place_gp_skip_io | 132\r\n5_1_fastroute | 126\r\n3_4_resizer | 123\r\n6_report | 116\r\n3_5_opendp | 109\r\n... | ...\r\n\r\n\r\n\r\n\r\n\r\n"}, {"assistant": "That is average behaviour as drt is costly. It does scale pretty well with threads so more CPUs helps. We do have some work to do distributed drt if you want to test it out but it isn't in the flow currently due to the extra setup overhead."}, {"assistant": "How many threads in your data above?"}, {"user": "No question or suggestions here, just a datapoint that I thought it might have some value in sharing."}, {"assistant": "Fwiw we test with 40 cpus and I know Google often uses 96. We have tested with several hundred in distributed mode."}]} +{"messages": [{"user": "Currently OR CI is built with\r\n* Local centos7 gcc8\r\n* Local centos7 gcc8 without GUI\r\n* Docker centos7 gcc8\r\n* Docker ubuntu20.04 gcc9\r\n\r\nPRs additionally have GH actions that test:\r\n* macOS (x86)\r\n* c++20 (using clang-16)\r\n\r\nCentos7 is getting quite dated and I think it is time to replace it with a more modern distro. #3344 shows an example problem where qt5charts is not available in this older distro. I think Ubuntu 22 or Debian 11 are good contenders.\r\n\r\nI'd like community input as to what distro others are using with OR to help guide our choice. @antonblanchard @gadfort @QuantamHD @rovinski @msaligane @oharboe @donn @nayiri-k\r\n\r\nThe default compiler version would be updated to match the distro default.\r\n\r\nFYI @vvbandeira @tspyrou "}, {"assistant": "Google is on Debian test called [Glinux](https://en.wikipedia.org/wiki/GLinux). Ubuntu 22 or Debian 11 seem like reasonable choices to me.\r\n\r\nBut we use bazel to build everything from source so the biggest issue for me is if we start requiring very new versions of widely used libraries like Boost, because then I have to upgrade all of Google to use that version of software which can be a big pain.\r\n\r\nGoogle has a one version policy for any piece of software in the universe, and it's all stored in a monorepo."}, {"assistant": "I use Nix as a build system, so as long as the CMakeFiles are generic enough to compile on both macOS, Ubuntu and CentOS I have no issues with the specific versions of the operating system."}, {"assistant": "CentOS 7 is EOL on 2024-06-30. I know of machines that are still running it, so maybe it would be a good idea to hold off removing support until then."}, {"assistant": "As a data point, I wanted to mention that I just got it running on Gentoo, depending only on system packages except for or-tools"}]} +{"messages": [{"user": "@nerriav Global routing takes very little time for the project I am working on. However, when I make changes, these sometimes can make global routing impossible and I have to tweak my change.\r\n\r\nWhen global routing fails, it doesnt fail quickly, it just runs \"forever\"(hours compared to minutes) before it ultimately fails.\r\n\r\nCan I adjust a setting such that global route fails quickly so that I dont waste server build resources and I can quickly load the routing congestion report in the DRC viewer to drill down to the problem?"}, {"assistant": "In OR you can use the `-congestion_interations` argument which translates to `GLOBAL_ROUTE_ARGS=\" -congestion_iterations X \"` in ORFS. X is a positive integer. The default is 100."}, {"user": "Syntax subtleties... `export GLOBAL_ROUTE_ARGS=\"-congestion_iterations 10 -verbose\"`, failed with `[ERROR STA-0402] global_route -congestion_iterations 10 -verbose is not a known keyword or flag.`\r\n\r\n`export GLOBAL_ROUTE_ARGS=-congestion_iterations 10 -verbose` worked...\r\n\r\nIt is still stuck on:\r\n\r\n```\r\n[INFO GRT-0101] Running extra iterations to remove overflow.\r\n```\r\n\r\nWith `export GLOBAL_ROUTE_ARGS=-congestion_iterations 2 -verbose` it fails after 2:30 minutes.\r\n\r\nI'll see how high I can make it until it \"runs forever\". If it fails after 10 minutes, then I have something I can try out. If there is nothing wrong, I would expect it to complete in ca. 3 minutes.\r\n\r\nI'm curious if 10 iterations is enough for all the designs under test... https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/1076"}]} +{"messages": [{"user": "Do global and detailed placers respect def blockages? "}, {"assistant": "Yes"}]} +{"messages": [{"user": "Hello, Is there any idea whether eventually OpenRoad would like to support also synthesis as part of the tool (instead of using Yosys externally) ?"}, {"assistant": "There is no plan for that. At most we would integrate yosys. What motivates your question?"}, {"user": "Hi, @maliberty , several points:\r\n- Yosys does not support full System Verilog (AFAIK, only with proprietary parser). Nor it supports VHDL (only via GHDL yosys plugin, and getting this to work is tricky)\r\n- Synthesis is mentioned several times in: https://github.com/The-OpenROAD-Project/OpenROAD/issues/1759\r\n1. Hard to get netlist that passes the timing\r\n2. Possible QoR gains\r\n\r\n- Generally, placement / routing aware synthesis reaches better results in lower geometries\r\n- Industry high-end goes this direction\r\n- Easier user interface (single database, simpler to pass information from synthesis to PnR)\r\n"}, {"user": "However,\r\nI need to note that I am not actively using nor developing OpenRoad. As for the usage, in company where I work, we use Synopsys for Synthesis and PnR tools due to stability, documentation, good performance and vast features available. We are looking forward for the day when we will be able to use open source.\r\nAs for the development, I would really like to join, but I already have little time for the open-source work due to my daily job."}, {"assistant": "SV support is unrelated to OR and is being addressed in https://github.com/chipsalliance/Surelog. The pain is mostly related to missing ASIC oriented features in yosys/abc (eg operator mapping). \r\n\r\nIn general its a large effort and would need dedicated resources to work on it. There isn't enough bandwidth to make it a priority. If you want to start addressing some of these concerns I'd be happy to discuss further."}, {"assistant": "OR has already integrated abc which handles the technology dependent operations. Its less clear that there is a big advantage to the technology independent operations in yosys itself. There is some work slowly progressing on remapping in OR using abc."}]} +{"messages": [{"user": "I'm using `-group -order` with `set_io_constraints` and I'm using the tcl snippet below to enumerate pins.\r\n\r\nHowever, this brings up the question: what order does `get_ports` return pins in?\r\n\r\n```\r\nproc match_pins { regex } {\r\n set pins {}\r\n foreach pin [get_ports -regexp $regex] {\r\n lappend pins [get_property $pin name]\r\n }\r\n return $pins\r\n}\r\n```\r\n"}, {"user": "@nerriav FYI"}, {"assistant": "arbitrary order, no assumptions should be made"}, {"assistant": "The command comes from SDC and such an option would be non-standard and non-portable."}, {"user": "In mock-array-big, I introduced a designs/asap7/mock-array-big/util.tcl function, which is shared between macros and top level of the design.\r\n\r\nI'm thinking that a shared util.tcl function will be required for non-trivial designs anyway.\r\n\r\nPerhaps it is sufficient to provide an example of this in mock-array-big for now?\r\n\r\nI see this somewhat tying into how one would have a centralized method to calculate properties of macros and the top level design: manual placement of macros relative to eachother, sizes of macros calculated based on environment variables, etc.\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/discussions/1067"}]} +{"messages": [{"user": "Title."}, {"assistant": "The resizer does tend to loop over all corners so I think so."}]} +{"messages": [{"user": "I get a lot of these warnings when I run `make gui_final`\r\n\r\nThis is with the latest ORFS.\r\n\r\nWhat are they?\r\n\r\n```\r\n$ make DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk place\r\n```\r\n\r\n\r\n```\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 63.3687 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 79.0805 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 106.935 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 156.622 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 248.596 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 397, 432.982 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 0.36 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 0.72 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 1.44 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 2.88 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 5.76 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 11.52 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 406, 23.04 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 415, 12.8576 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 415, 15.7364 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 415, 21.3969 is not a float.\r\n[WARNING STA-0139] /home/oyvind/OpenROAD-flow-scripts/flow/platforms/asap7/lib/asap7sc7p5t_AO_RVT_TT_nldm_211120.lib.gz line 415, 32.5931 is not a float.\r\n```"}, {"assistant": "@oharboe \r\nI ran with latest commit and not able to get similar logs."}, {"assistant": "The report says 'make place' and 'make gui_final' which are not a compatible pair. I can't reproduce this either even running all the way through."}, {"user": "```\r\nrm -rf results/\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk place\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk gui_place\r\n```\r\n\r\n```\r\n$ make DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk gui_place\r\n[INFO][FLOW] Using platform directory ./platforms/asap7\r\n[INFO-FLOW] ASU ASAP7 - version 2\r\nDefault PVT selection: BC\r\nODB_FILE=./results/asap7/mock-array-big_Element/base/3_place.odb /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad -gui ./scripts/gui.tcl\r\nWarning: Ignoring XDG_SESSION_TYPE=wayland on Gnome. Use QT_QPA_PLATFORM=wayland to run on Wayland anyway.\r\nThis plugin does not support propagateSizeHints()\r\nOpenROAD v2.0-8114-gaa1f8060d \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 0.72 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 1.44 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 2.88 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 5.76 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 11.52 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 23.04 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 82, 46.08 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 96, 0.72 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 96, 1.44 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 96, 2.88 is not a float.\r\n[WARNING STA-0139] ./platforms/asap7/lib/asap7sc7p5t_AO_RVT_FF_nldm_211120.lib.gz line 96, 5.76 is not a float.\r\n```\r\n"}, {"user": "@maliberty Aha! This is a locale issue. In their wisdom a hundred years ago, Norwegians decided to use \",\" to separate integers from fractions in floating point... So \"12.34\" is not a valid float in Norwegian locale, rather \"12,34\" is.\r\n\r\nThe evidence that this is the problem is that setting `LC_NUMERIC=\"en_GB.UTF-8\"` fixes the problem.\r\n\r\nIn this case, the locale is decided by the format that is being parsed, it is not a human readable/writeable number.\r\n\r\nLet's see if this works: https://github.com/Pinata-Consulting/OpenSTA/tree/lock-down-strtof-locale\r\n\r\nYep :-)\r\n\r\nThis also explains why we don't see this when we run from docker, only local install."}, {"assistant": "Brazil has the same issue. https://github.com/The-OpenROAD-Project/OpenROAD/blob/6920ac530b6959f742e75b7f55062b1642730b14/src/Main.cc#L217 attempts to solve this. Do none of the locales exist on your systems?"}, {"assistant": "Would you try your strtof check along with getlocale after these various points to try to see what's going on. I think this works in Brazil so I'm trying to understand what's different here. @luis201420 any insights?\r\n"}, {"assistant": "Perhaps it relates to LC_NUMERIC or another. Can you try unsetting all LC_* but LC_ALL in your environment to see if that matters?"}, {"user": "@maliberty @luis201420 With this change, I no longer get the warnings.\r\n\r\nThis is just a quick hack, I think it would be better if someone who knows what is going on and are aware of other edgecases articulates the pull request :-)\r\n\r\n```\r\ndiff --git a/src/gui/src/gui.cpp b/src/gui/src/gui.cpp\r\nindex 355aa6842..7d79d99a3 100644\r\n--- a/src/gui/src/gui.cpp\r\n+++ b/src/gui/src/gui.cpp\r\n@@ -1141,6 +1141,16 @@ int startGui(int& argc,\r\n }\r\n main_window->show();\r\n \r\n+ // This avoids problems with locale setting dependent\r\n+ // C functions like strtod (e.g. 0.5 vs 0,5).\r\n+ std::array locales = {\"en_US.UTF-8\", \"C.UTF-8\", \"C\"};\r\n+ for (auto locale : locales) {\r\n+ if (std::setlocale(LC_ALL, locale) != nullptr) {\r\n+ break;\r\n+ }\r\n+ }\r\n+\r\n+\r\n gui->setLogger(open_road->getLogger());\r\n \r\n main_window->setDatabase(open_road->getDb());\r\n```\r\n"}, {"assistant": "@luis201420 will you look at this since you can reproduce it"}, {"user": "I guess this has been identified as a bug in OpenROAD, given that there are frameworks that set the locale after OpenROAD has set the locale."}]} +{"messages": [{"user": "mock-array-big has 3 essential parameters that can be adjusted: array area(number of elements), element size (area) and data width (bits).\r\n\r\nI thought it would be interesting to see how detailed routing (TritonRoute) varies across these parameters, so I made a python snippet(https://github.com/Pinata-Consulting/OpenROAD-flow-scripts/commits/plot-running-times) to gather some data and plot them\r\n\r\nThe graph below is interactive(measured on a machine with 16 threads and 64gByte of RAM, where memory consumption appears to peak at 20gByte), which helps in terms of understanding the 4 dimensions being represented:\r\n\r\nVideo: https://drive.google.com/file/d/1pmkIZh6tUOrWhAkVRgm0fxCD7yaf766Q/view\r\n\r\nSnapshot:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/236807617-6c48df46-609a-4614-937e-539cbf7c5ce7.png)\r\n\r\n**8 x 8 64 bit array detailed route times plotted against threads**\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/236921035-c2ac6218-b515-4c83-b342-0c3d2f677f99.png)\r\n\r\n**Conclusion so far**\r\n\r\nDetailed routing is surprisingly slow when the area is large, but everything else is the same.\r\n\r\nThis run takes 40 minutes or so, `APTOS_MOCK_PITCH_SCALE=20 make FLOW_VARIANT=scale-20 route DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk` whereas `APTOS_MOCK_PITCH_SCALE=2 make FLOW_VARIANT=scale-2 DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk` completes in a few minutes\r\n\r\n\r\n**Detailed of testing...**\r\n\r\nIt looks like the performance of detailed routing is sensitive to area:\r\n\r\n```\r\nMOCK_ARRAY_PITCH_SCALE=2 make OPENROAD_EXE=\"perf record -o perf.data ~/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\" DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk FLOW_VARIANT=scale-2 route\r\n```\r\n\r\n```\r\nSamples: 15M of event 'cycles', Event count (approx.): 14285585618565\r\nOverhead Command Shared Object Symbol\r\n 16,94% openroad openroad [.] fr::FlexGridGraph::initEdges\r\n 8,38% openroad openroad [.] fr::FlexGridGraph::outOfDieVia\r\n 7,46% openroad openroad [.] fr::FlexDRWorker::modMinSpacingCostVia\r\n 5,92% openroad openroad [.] fr::FlexGCWorker::Impl::isCornerOverlap\r\n 4,62% openroad libstdc++.so.6.0.30 [.] std::_Rb_tree_increment\r\n 4,23% openroad [unknown] [k] 0xffffffffa7b87f27\r\n 4,20% openroad openroad [.] fr::FlexDRWorker::modMinSpacingCostPlanar\r\n 3,31% openroad openroad [.] fr::frLayer::getMinSpacingValue\r\n 3,22% openroad openroad [.] fr::FlexGridGraph::getIdx\r\n 2,93% openroad openroad [.] fr::FlexGCWorker::Impl::initNet_pins_polygonCorners_helper\r\n 2,48% openroad openroad [.] fr::FlexDRWorker::modMinSpacingCostVia_eol\r\n 2,46% openroad openroad [.] box2boxDistSquareNew\r\n 2,37% openroad openroad [.] fr::FlexDRWorker::modBlockedPlanar\r\n 2,17% openroad openroad [.] fr::FlexGridGraph::addFixedShapeCostVia\r\n 1,71% openroad openroad [.] odb::dbTransform::apply\r\n 1,45% openroad openroad [.] fr::FlexGridGraph::isEdgeInBox\r\n 1,43% openroad openroad [.] odb::dbTransform::apply\r\n 1,28% openroad openroad [.] fr::FlexDRWorker::modBlockedVia\r\n 1,25% openroad openroad [.] std::vector```\r\n\r\nThe archived version should match the paper but any further improvements will not be present."}, {"assistant": "That should be fine. Are you using a similar number of threads in standalone TR?"}, {"assistant": "Are you running a recent version of OpenROAD with the following fix: https://github.com/The-OpenROAD-Project/OpenROAD/commit/0cf19963d358347bcf06a2cd803ea883f8c46f27\r\n\r\nThat issue isn't in the original TritonRoute source, and can cause significantly more runtime in the pin access code."}, {"assistant": "@vijayank88 did you mean to close this? I just checked, and we are spending significantly more time in genInstRowPattern vs TritonRoute."}, {"assistant": "Most of the problem appears to be 5fada4c44b2d4aba09185eb1217f928645c32c4b. Start up time for ispd19_test1 goes from 17 seconds to 280 seconds. I haven't got far enough to understand if all that overhead is required. FYI @maliberty @osamahammad21 \r\n"}, {"assistant": "Its not obvious to me how that change triggers the issue but its @osamahammad21 change so he might have an idea."}, {"assistant": "I'm not sure why, but the problem is caused by filtering out other instances when generating our preferred access points:\r\n\r\n```\r\n- hasVio = !genPatterns_gc({prevInst, currInst}, objs, Edge);\r\n+ // hasVio = !genPatterns_gc({prevInst, currInst}, objs, Edge);\r\n+ hasVio = !genPatterns_gc({}, objs, Edge);\r\n```\r\n\r\nI would have expected this to take less time, unless the act of filtering out other instances is taking lots of time."}, {"assistant": "@gilgamsh It would be interesting to see a profile of both cases to see where the difference in time is. That should tell us something of the nature of the difference to corroborate the suspicions on what differences in code that can cause this."}, {"assistant": "Note that a fair number of enhancements and bug fixes have gone into the OR version. It is possible you are not observing equivalent results."}]} +{"messages": [{"user": "The `-metrics` feature is useful, but I wonder if there is a way to get it when using the `sta` binary that's included with OpenROAD. We use this binary as OpenROAD's sta commands do not support hierarchical STA, so I'm just wondering if this is at all possible."}, {"assistant": "All the metrics generation is in OR so I don't think so."}]} +{"messages": [{"user": "I tried, because I was curious, to resume building with locally built OpenROAD after using a Docker image with OpenROAD and got the SEGFAULT below.\r\n\r\nAre Docker and locally built OpenROAD binaries interoperable?\r\n\r\n```\r\nStack trace:\r\n 0# 0x000055DC737CFAD5 in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n 1# 0x00007F6F2783BCF0 in /lib/x86_64-linux-gnu/libc.so.6\r\n 2# 0x00007F6F27971E37 in /lib/x86_64-linux-gnu/libc.so.6\r\n 3# 0x00007F6F27886DAE in /lib/x86_64-linux-gnu/libc.so.6\r\n 4# fread in /lib/x86_64-linux-gnu/libc.so.6\r\n 5# 0x000055DC75A083EA in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n 6# odb::operator>>(odb::dbIStream&, odb::_dbTechLayer&) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n 7# odb::operator>>(odb::dbIStream&, odb::_dbTech&) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n 8# odb::operator>>(odb::dbIStream&, odb::_dbDatabase&) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n 9# odb::dbDatabase::read(_IO_FILE*) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n10# ord::OpenRoad::readDb(char const*) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n11# 0x000055DC73816BDE in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n12# TclNRRunCallbacks in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n13# 0x00007F6F2BCDE028 in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n14# Tcl_EvalEx in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n15# Tcl_Eval in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n16# sta::sourceTclFile(char const*, bool, bool, Tcl_Interp*) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n17# ord::tclAppInit(Tcl_Interp*) in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n18# Tcl_MainEx in /lib/x86_64-linux-gnu/libtcl8.6.so\r\n19# main in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\n20# 0x00007F6F27823510 in /lib/x86_64-linux-gnu/libc.so.6\r\n21# __libc_start_main in /lib/x86_64-linux-gnu/libc.so.6\r\n22# _start in /home/oyvind/OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad\r\nCommand terminated by signal 11\r\n```"}, {"assistant": "That's surprising. Are the two builds from the same commit? Perhaps some cross-version compatibility bug has crept in."}]} +{"messages": [{"user": "I'm looking forward to taking mpl2 for a spin on mock-array-big(there's an assert I've reported, that I'm sure will be fixed before long.)\r\n\r\nConcerning the algorithm of mpl2: does it consider the IO pins and how they are connected to other macros?\r\n\r\nIn the case of mock-array-big, there can be no doubt that the best layout is a grid. There are quite a few macros in that design (8x8 in an array). It is easily possible to reduce or increase the datapath width of the mock-array-big as well as change the layout of the array to pretty much any M x N.\r\n\r\nAt the top level of another design I'm interested in, the situation is similar, even if it is not an array.\r\n\r\nI don't expect there to be much doubt as to how the 4 large macros can be organized as macro io pin constraints have placed pins on edges. Afterwards there really is only one way the macros can be placed. If you get one macro placement wrong, you have an enormous amount of routing that needs to be done for all the pins.\r\n\r\nThe number of macros is 4 or so all that is needed is to have some sense of how much space is needed in the routing channel between the macros.\r\n\r\nThe advantage of automatic macro placement is to reduce the amount of brittle Tcl I have to write during architectural exploration. Writing Tcl to place macros is VERY time consuming at the top level, even with mock abstracts. Mock abstracts is where you skip CTS and routing to work only on higher level floorplanning and routing. To generate a mock abstract, run: `make skip_cts skip_route generate_abstract`"}, {"user": "I have tried mpl2 on mock-array-big, but it crashes."}]} +{"messages": [{"user": "What does this mean?\r\n\r\n\"foobar\" is the first iterm of the macro and the macro is very tall and has lots of wires on the left hand side.\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/232051624-f59d4343-6a83-4e02-9e7b-f4518eb69bbf.png)\r\n"}, {"assistant": "At the start of drt we figure out how we can access each pin we need to connect to. The access point is a spot where we could legally drop a via or make a planar connection (the later is more common for macro pins). This error results when we can't find any legal way to connect to the pin so the router gives up early rather than struggle on hopelessly.\r\n\r\nThe analysis is quite local to the pin and its immediate surrounding fixed objects (i.e. other pins or blockages). It would be helpful to have more of a close up image of the pin to get a better sense of what is going on."}]} +{"messages": [{"user": "Hello,\r\n\r\nIn the DFT tool, I am trying to connect a new created scan_out port at the top level module with the scan out of a scan cell.\r\n\r\nThe scan out of the cell is previously connected to a functional path, so I am doing something like:\r\n\r\n```\r\nodb::dbNet* functional_net = scan_out_cell->getNet();\r\nscan_out_module->connect(functional_net);\r\n```\r\nWhen I print the BTerms of the net, I get both, the scan_out of the module and the previous connected port.\r\n\r\nHowever, I doesn't seems to work if I write the verilog, as I am only seeing it being connected to the original functional port instead of being connected to both of them: scan out and functional port.\r\n\r\nIs there something that am I missing?\r\n\r\nThanks,\r\nFelipe"}, {"assistant": "What is the type of scan_out_module ?"}, {"assistant": "An issue with a test case might be better as it doesn't sound like an unusual operation."}, {"user": "This was addressed in https://github.com/The-OpenROAD-Project/OpenROAD/issues/3183\r\n\r\nHowever, @maliberty was right in that ticket and we don't really need to punch a new port for scan out, we can just reuse the already existing port. So, we only need to punch a new scan out port if there is funcional logic before scan insertion and there are only ITerms in the net."}]} +{"messages": [{"user": "I'm doing some exploration of floorplanning, which means that I sometimes have a LOT of free space after detailed routing.\r\n\r\nI saw this net, which I thought was curious: a meandering wire in the void...\r\n\r\nWouldn't a single vertical + horizontal wire be faster?\r\n\r\nI'm curious as to why the detailed router meanders in this way.\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/231722490-7eeb540d-5004-424b-bca1-f29bc53fa899.png)\r\n"}, {"assistant": "what does the route guide look like for this wire?"}, {"user": "I know what is going on. That wire has a lot of flip-flops on it.\r\n\r\nThis is a holdover from FPGA design. In the FPGA design, we used global synthesis and we had a synchronous reset with a LARGE fan-out. That large fan-out was handled by adding a number of flip-flops to it so that the tools would be able to create a synchronous reset tree to deal with the fanout and reset congestion. This is congruent with the recommendation in Quartus to use the HyperFlex architecture where there are bypassable registers in the routing. To use those, you basically add a bunch of pipeline stages to your synchronous reset. Basically the more modern Intel FPGAs now recommend synchronous reset over asynchronous reset for this reason.\r\n\r\nhttps://www.intel.com/content/www/us/en/docs/programmable/683353/21-3/fpga-architecture-introduction.html\r\n\r\nThe above with the caveat that I'm not an FPGA expert when it comes to detail, I just write RTL, follow some high level guidelines, and the tools handle the rest..."}]} +{"messages": [{"user": "As a general strategy, would it make sense to exhaust the current level of detail when a failure is found, rather than start bisecting at the top?\r\n\r\nIt found something to chop away here:\r\n\r\n```\r\nReading base odb file\r\nInsts level debugging\r\nNumber of Insts 913\r\nNumber of Nets 119228\r\nNumber of elements to be cut is 57, [############C###]\r\nDone cutting design.\r\nWriting odb file\r\nStep 57 is running, deltaDebug is waiting.\r\nTimeout updated to approx 2 minutes!\r\nError Code found: [ERROR GRT-0119] Routing congestion too high.\r\nStep 57 is done.\r\n```\r\n\r\nThen it started bisecting at the top again, before finally finding something to chop away here.\r\n\r\nSo all that chopping away from the top was wasted, in this case.\r\n\r\n```\r\nReading base odb file\r\nInsts level debugging\r\nNumber of Insts 856\r\nNumber of Nets 119228\r\nNumber of elements to be cut is 26, [###############C################]\r\nDone cutting design.\r\nWriting odb file\r\nStep 103 is running, deltaDebug is waiting.\r\nTimeout updated to approx 2 minutes!\r\nError Code found: [ERROR GRT-0119] Routing congestion too high.\r\nStep 103 is done.\r\n```"}, {"assistant": "Its hard to give a general answer as to what will work better. Most likely it is test case specific. Feel free to try and see."}]} +{"messages": [{"user": "I'm getting this problem again while building OpenROAD locally. I've tried recloning and deleting the entire ORFS folder, still no luck.\r\n\r\nAny ideas?\r\n\r\n```\r\n$ lsb_release -a\r\nNo LSB modules are available.\r\nDistributor ID:\tUbuntu\r\nDescription:\tUbuntu 22.10\r\nRelease:\t22.10\r\nCodename:\tkinetic\r\n\r\n```\r\n```\r\n./build_openroad.sh --local --openroad-args \"-D CMAKE_BUILD_TYPE=RELEASE\"\r\n```\r\n\r\n```\r\n[deleted]\r\nFAILED: src/dpl/test/dpl_test src/dpl/test/dpl_test[1]_tests.cmake /home/oyvind/ascenium/blah/tools/OpenROAD/build/src/dpl/test/dpl_test[1]_tests.cmake \r\n: && /usr/bin/c++ -O3 -DNDEBUG src/dpl/test/CMakeFiles/dpl_test.dir/dpl_test.cc.o -o src/dpl/test/dpl_test -lgtest -lgtest_main src/dpl/libdpl_lib.a src/odb/src/cdl/libcdl.a src/odb/src/defin/libdefin.a src/odb/src/def/libdef.a src/odb/src/def/libdefzlib.a src/odb/src/lefin/liblefin.a src/odb/src/lef/liblef.a src/odb/src/lef/liblefzlib.a /usr/lib/x86_64-linux-gnu/libz.so src/odb/src/db/libdb.a src/odb/src/defout/libdefout.a src/odb/src/lefout/liblefout.a src/odb/src/zutil/libzutil.a src/odb/src/db/libdb.a src/odb/src/defout/libdefout.a src/odb/src/lefout/liblefout.a src/odb/src/zutil/libzutil.a src/odb/src/tm/libtm.a /home/oyvind/ascenium/blah/tools/OpenROAD/src/sta/app/libOpenSTA.a /usr/lib/x86_64-linux-gnu/libtcl.so /usr/lib/x86_64-linux-gnu/libtclreadline.so /usr/lib/x86_64-linux-gnu/libz.so -ltcl src/utl/utl.a src/utl/libutl_lib.a /home/oyvind/ascenium/blah/dependencies/lib/libspdlog.a && cd /home/oyvind/ascenium/blah/tools/OpenROAD/build/src/dpl/test && /home/oyvind/ascenium/blah/dependencies/bin/cmake -D TEST_TARGET=dpl_test -D TEST_EXECUTABLE=/home/oyvind/ascenium/blah/tools/OpenROAD/build/src/dpl/test/dpl_test -D TEST_EXECUTOR= -D TEST_WORKING_DIR=/home/oyvind/ascenium/blah/tools/OpenROAD/src/dpl/test -D TEST_EXTRA_ARGS= -D TEST_PROPERTIES= -D TEST_PREFIX= -D TEST_SUFFIX= -D TEST_FILTER= -D NO_PRETTY_TYPES=FALSE -D NO_PRETTY_VALUES=FALSE -D TEST_LIST=dpl_test_TESTS -D CTEST_FILE=/home/oyvind/ascenium/blah/tools/OpenROAD/build/src/dpl/test/dpl_test[1]_tests.cmake -D TEST_DISCOVERY_TIMEOUT=5 -D TEST_XML_OUTPUT_DIR= -P /home/oyvind/ascenium/blah/dependencies/share/cmake-3.24/Modules/GoogleTestAddTests.cmake\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::report(char const*)':\r\nLoggerCommon.cpp:(.text+0x18f): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::open_metrics(char const*)':\r\nLoggerCommon.cpp:(.text+0x2e9): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::close_metrics(char const*)':\r\nLoggerCommon.cpp:(.text+0x309): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::set_metrics_stage(char const*)':\r\nLoggerCommon.cpp:(.text+0x32e): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::clear_metrics_stage()':\r\nLoggerCommon.cpp:(.text+0x369): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o):LoggerCommon.cpp:(.text+0x38e): more undefined references to `ord::getLogger()' follow\r\ncollect2: error: ld returned 1 exit status\r\n[3/39] Automatic MOC and UIC for target gui\r\nninja: build stopped: subcommand failed.\r\n```\r\n"}, {"assistant": "I can't reproduce it but can you try changing https://github.com/The-OpenROAD-Project/OpenROAD/blob/8a49dff86645352d30780951b1146b31ef41b0f4/src/dpl/CMakeLists.txt#L58 to utl_lib and see if that helps."}, {"assistant": "PR coming. I'm not sure why it varies - perhaps different compilers?"}]} +{"messages": [{"user": "I saw your presentation at Latchup, and was really impressed with how you were able to dive into the design and figure out things such as the critical path from the GUI.\r\n\r\nI'm using the OpenLane flow, and have the odb file open:\r\n\r\n![image](https://user-images.githubusercontent.com/238325/230816281-25f560de-e476-45ba-b3ec-5f6b595fae93.png)\r\n\r\nHowever, it is not clear how to get timing information to show up. I am viewing the newest and largest odb file from `openlane/mimi-bare/runs/mimi-bare/tmp` so I assume it's the file with all of the relevant data.\r\n\r\nIs there some setting I need to change in openlane in order to find the relevant data? Or is there another flow I should be using?"}, {"assistant": "You need to hit the update button. It takes a while so we don't do it automatically in case you want to do any setting first. "}]} +{"messages": [{"user": "So I thought my run was almost finished, it went fairly quickly for a while, but then it got stuck in \"Routeability\" below.\r\n\r\n5 minutes until it got to the GPL-0075 progress message, then stuck there for at least 30 minutes.\r\n\r\nWhat does this mean and what can I do about it?\r\n\r\nThe floorplan in my case looks quite reasonable and generous.\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/580bd35a8b17f0ea7ff8afafb6cf6d23b757063e/src/gpl/src/routeBase.cpp#L557\r\n\r\n```\r\n[NesterovSolve] Iter: 370 overflow: 0.254754 HPWL: 19171375971\r\n[NesterovSolve] Iter: 380 overflow: 0.250836 HPWL: 18915207500\r\n[NesterovSolve] Iter: 390 overflow: 0.225598 HPWL: 18784146027\r\n[NesterovSolve] Iter: 400 overflow: 0.201047 HPWL: 18784861983\r\n[INFO GPL-0075] Routability numCall: 1 inflationIterCnt: 1 bloatIterCnt: 0\r\n```\r\n"}, {"user": "A little bit of suspend/resume profiling using latest OpenROAD and release build...\r\n\r\nHmmm... curious. I don't think this is a performance problem, but there were a lot of exceptions thrown, so I had to turn off breakpoints on exceptions.\r\n\r\n```\r\n__cxa_throw (@__cxa_throw:3)\r\n\r\nsta::DmpAlg::findDriverParams(double) (.cold) (@sta::DmpAlg::findDriverParams(double) (.cold):14)\r\nsta::DmpPi::gateDelaySlew(double&, double&) (.cold) (@sta::DmpPi::gateDelaySlew(double&, double&) (.cold):50)\r\nsta::DmpCeffDelayCalc::gateDelay(sta::LibertyCell const*, sta::TimingArc const*, float const&, float, sta::Parasitic const*, float, sta::Pvt const*, sta::DcalcAnalysisPt const*, float&, float&) (@sta::DmpCeffDelayCalc::gateDelay(sta::LibertyCell const*, sta::TimingArc const*, float const&, float, sta::Parasitic const*, float, sta::Pvt const*, sta::DcalcAnalysisPt const*, float&, float&):88)\r\nsta::GraphDelayCalc1::findArcDelay(sta::LibertyCell*, sta::Pin const*, sta::Vertex*, sta::MultiDrvrNet*, sta::TimingArc*, sta::Parasitic*, float, sta::Vertex*, sta::Edge*, sta::Pvt const*, sta::DcalcAnalysisPt const*, sta::ArcDelayCalc*) (@sta::GraphDelayCalc1::findArcDelay(sta::LibertyCell*, sta::Pin const*, sta::Vertex*, sta::MultiDrvrNet*, sta::TimingArc*, sta::Parasitic*, float, sta::Vertex*, sta::Edge*, sta::Pvt const*, sta::DcalcAnalysisPt const*, sta::ArcDelayCalc*):112)\r\nsta::GraphDelayCalc1::findDriverEdgeDelays(sta::LibertyCell*, sta::Instance*, sta::Pin const*, sta::Vertex*, sta::MultiDrvrNet*, sta::Edge*, sta::ArcDelayCalc*) (@sta::GraphDelayCalc1::findDriverEdgeDelays(sta::LibertyCell*, sta::Instance*, sta::Pin const*, sta::Vertex*, sta::MultiDrvrNet*, sta::Edge*, sta::ArcDelayCalc*):105)\r\nsta::GraphDelayCalc1::findDriverDelays1(sta::Vertex*, bool, sta::MultiDrvrNet*, sta::ArcDelayCalc*) (@sta::GraphDelayCalc1::findDriverDelays1(sta::Vertex*, bool, sta::MultiDrvrNet*, sta::ArcDelayCalc*):108)\r\nsta::GraphDelayCalc1::findDriverDelays(sta::Vertex*, sta::ArcDelayCalc*) (@sta::GraphDelayCalc1::findDriverDelays(sta::Vertex*, sta::ArcDelayCalc*):63)\r\nsta::FindVertexDelays::visit(sta::Vertex*) (@sta::FindVertexDelays::visit(sta::Vertex*):74)\r\nsta::BfsIterator::visit(int, sta::VertexVisitor*) (@sta::BfsIterator::visit(int, sta::VertexVisitor*):71)\r\nsta::GraphDelayCalc1::findDelays(int) (@sta::GraphDelayCalc1::findDelays(int):47)\r\nsta::Sta::checkSlewLimitPreamble() (@sta::Sta::checkSlewLimitPreamble():82)\r\nrsz::RepairDesign::repairDesign(double, double, double, int&, int&, int&, int&, int&) (@rsz::RepairDesign::repairDesign(double, double, double, int&, int&, int&, int&, int&):65)\r\nrsz::Resizer::findResizeSlacks() (@rsz::Resizer::findResizeSlacks():24)\r\ngpl::TimingBase::updateGNetWeights(float) (@gpl::TimingBase::updateGNetWeights(float):18)\r\ngpl::NesterovPlace::doNesterovPlace(int) (@gpl::NesterovPlace::doNesterovPlace(int):1262)\r\n_wrap_replace_nesterov_place_cmd (@_wrap_replace_nesterov_place_cmd:20)\r\nTclNRRunCallbacks (@TclNRRunCallbacks:37)\r\n___lldb_unnamed_symbol1504 (@___lldb_unnamed_symbol1504:315)\r\nTcl_EvalEx (@Tcl_EvalEx:9)\r\n```\r\n\r\nOoops.... from within the debugger(attaching) to the release build, I ran into an recursive loop below and a SEGFAULT.\r\n\r\nCuriously, this infinite stack recursion does not appear with the debug build, which makes for an interesting debug exercise...\r\n\r\n```\r\nrsz::RepairDesign::repairNetJunc(std::shared_ptr, int, int&, sta::Vector&) (@rsz::RepairDesign::repairNetJunc(std::shared_ptr, int, int&, sta::Vector&):16)\r\nrsz::RepairDesign::repairNet(std::shared_ptr, int, int&, sta::Vector&) (@rsz::RepairDesign::repairNet(std::shared_ptr, int, int&, sta::Vector&):82)\r\n[deleted 100s if not 1000s of these]\r\n(@rsz::RepairDesign::repairNet(std::shared_ptr, sta::Pin const*, float, int, sta::Corner const*):29)\r\nrsz::RepairDesign::repairNet(sta::Net*, sta::Pin const*, sta::Vertex*, bool, bool, bool, int, bool, int&, int&, int&, int&, int&) (@rsz::RepairDesign::repairNet(sta::Net*, sta::Pin const*, sta::Vertex*, bool, bool, bool, int, bool, int&, int&, int&, int&, int&):356)\r\nrsz::RepairDesign::repairDesign(double, double, double, int&, int&, int&, int&, int&) (@rsz::RepairDesign::repairDesign(double, double, double, int&, int&, int&, int&, int&):195)\r\nrsz::Resizer::findResizeSlacks() (@rsz::Resizer::findResizeSlacks():24)\r\ngpl::TimingBase::updateGNetWeights(float) (@gpl::TimingBase::updateGNetWeights(float):18)\r\ngpl::NesterovPlace::doNesterovPlace(int) (@gpl::NesterovPlace::doNesterovPlace(int):1262)\r\n_wrap_replace_nesterov_place_cmd (@_wrap_replace_nesterov_place_cmd:20)\r\nTclNRRunCallbacks (@TclNRRunCallbacks:37)\r\n___lldb_unnamed_symbol1504 (@___lldb_unnamed_symbol1504:315)\r\nTcl_EvalEx (@Tcl_EvalEx:9)\r\nTcl_Eval (@Tcl_Eval:11)\r\nsta::sourceTclFile(char const*, bool, bool, Tcl_Interp*) (@sta::sourceTclFile(char const*, bool, bool, Tcl_Interp*):31)\r\nord::tclAppInit(Tcl_Interp*) (@ord::tclAppInit(Tcl_Interp*):128)\r\nTcl_MainEx (@Tcl_MainEx:111)\r\nmain (@main:742)\r\n__libc_start_call_main (@__libc_start_call_main:29)\r\n__libc_start_main_impl (@__libc_start_main@@GLIBC_2.34:43)\r\n_start (@_start:15)\r\n```\r\n\r\n\r\n"}, {"user": "Letting it run for a while, debug is MUCH slower than release, I see when I suspend in the debugger. There are 200000 nets to process in gen_brk_RSMT(), coeffADJ() is going through double loops for a total of 10000000 iterations...\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/229814542-0e59488f-6f61-46ca-9219-fe4cea5fb085.png)\r\n\r\n\r\n```\r\ngrt::FastRouteCore::getEdgeCapacity(grt::FrNet*, int, int, grt::EdgeDirection) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/fastroute/src/FastRoute.cpp:592)\r\ngrt::FastRouteCore::coeffADJ(int) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/fastroute/src/RSMT.cpp:616)\r\ngrt::FastRouteCore::gen_brk_RSMT(bool, bool, bool, bool, bool) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/fastroute/src/RSMT.cpp:662)\r\ngrt::FastRouteCore::run() (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/fastroute/src/FastRoute.cpp:766)\r\ngrt::GlobalRouter::findRouting(std::vector>&, int, int) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/GlobalRouter.cpp:397)\r\ngrt::GlobalRouter::globalRoute(bool) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/grt/src/GlobalRouter.cpp:285)\r\ngpl::RouteBase::getGlobalRouterResult() (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/gpl/src/routeBase.cpp:378)\r\ngpl::RouteBase::routability() (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/gpl/src/routeBase.cpp:566)\r\ngpl::NesterovPlace::doNesterovPlace(int) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/gpl/src/nesterovPlace.cpp:699)\r\ngpl::Replace::doNesterovPlace(int) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/gpl/src/replace.cpp:343)\r\nreplace_nesterov_place_cmd() (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/build/src/gpl/CMakeFiles/gpl.dir/replaceTCL_wrap.cxx:1740)\r\n::_wrap_replace_nesterov_place_cmd(ClientData, Tcl_Interp *, int, Tcl_Obj *const *) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/build/src/gpl/CMakeFiles/gpl.dir/replaceTCL_wrap.cxx:2190)\r\nTclNRRunCallbacks (@TclNRRunCallbacks:37)\r\n___lldb_unnamed_symbol1504 (@___lldb_unnamed_symbol1504:315)\r\nTcl_EvalEx (@Tcl_EvalEx:9)\r\nTcl_Eval (@Tcl_Eval:11)\r\nsta::sourceTclFile(char const*, bool, bool, Tcl_Interp*) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/sta/app/StaMain.cc:95)\r\n::tclAppInit(int &, char **, const char *, Tcl_Interp *) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/Main.cc:412)\r\nord::tclAppInit(Tcl_Interp*) (/home/oyvind/ascenium/OpenROAD-flow-scripts/tools/OpenROAD/src/Main.cc:440)\r\nTcl_MainEx (@Tcl_MainEx:111)\r\n```\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/229812113-27d8013b-9fbc-4727-93ee-18fed95d3702.png)\r\n\r\n"}, {"assistant": "You could try disabling each of these in turn to localize the cause\r\n```\r\nif {$::env(GPL_ROUTABILITY_DRIVEN)} {\r\n append global_placement_args \" -routability_driven\"\r\n}\r\nif {$::env(GPL_TIMING_DRIVEN)} {\r\n append global_placement_args \" -timing_driven\"\r\n}\r\n```\r\nThe stacks in rsz/sta are related to timing_driven. If you see a stack in grt that is related to routability_driven."}]} +{"messages": [{"user": "Any idea what is going on here?\r\n\r\n```\r\n./build_openroad.sh --local --openroad-args \"-D CMAKE_BUILD_TYPE=RELEASE\"\r\n[deleted]\r\nTIMEOUT=5 -D TEST_XML_OUTPUT_DIR= -P /home/oyvind/ascenium/OpenROAD-flow-scripts/dependencies/share/cmake-3.24/Modules/GoogleTestAddTests.cmake\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::report(char const*)':\r\nLoggerCommon.cpp:(.text+0x18f): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::open_metrics(char const*)':\r\nLoggerCommon.cpp:(.text+0x2e9): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::close_metrics(char const*)':\r\nLoggerCommon.cpp:(.text+0x309): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::set_metrics_stage(char const*)':\r\nLoggerCommon.cpp:(.text+0x32e): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o): in function `utl::clear_metrics_stage()':\r\nLoggerCommon.cpp:(.text+0x369): undefined reference to `ord::getLogger()'\r\n/usr/bin/ld: src/utl/utl.a(LoggerCommon.cpp.o):LoggerCommon.cpp:(.text+0x38e): more undefined references to `ord::getLogger()' follow\r\ncollect2: error: ld returned 1 exit status\r\n```"}, {"assistant": "@oharboe \r\nHave you removed `OpenROAD-flow-scripts/tools` directory before building again.\r\nSometimes it may cause the issue.\r\n@vvbandeira Can please check this?"}, {"assistant": "which binary is it building when the error happens?"}, {"user": "Rejoice! I finally got it to compile. I deleted the *entire* ORFS folder, recloned, reran sudo ./setup.sh and then the build worked.\r\n\r\nSo, somewhere inside the ORFS folder there was an out of date file that wasn't being built...\r\n\r\nIt would be nice to know what exactly is going wrong, but I guess that will have to wait until next time it breaks and I do some more investigations?"}]} +{"messages": [{"user": "I am using https://github.com/The-OpenROAD-Project/TritonRoute to run the benchmarks of ispd2018&2019. However I found Multithreaded acceleration is almost useless. Does the legacy code in https://github.com/The-OpenROAD-Project/TritonRoute support Multithreaded acceleration ?"}, {"assistant": "How are you enabling the multi threading? It should make a large difference"}, {"assistant": "The standalone TritonRoute is archived and not under any active development or support. If that meets you needs that's fine but the integrated version in OR is continuing to be improved."}, {"assistant": "Since you are interested in contests I would look at \r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/drt/test/ispd18_sample.tcl\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/master/src/drt/test/run-ispd.py\r\n\r\nas examples"}]} +{"messages": [{"user": "(I apologize for my ignorance in advance -- if an answer can be found in the documentation or elsewhere, please let me know, and I'll take this question down.)\r\n\r\nWhat versions of Python is OpenROAD compatible with? Is any version of Python3 supported? "}, {"assistant": "\"openroad -python\" gives you access to OR with a python prompt. Note that this is still in development and subject to a change and missing features. See https://github.com/The-OpenROAD-Project/OpenROAD/issues/1812\r\n\r\nopenroad as a pip module has been discussed but is not currently available (see https://github.com/The-OpenROAD-Project/OpenROAD/pull/2311)"}]} +{"messages": [{"user": "What's going on here?\r\n\r\n```bash\r\n$ etc/DependencyInstaller.sh -prefix=~/openroad-tools/ -common\r\n[deleted]\r\nLength: 136670223 (130M) [application/x-gzip]\r\nSaving to: \u2018boost_1_80_0.tar.gz.1\u2019\r\n\r\nboost_1_80_0.tar.gz 100%[===================>] 130,34M 2,37MB/s in 65s\r\n\r\n2023-03-27 16:56:06 (2,02 MB/s) - \u2018boost_1_80_0.tar.gz.1\u2019 saved [136670223/136670223]\r\n\r\n+ md5sum -c /dev/fd/63\r\n++ echo '077f074743ea7b0cb49c6ed43953ae95 boost_1_80_0.tar.gz'\r\nboost_1_80_0.tar.gz: FAILED\r\nmd5sum: WARNING: 1 computed checksum did NOT match\r\n+ exit 1\r\n```"}, {"user": "Hmm.... I suspect a manifestation of https://github.com/The-OpenROAD-Project/OpenROAD/issues/3096"}, {"assistant": "The problem is that the first download failed, and the file was not correctly deleted.\r\n\r\nNew download:\r\n```\r\nboost_1_80_0.tar.gz 100%[===================>] 130,34M 2,37MB/s in 65s\r\n```\r\n\r\nSaving with the `.1` suffix:\r\n```\r\n2023-03-27 16:56:06 (2,02 MB/s) - \u2018boost_1_80_0.tar.gz.1\u2019 saved [136670223/136670223]\r\n```\r\n\r\nChecking against the file without the suffix:\r\n```\r\n+ md5sum -c /dev/fd/63\r\n++ echo '077f074743ea7b0cb49c6ed43953ae95 boost_1_80_0.tar.gz'\r\n```\r\n\r\nI will propose a PR that uses `mktemp` that should avoid this and the #3096 issues. You can manually delete the folder/offending file for now -- apologies for the inconvenience."}]} +{"messages": [{"user": "I was testing some other things and noticed that sometimes I see routing happening in a straight line without going to a lower metal layer, others it doesn't happen.\r\n\r\nI believe what is happening is that a buffer is needed in some cases and not others, which is down to the details of the .sdc file?\r\n\r\nRun:\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk\r\n```\r\n\r\nThen:\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk gui_final\r\n```\r\n\r\nHere we can see routing in a straight line without changing metal layers between the elements, but not at the edges of the array:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227799815-a54ace6b-93ba-4589-be3e-4d9e1e07b8f0.png)\r\n\r\n\r\nConsider the element in the upper right corner:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227799862-8aa8e0f3-40ff-4ece-b601-8f7851e49e62.png)\r\n\r\n\r\nInstead of staying on M4, the router is dropping down to M2:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227799898-11731f1d-7932-4f0b-9f96-45730331938a.png)\r\n\r\n\r\nI see a buffer is inserted:\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227800127-34acfc60-be4b-4559-88d5-32b4646f5339.png)\r\n\r\n\r\nI believe there's some interaction with the PDN grid where sometimes horizontal routes are going all the way up to M6:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227800358-5455470c-93e1-47ef-b6ae-8c55dea6fbd7.png)\r\n\r\nSometimes vertical routes need to go all the way up to M7:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/227800426-d2996f1a-f7a1-4713-8644-49557cd9dcac.png)\r\n"}, {"assistant": "buffer_ports puts buffers on all the IOs so that is expected. You could try skipping that if you want to avoid them. The router has to drop down to the layer where the buffer pins are.\r\n\r\nThere are pdn stripes on m5/m6 so the router will have to avoid those. You can always customize the grid"}]} +{"messages": [{"user": "I want to do manual placement of all my srams in the design. Can someone guide me through the steps? I can use \"macro_placement\" command to do the placement but results are not good. I want to try manual placement. Is there a command to move the macro from one place to another by looking at GUI?"}, {"assistant": "@msingh9 \r\nAre you using ORFS?"}]} +{"messages": [{"user": "I have \"repair_design\" to repair slew and cap, but this has been running for long time with no output. I think it is hanging. My design is not that big. I think it will be useful to get some sense of how much work has been completed, like work progress from these functions. Maybe I should file this a enhancement request? Is there a way to print some message while it is working?"}, {"assistant": "You could file it as an enhancement request or try to tackle it yourself and file a PR."}, {"assistant": "@msingh9 \r\nAre you using standalone OpenROAD or with OpenROAD-flow-scripts?"}, {"assistant": "How large is your design?"}]} +{"messages": [{"user": "If ran openroad without gui, can I bring gui on later on after few steps from flow.tcl? I could save the design db and then open that design in gui, but I am just wondering if I can bring gui on from within openroad prompt.\r\n\r\n1) openroad -log log\r\n2) source .tcl\r\n3) After few steps of flow\r\n4) I want to open the design in gui"}, {"assistant": "You can open the gui at anytime with `gui::show`"}, {"user": "This works like a charm. Thank you for comment."}, {"assistant": "FYI you can go the other way with \"Hide GUI\":\r\n![image](https://user-images.githubusercontent.com/761514/227319100-b11dc3c6-bf82-4464-aac2-318293c43c13.png)\r\n"}]} +{"messages": [{"user": "I am using a custom macro placement script. Changing the macro position from default to any other formation causing error in detailed routing. \r\n\r\n`[ERROR DRT-0255] Maze Route cannot find path of net (some net) in worker of routeBox (34000 75000) (41000 45000)`\r\n\r\nIs it an algorithm error, any idea?\r\n"}, {"assistant": "Is automatic macro placement creating that error?"}, {"assistant": "This is a problem in detailed routing that would require a test case to investigate. Can you provide one?"}, {"assistant": "I don't expect this error from the router even with a bad macro placement."}, {"assistant": "How do you do custom macro placement?"}, {"assistant": "It would be great to have a test case for this problem as is so we can fix it in addition to any workarounds in placement to avoid it."}]} +{"messages": [{"user": "I realize this is an open ended question: How can I import Yosys netlists into OpenROAD and identify any timing concerns in the design?\r\n\r\nIs there any documentation, tutorials or examples I can look at?\r\n\r\nI think I have seen an ability to select interesting paths and drill down using \"select\" (yosys command? opensta command?) and filter timing paths, but I don't recall where.\r\n\r\nIdeally using ORFS.\r\n\r\nThis would be more convenient than invoking yosys + open sta directly and interacting with the shell in either. "}, {"assistant": "You can use 'make gui_floorplan' to open the results after the floorplan step which is pretty quick. We could add an way to directly load the yosys output. In either case you won't see any layout as nothing has been placed but you can use the usual timing path viewer.\r\n\r\nYou can't use yosys commands in OR as they are different tools."}, {"assistant": "In the GUI from Windows->Timing Report you can get the path viewer. When you select items in the path viewer you can see them in the inspector if you need to get more physical/netlist details."}, {"assistant": "@vijayank88 are there any tutorials for timing debug?"}, {"assistant": "Fwiw https://www.youtube.com/watch?v=5lkKp-gL1Ow"}, {"assistant": "@oharboe \r\nOnly after placement you can trace timing path in OpenROAD gui.\r\nYou can refer `logs/nangate45/gcd/base/2_1_floorplan.log` (gcd example). It is the first OpenSTA timing report post synthesis.\r\n"}, {"assistant": "You can really only do back annotation after you reach a fully routed result. There is nothing to back annotate before that. That is already supported in ORFS and the make gui_final will load the parasitics automatically.\r\n\r\nYou can generate timing report at any step of the flow. Pre-placement you will get wire load models. Later in the flow we use estimate_parasitics with -placement (after CTS) or -global_routing (after global routing). Post-routing we use rcx extracted values.\r\n\r\nYosys 'schematics' are a capability of yosys and have nothing to do with OR. The timing report already contains a list of all the cells/ports/nets so a schematic doesn't add much for a path. In general generating schematics for arbitrary chunks of logic is hard and is essentially another P&R problem itself. Even the proprietary tools aren't great at this beyond a small amount of logic."}, {"assistant": "If you have layout you can use the inspector to look at an ITerm and there are buttons to show the fanin and fanout cones\r\n![image](https://user-images.githubusercontent.com/761514/226408803-ae3cef35-4855-4909-9786-e7b4f569a8af.png)\r\n"}, {"assistant": "Here is a tightly package cone on gcd:\r\n![image](https://user-images.githubusercontent.com/761514/226409401-157a4b9b-7384-4e75-b43c-ed0b6d099e6e.png)\r\n"}, {"assistant": "@oharboe is this sufficient info or do you need something more?"}, {"user": "Will open new more specific questions in the future as needed. This was helpful to improve our understanding meanwhile."}]} +{"messages": [{"user": "Hello, I'm an undergrad who has been trying to add some new functionality and thus trying to learn how the codebase works.\r\n\r\nRight now, I am working in Resizer and trying to write a function that will print out the top failing (negative slack) paths. I was studying the code for worst slacks by studying the `worstSlack` functions in `Search.cc` and `WorstSlack.cc`, and also the `findResizeSlacks()` function in `Resizer.cc`. Looking at the `findResizeSlacks1()` function in `Resizer.cc`, it appears to populate the `worst_slack_nets_` field. However, when I try to access `worst_slack_nets_` in my function, it appears to be empty.\r\n\r\nIs there something that I need to call before this to populate the field? Should I even be trying to access `worst_slack_nets_` at all? "}, {"assistant": "@openroadie @maliberty any ideas here?\r\n\r\n@cshi15 maybe take a quick look at #3045 to see if there was anything useful there.\r\nAlso maybe if you can commit what you have to a fork then it will make it easier to understand what you have tried so far."}, {"assistant": "I'm guessing you need to call Resizer::resizePreamble() first."}, {"assistant": "Can you put the code on a branch somewhere? "}]} +{"messages": [{"user": "Now I'd like to use OpenDB Framework and am searching for how to use each tool (i.e. OpenDB, OpenDB, etc) in **the OpenROAD repository** as a submodule for my open-source project.\r\n\r\nFor example, I'm using the OpenDB Framework as [this repository](https://github.com/ApeachM/EDA-API).\r\nIn that repository, I only can know how to use the [legacy one](https://github.com/The-OpenROAD-Project/OpenDB) as a submodule, but couldn't find how to set the OpenROAD repository as a submodule.\r\n\r\nI would be very appreciative if there is any recommended way to use each tool (like RePlAce, OpenDP, ..) in the OpenROAD repository which is now updated recently, and if you let me know them.\r\n \r\nThank you for reading my question.\r\n\r\nBest regards.\r\n\r\n"}, {"assistant": "We do not offer each tool as a submodule. It is a lot of overhead to manage submodules (we did that initially). You could make OR itself a submodule and link to the portions you wish."}, {"assistant": "You should be able to reference our libraries from your app like\r\n\r\ntarget_link_libraries(\r\n PUBLIC\r\n odb\r\n)\r\n\r\nyou would need to include src/CMakeLists.txt"}, {"assistant": "@QuantamHD what do you think about applying your library separation work to mpl2?"}, {"user": "@QuantamHD \r\n> @ApeachM I'll ask you for a favor back. If you do end up running mpl2 in your project can you contribute some C++ unit tests back to the project? https://github.com/The-OpenROAD-Project/OpenROAD/pull/3109/files#diff-24b9bab7be8fe0944c3ae7ccbd1d8700449a2e965d33d624fd7f8e3315ebdc9e\r\n\r\nI'd like to do the favor that you mentioned, but I have a question for you.\r\nNow I'm struggling to construct the unit test for mpl2, but there are several problems with making it.\r\n\r\n### 1. The construction dependency exists. \r\n\r\nAt least calling `void MacroPlacer2::init(sta::dbNetwork* network, odb::dbDatabase* db, sta::dbSta* sta, utl::Logger* logger, par::PartitionMgr* tritonpart)` function, I need `sta::dbNetwork` and `sta::dbSta` in the test code like below.\r\n\r\n```cpp\r\n#include \r\n\r\n#include \r\n\r\n#include \"gtest/gtest.h\"\r\n#include \"mpl2/rtl_mp.h\"\r\n#include \"db_sta/dbSta.hh\"\r\n#include \"par/PartitionMgr.h\"\r\n#include \"utl/Logger.h\"\r\n\r\nnamespace mpl2 {\r\n\r\nTEST(Mpl2, CanConstruct)\r\n{\r\n MacroPlacer2();\r\n}\r\n\r\nTEST(Mpl2, init){\r\n MacroPlacer2 macro_placer_2{};\r\n\r\n sta::dbSta* db_sta = new sta::dbSta;\r\n sta::dbNetwork* db_network = db_sta->getDbNetwork();\r\n odb::dbDatabase* db_database = odb::dbDatabase::create();\r\n utl::Logger logger;\r\n par::PartitionMgr partition_mgr;\r\n\r\n /**\r\n * Construct some data in dbDatabase and dbSta by parsing or calling their methods..\r\n * */\r\n partition_mgr.init(db_database, db_network, db_sta, &logger);\r\n macro_placer_2.init(db_network, db_database, db_sta, &logger, &partition_mgr);\r\n}\r\n}; // namespace mpl2\r\n```\r\n\r\n\r\n\r\nBut at `line 21`: `sta::dbSta* db_sta = new sta::dbSta;` an error occurs with the below message.\r\n\r\n```shell\r\nOpenROAD/src/mpl2/test/cpp/mpl2_test.cc:21: undefined reference to `sta::dbSta::dbSta()'\r\n```\r\n\r\n\r\n\r\nI think this problem is due to a linking issue; `dbSta_lib` library doesn\u2019t link `dbSta.cc`, but links only `dbSta.hh`.\r\n\r\nThe `DbSta.cc` file is dependent on `ord::OpenRoad::Observer::Observer()`, so it\u2019s a pretty tricky thing to link with `mpl2_test` library and `sta::dbSta`. \r\n\r\nIs there any proposed method to use `sta::dbSta` in the `OpenROAD/src/mpl2/test/cpp/mpl2_test.cc` file? Unless, I think I can\u2019t make unit test for the one after `mpl2.init(sta::dbNetwork, ..., utl::Logger)`. \r\n\r\n\r\n\r\n### 2. Unless editing code in mpl2/src/*.cpp, there aren\u2019t many things to make unit test.\r\n\r\nFor making the unit test for `MacroPlacer2`, I can only call Constructor, Destructor, `init()`, and `place()`. \r\n\r\nEven though the assumption of linking the `mpl2_test` library and `hier_rtlmp.h, hier_rtlmp.cpp`, the `HierRTLMP` has public functions only for setters (`setGlobalFence`, \u2026,`setDebug`) and the top interface (`hierRTLMacroPlacer()`). \r\n\r\nTo test whether the `HierRTLMP` is properly working, I think I need to make some accessors to private variables (like `getGlobalFence` \u2026). But I can\u2019t assure you that it\u2019s okay for me to edit the codes in mpl2/src/*.cpp.\r\n\r\n### \r\n\r\n### Conclusion\r\n\r\nIf the first problem is solved, the second problem says there are not so many things to make unit test unless I edit the codes.\r\n\r\nI\u2019d like to ask how I can solve problem 1 (the linking issue for `sta::dbSta`), and whether it\u2019s okay or not to edit the code except the test code.\r\n\r\n\r\n\r\nThank you for reading my questions."}]} +{"messages": [{"user": "I am having some error showing macros can not connect to some pins. \r\n\r\nI can't figure out how to view macro to macro connections (flightline) and macro to pin connections in gui mode. \r\n\r\nHelp me if anyone figured this out!"}, {"assistant": "Use `net` name to view in GUI using `Find` menu. It was explained here: https://openroad-flow-scripts.readthedocs.io/en/latest/tutorials/FlowTutorial.html#tracing-the-clock-tree"}, {"user": "I was looking for macro to macro connection. \r\n\r\nI got the solution though. \r\n\r\nWe have to select a macro, right click, highlight, go to all nets and chose a group.\r\n\r\nThank you for the suggestions though.\r\n"}]} +{"messages": [{"user": "I am interested to find out my worst timing path. I can run following command to get path objects, but how do I get full report like start point, logic gates in between and end point.\r\n\r\nopenroad> find_timing_paths -from * -to * -group_count 10 -sort_by_slack\r\n_d02fb74000000000_p_PathEnd _1005b54000000000_p_PathEnd _1040b44000000000_p_PathEnd _1006b54000000000_p_PathEnd _3071b64000000000_p_PathEnd _b0bfb54000000000_p_PathEnd _d0173d3f00000000_p_PathEnd _20cdb54000000000_p_PathEnd _9091bc4000000000_p_PathEnd _003db64000000000_p_PathEnd\r\n"}, {"assistant": "From the docs for find_timing_paths https://github.com/The-OpenROAD-Project/OpenSTA/blob/master/doc/OpenSTA.pdf\r\n\r\n```\r\nUse the get_property function to access properties of the paths.\r\n```\r\n"}, {"user": "Thank you very much for prompt response. This works fantastically. I wrote a small TCL function to nicely print complete timing path with the arrival time. Maybe, it will be helpful to someone. \r\n\r\n```\r\n### Document this ####\r\nUsage: report_timing_paths \r\nExample: report_timing_paths -from * -to * -group_count 2 -sort_by_slack \r\n\r\nproc report_timing_paths {args} {\r\n set path_ends [sta::find_timing_paths_cmd \"find_timing_paths\" args]\r\n set pathno 1\r\n foreach path_end $path_ends {\r\n set start_clock [get_property [get_property $path_end startpoint_clock] full_name]\r\n set start_point [get_property [get_property $path_end startPoint] full_name]\r\n set end_point [get_property [get_property $path_end endPoint] full_name]\r\n set end_clock [get_property [get_property $path_end endpoint_clock] full_name]\r\n set slack [get_property $path_end slack]\r\n puts \"Path ${pathno} : \"\r\n puts \" [format \"%-80s\" $start_point], ${start_clock}\"\r\n set points [get_property $path_end points]\r\n foreach point $points {\r\n set arrival [get_property $point arrival]\r\n set pin [get_property [get_property $point pin] full_name]\r\n set cslack [get_property $point slack]\r\n puts \" [format \"%-80s\" $pin], $arrival\"\r\n }\r\n puts \" [format \"%-80s\" $end_point], ${end_clock}, [format \"%.3f\" $slack]\"\r\n incr pathno\r\n puts \"\"\r\n }\r\n}\r\n```"}]} +{"messages": [{"user": "How to define a constraint on a generated clock that's divided by 2 from a master clock source?"}, {"assistant": "OpenROAD flow accepts all standard SDC formats. Just browse it and implement the same.\r\nOpenSTA doc found [here](https://github.com/The-OpenROAD-Project/OpenSTA/blob/master/doc/OpenSTA.pdf)"}, {"assistant": "In particular see create_generated_clock"}]} +{"messages": [{"user": "Hi everybody,\r\n\r\nI'm making a very small sample that called `AND gate` from scatch for leaning but I did sth wrong (failed at **STEP 3**).\r\nPlease help me, let me know what I did wrong.\r\n*I'm a newbie in this domain, so I'm sorry for my stupid questions.*\r\n\r\nMy Expection:\r\n- Write a verilog & constraint file\r\n- Run several commands to create an .odb file for the Floorplan stage\r\n- Load the .odb into OpenROAD GUI\r\n- Find out the parameters, configurations, etc that required/using in the Floorplan stage\r\n\r\n---\r\n**STEP 1.** The verilog & constraint file which I wrote as the following:\r\n\r\nThe verilog file `and_gate.v`\r\n```verilog\r\nmodule and_gate(input a, input b, output y);\r\n assign y = a & b;\r\nendmodule\r\n```\r\n\r\nThe constraint file `and_gate.sdc`\r\n```verilog\r\ncreate_clock -period 10.0 [get_ports clk]\r\n```\r\n\r\n---\r\n**STEP 2.** To create net-list, I used the `yosys` command `yosys -p \"read_verilog and_gate.v; synth -top and_gate; write_json and_gate.json\"`\r\n\r\nA net-list file that named `and_gate.json` is created under the json file format.\r\n
\r\nClick here to see details\r\n\r\n```json\r\n{\r\n \"creator\": \"Yosys 0.13+15 (git sha1 bc027b2ca, gcc 11.3.0-1ubuntu1~22.04 -fPIC -Os)\",\r\n \"modules\": {\r\n \"and_gate\": {\r\n \"attributes\": {\r\n \"top\": \"00000000000000000000000000000001\",\r\n \"src\": \"and_gate.v:1.1-3.10\"\r\n },\r\n \"ports\": {\r\n \"a\": {\r\n \"direction\": \"input\",\r\n \"bits\": [ 2 ]\r\n },\r\n \"b\": {\r\n \"direction\": \"input\",\r\n \"bits\": [ 3 ]\r\n },\r\n \"c\": {\r\n \"direction\": \"output\",\r\n \"bits\": [ 4 ]\r\n }\r\n },\r\n \"cells\": {\r\n \"$abc$76$auto$blifparse.cc:381:parse_blif$77\": {\r\n \"hide_name\": 1,\r\n \"type\": \"$_AND_\",\r\n \"parameters\": {\r\n },\r\n \"attributes\": {\r\n },\r\n \"port_directions\": {\r\n \"A\": \"input\",\r\n \"B\": \"input\",\r\n \"Y\": \"output\"\r\n },\r\n \"connections\": {\r\n \"A\": [ 3 ],\r\n \"B\": [ 2 ],\r\n \"Y\": [ 4 ]\r\n }\r\n }\r\n },\r\n \"netnames\": {\r\n \"a\": {\r\n \"hide_name\": 0,\r\n \"bits\": [ 2 ],\r\n \"attributes\": {\r\n \"src\": \"and_gate.v:1.23-1.24\"\r\n }\r\n },\r\n \"b\": {\r\n \"hide_name\": 0,\r\n \"bits\": [ 3 ],\r\n \"attributes\": {\r\n \"src\": \"and_gate.v:1.32-1.33\"\r\n }\r\n },\r\n \"c\": {\r\n \"hide_name\": 0,\r\n \"bits\": [ 4 ],\r\n \"attributes\": {\r\n \"src\": \"and_gate.v:1.42-1.43\"\r\n }\r\n }\r\n }\r\n }\r\n }\r\n}\r\n```\r\n
\r\n\r\n---\r\n**STEP 3.** Trying to use `openroad` to do `Floorplan` (FAILED)\r\n\r\nMake a `results` folder then set its path to the `RESULTS_DIR` variable for `openroad` use to store output files\r\n```\r\n$ mkdir results\r\n$ set RESULTS_DIR results\r\n```\r\n\r\nAfter I ran `read_design -json and_gate.json` failed (missing `read_design` command), I tried `read_verilog and_gate.v` but it's still failed.\r\n\r\n```bash\r\nubuntu@ubuntu-linux:~/Desktop/ic_test$ openroad -no_init\r\nOpenROAD v2.0-6895-g5c85b36f8 \r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\nopenroad> \r\nopenroad> read_design -json and_gate.json\r\ninvalid command name \"read_design\"\r\nwhile evaluating read_design -json and_gate.json\r\nopenroad> \r\nopenroad> read_verilog and_gate.v\r\n[ERROR STA-0164] and_gate.v line 2, syntax error\r\nSTA-0164\r\nwhile evaluating read_verilog and_gate.v\r\nopenroad> \r\nopenroad>\r\n```\r\n\r\nThis is `openroad help` in my machine\r\n
\r\nClick here to see details\r\n\r\n```bash\r\nopenroad> help\r\nadd_global_connection -net\r\nadd_pad [-name name] [-type type] [-cell library_cell] [-signal signal_name]\r\n [-edge edge] [-location location] [-bump rowcol]\r\n [-padcell_to_rdl list_of_vias] [-rdl_to_bump list_of_vias] [-bondpad bondpad]\r\n [-inst_name inst_name]\r\nadd_pdn_connect [-grid grid_name] -layers list_of_2_layers\r\n [-cut_pitch pitch_value] [-fixed_vias list_of_vias]\r\n [-dont_use_vias list_of_vias] [-max_rows rows] [-max_columns columns]\r\n [-ongrid ongrid_layers] [-split_cuts split_cuts_mapping]\r\nadd_pdn_ring [-grid grid_name] -layers list_of_2_layer_names -widths\r\nadd_pdn_stripe [-grid grid_name] -layer layer_name [-width width_value]\r\n [-followpins] [-extend_to_core_ring] [-pitch pitch_value]\r\n [-spacing spacing_value] [-offset offset_value]\r\n [-starts_width (POWER|GROUND)] [-extend_to_boundary] [-snap_to_grid]\r\n [-number_of_straps count] [-nets list_of_nets]\r\nadd_to_physical_cluster\r\n [-modinst path | -inst inst_name | -physical_cluster cluster_name]\r\n cluster_name\r\nadd_worker_address [-host host] [-port port]\r\nadjust_rc [-res_factor res] [-cc_factor cc] [-gndc_factor gndc]\r\nall_clocks\r\nall_inputs\r\nall_outputs\r\nall_registers [-clock clocks] [-rise_clock clocks] [-fall_clock clocks] [-cells]\r\n [-data_pins] [-clock_pins] [-async_pins] [-output_pins] [-level_sensitive]\r\n [-edge_triggered]\r\nanalyze_power_grid [-vsrc vsrc_file ] [-outfile out_file] [-enable_em]\r\n [-em_outfile em_out_file] [-net net_name] [-dx bump_pitch_x]\r\n [-dy bump_pitch_y] [-node_density val_node_density]\r\n [-node_density_factor val_node_density_factor]\r\nassign_ground_net -domain domain_name -net snet_name\r\nassign_ndr -ndr name\r\nassign_power_net -domain domain_name -net snet_name\r\nbench_read_spef filename\r\nbench_verilog filename\r\nbench_wires [-met_cnt mcnt] [-cnt count] [-len wire_len] [-over] [-diag] [-all]\r\n [-db_only] [-under_met layer] [-w_list width] [-s_list space]\r\n [-over_dist dist] [-under_dist dist]\r\nbuffer_ports [-inputs] [-outputs] [-max_utilization util]\r\ncheck_antennas [-verbose] [-report_file report_file] [-net net]\r\ncheck_drc [-box box] [-output_file filename]\r\ncheck_placement [-verbose]\r\ncheck_power_grid [-net power_net]\r\ncheck_setup [-verbose] [-no_input_delay] [-no_output_delay] [-multiple_clock]\r\n [-no_clock] [-unconstrained_endpoints] [-loops] [-generated_clocks]\r\n [> filename] [>> filename]\r\nclear_global_connect\r\nclock_tree_synthesis [-wire_unit unit] [-buf_list buflist] [-root_buf buf]\r\n [-clk_nets nets] [-tree_buf buf] [-distance_between_buffers]\r\n [-branching_point_buffers_distance] [-clustering_exponent]\r\n [-clustering_unbalance_ratio] [-sink_clustering_size]\r\n [-sink_clustering_max_diameter] [-sink_clustering_enable] [-balance_levels]\r\n [-sink_clustering_levels levels] [-num_static_layers]\r\n [-sink_clustering_buffer]\r\nconfigure_cts_characterization [-max_cap cap] [-max_slew slew]\r\n [-slew_steps slew_steps] [-cap_steps cap_steps]\r\nconnect_pin net pin\r\nconnect_pins net pins\r\ncreate_child_physical_clusters [-top_module | -modinst path]\r\ncreate_clock [-name name] [-period period] [-waveform waveform] [-add]\r\n [-comment comment] [pins]\r\ncreate_generated_clock [-name clock_name] -source master_pin\r\n [-master_clock clock] [-divide_by divisor | -multiply_by multiplier]\r\n [-duty_cycle duty_cycle] [-invert] [-edges edge_list]\r\n [-edge_shift edge_shift_list] [-combinational] [-add] [-comment comment]\r\n port_pin_list\r\ncreate_logic_port [-direction direction] port_name\r\ncreate_menu_item [-name name] -text item_text -script tcl_script\r\n [-path menu_path] [-shortcut key_shortcut] [-echo]\r\ncreate_ndr -name name [-spacing val] [-width val] [-via val]\r\ncreate_physical_cluster cluster_name\r\ncreate_power_domain [-elements elements] name\r\ncreate_power_switch [-domain domain] [-output_supply_port output_supply_port]\r\n [-input_supply_port input_supply_port] [-control_port control_port]\r\n [-on_state on_state] name\r\ncreate_toolbar_button [-name name] -text button_text -script tcl_script [-echo]\r\ncreate_voltage_area [-name name] [-coordinate coordinates]\r\n [-guard_band_x guard_x] [-guard_band_y guard_y] cells\r\ncreate_voltage_domain domain_name -area\r\ncurrent_design [design]\r\ncurrent_instance [instance]\r\ncut_rows [-endcap_master endcap_master] [-halo_width_x halo_x]\r\n [-halo_width_y halo_y]\r\ndefine_corners corner1 [corner2]\r\ndefine_pad_cell [-name name] [-type cell_type|-fill|-corner|-bondpad|-bump]\r\n [-cell_name cell_names_per_side] [-orient orientation_per_side]\r\n [-pad_pin_name pad_pin_name] [-break_signals signal_list]\r\n [-offset cell_offset] [-physical_only]\r\ndefine_pdn_grid [-name ] [-macro] [-existing]\r\n [-grid_over_pg_pins|-grid_over_boundary]\r\n [-voltage_domains ]\r\n [-orient ] [-instances ]\r\n [-cells ] [-default] [-halo ]\r\n [-pins ] [-starts_with (POWER|GROUND)]\r\n [-obstructions ] [-power_switch_cell ]\r\n [-power_control ] [-power_control_network (STAR|DAISY)]\r\ndefine_pin_shape_pattern [-layer layer] [-x_step x_step] [-y_step y_step]\r\n [-region region] [-size size] [-pin_keepout dist]\r\ndefine_power_switch_cell -name\r\ndefine_process_corner [-ext_model_index index] filename\r\ndelete_clock [-all] clocks\r\ndelete_from_list list objs\r\ndelete_generated_clock [-all] clocks\r\ndelete_instance inst\r\ndelete_net net\r\ndelete_physical_cluster cluster_name\r\ndelete_voltage_domain domain_name\r\ndensity_fill [-rules rules_file] [-area {lx ly ux uy}]\r\ndetailed_placement [-max_displacement disp|{disp_x disp_y}]\r\ndetailed_route [-output_maze filename] [-output_drc filename]\r\n [-output_cmap filename] [-output_guide_coverage filename]\r\n [-db_process_node name] [-disable_via_gen] [-droute_end_iter iter]\r\n [-via_in_pin_bottom_layer layer] [-via_in_pin_top_layer layer]\r\n [-or_seed seed] [-or_k_ k] [-bottom_routing_layer layer]\r\n [-top_routing_layer layer] [-verbose level] [-param filename] [-distributed]\r\n [-remote_host rhost] [-remote_port rport] [-shared_volume vol]\r\n [-cloud_size sz] [-clean_patches] [-no_pin_access] [-min_access_points count]\r\n [-save_guide_updates] [-repair_pdn_vias layer]\r\ndetailed_route_debug [-pa] [-ta] [-dr] [-maze] [-net name] [-pin name]\r\n [-worker x y] [-iter iter] [-pa_markers] [-dump_dr] [-dump_dir dir]\r\n [-pa_edge] [-pa_commit]\r\ndetailed_route_run_worker [-dump_dir dir] [-worker_dir dir] [-drc_rpt drc]\r\ndetailed_route_worker_debug [-maze_end_iter iter] [-drc_cost d_cost]\r\n [-marker_cost m_cost] [-fixed_shape_cost f_cost] [-marker_decay m_decay]\r\n [-ripup_mode mode] [-follow_guide f_guide]\r\ndiff_spef [-file filename] [-r_res] [-r_cap] [-r_cc_cap] [-r_conn]\r\ndisconnect_pin net -all|pin\r\ndisconnect_pins net -all|pins\r\ndisplay_timing_cone pin [-fanin] [-fanout] [-off]\r\ndraw_route_guides net_names [-show_pin_locations]\r\nelapsed_run_time\r\nestimate_parasitics -placement|-global_routing\r\nextract_parasitics [-ext_model_file filename] [-corner_cnt count]\r\n [-max_res ohms] [-coupling_threshold fF] [-debug_net_id id] [-lef_res]\r\n [-cc_model track] [-context_depth depth] [-no_merge_via_res]\r\nfiller_placement [-prefix prefix] filler_masters\r\nfind_timing_paths [-from from_list|-rise_from from_list|-fall_from from_list]\r\n [-through through_list|-rise_through through_list|-fall_through through_list]\r\n [-to to_list|-rise_to to_list|-fall_to to_list]\r\n [-path_delay min|min_rise|min_fall|max|max_rise|max_fall|min_max]\r\n [-unconstrained] [-corner corner] [-group_count path_count]\r\n [-endpoint_count path_count] [-unique_paths_to_endpoint]\r\n [-slack_max slack_max] [-slack_min slack_min] [-sort_by_slack]\r\n [-path_group group_name]\r\nfocus_net net [-remove] [-clear]\r\nget_cells [-hierarchical] [-hsc separator] [-filter expr] [-regexp] [-nocase]\r\n [-quiet] [-of_objects objects] [patterns]\r\nget_clocks [-regexp] [-nocase] [-quiet] patterns\r\nget_fanin -to sink_list [-flat] [-only_cells] [-startpoints_only]\r\n [-levels level_count] [-pin_levels pin_count]\r\n [-trace_arcs timing|enabled|all]\r\nget_fanout -from source_list [-flat] [-only_cells] [-endpoints_only]\r\n [-levels level_count] [-pin_levels pin_count]\r\n [-trace_arcs timing|enabled|all]\r\nget_full_name objects\r\nget_lib_cells [-hsc separator] [-regexp] [-nocase] [-quiet]\r\n [-of_objects objects] [patterns]\r\nget_lib_pins [-hsc separator] [-regexp] [-nocase] [-quiet] patterns\r\nget_libs [-regexp] [-nocase] [-quiet] patterns\r\nget_name objects\r\nget_nets [-hierarchical] [-hsc separator] [-regexp] [-nocase] [-quiet]\r\n [-of_objects objects] [patterns]\r\nget_pins [-hierarchical] [-hsc separator] [-quiet] [-filter expr] [-regexp]\r\n [-nocase] [-of_objects objects] patterns\r\nget_ports [-quiet] [-filter expr] [-regexp] [-nocase] [-of_objects objects]\r\n [patterns]\r\nget_property [-object_type cell|pin|net|port|clock|timing_arc] object property\r\nget_timing_edges [-from from_pin] [-to to_pin] [-of_objects objects]\r\n [-filter expr]\r\nglobal_connect\r\nglobal_placement [-skip_initial_place] [-skip_nesterov_place] [-timing_driven]\r\n [-routability_driven] [-disable_timing_driven] [-disable_routability_driven]\r\n [-incremental] [-force_cpu] [-skip_io] [-bin_grid_count grid_count]\r\n [-density target_density] [-init_density_penalty init_density_penalty]\r\n [-init_wirelength_coef init_wirelength_coef] [-min_phi_coef min_phi_coef]\r\n [-max_phi_coef max_phi_coef] [-reference_hpwl reference_hpwl]\r\n [-overflow overflow] [-initial_place_max_iter initial_place_max_iter]\r\n [-initial_place_max_fanout initial_place_max_fanout]\r\n [-routability_check_overflow routability_check_overflow]\r\n [-routability_max_density routability_max_density]\r\n [-routability_max_bloat_iter routability_max_bloat_iter]\r\n [-routability_max_inflation_iter routability_max_inflation_iter]\r\n [-routability_target_rc_metric routability_target_rc_metric]\r\n [-routability_inflation_ratio_coef routability_inflation_ratio_coef]\r\n [-routability_max_inflation_ratio routability_max_inflation_ratio]\r\n [-routability_rc_coefficients routability_rc_coefficients]\r\n [-timing_driven_net_reweight_overflow timing_driven_net_reweight_overflow]\r\n [-timing_driven_net_weight_max timing_driven_net_weight_max]\r\n [-timing_driven_nets_percentage timing_driven_nets_percentage]\r\n [-pad_left pad_left] [-pad_right pad_right]\r\nglobal_route [-guide_file out_file] [-congestion_iterations iterations]\r\n [-congestion_report_file file_name] [-grid_origin origin]\r\n [-overflow_iterations iterations] [-critical_nets_percentage percent]\r\n [-allow_congestion] [-allow_overflow] [-verbose]\r\nglobal_route_debug [-st]\r\ngroup_path -name group_name [-weight weight] [-critical_range range] [-default]\r\n [-comment comment] [-from from_list] [-rise_from from_list]\r\n [-fall_from from_list] [-through through_list] [-rise_through through_list]\r\n [-fall_through through_list] [-to to_list] [-rise_to to_list]\r\n [-fall_to to_list]\r\nhelp [pattern]\r\nhighlight_path [-min|-max] pin\r\nimprove_placement [-random_seed seed] [-max_displacement disp|{disp_x disp_y}]\r\ninitialize_floorplan [-utilization util] [-aspect_ratio ratio]\r\n [-core_space space | {bottom top left right}] [-die_area {lx ly ux uy}]\r\n [-core_area {lx ly ux uy}] [-site site_name]\r\ninitialize_padring [-signal_assignment_file signal_assigment_file]\r\ninsert_buffer buffer_name buffer_cell net load_pins buffer_out_net_name\r\ninsert_tiecells tie_pin [-prefix prefix]\r\nlink_design [top_cell_name]\r\nlog_begin filename\r\nlog_end\r\nmacro_placement [-halo {vertical_width horizontal_width}]\r\n [-channel {vertical_width horizontal_width}] [-fence_region {lx ly ux uy}]\r\n [-snap_layer snap_layer_number] [-style corner_max_wl|corner_min_wl]\r\nmacro_placement_debug [-partitions]\r\nmake_instance inst_path lib_cell\r\nmake_net\r\nmake_tracks [layer] [-x_pitch x_pitch] [-y_pitch y_pitch] [-x_offset x_offset]\r\n [-y_offset y_offset]\r\noptimize_mirroring\r\npdngen [-skip_trim] [-dont_add_pins] [-reset] [-ripup] [-report_only]\r\n [-failed_via_report file]\r\npin_access [-db_process_node name] [-bottom_routing_layer layer]\r\n [-top_routing_layer layer] [-min_access_points count] [-verbose level]\r\nplace_cell -inst_name inst_name [-cell library_cell] -origin xy_origin -orient\r\nplace_pin [-pin_name pin_name] [-layer layer] [-location location]\r\n [-pin_size pin_size] [-force_to_die_boundary]\r\nplace_pins [-hor_layers h_layers] [-ver_layers v_layers] [-random_seed seed]\r\n [-random] [-corner_avoidance distance] [-min_distance min_dist]\r\n [-min_distance_in_tracks] [-exclude region] [-group_pins pin_list]\r\nread_db filename\r\nread_def [-floorplan_initialize|-incremental] [-continue_on_errors] filename\r\nread_guides file_name\r\nread_lef [-tech] [-library] filename\r\nread_liberty [-corner corner] [-min] [-max] [-no_latch_infer] filename\r\nread_parasitics [-min] [-max] [-elmore] [-path path] [-increment]\r\n [-pin_cap_included] [-keep_capacitive_coupling]\r\n [-coupling_reduction_factor factor] [-reduce_to pi_elmore|pi_pole_residue2]\r\n [-delete_after_reduce] [-quiet] [-save] filename\r\nread_power_activities [-scope scope] -vcd filename\r\nread_sdc [-echo] filename\r\nread_sdf [-path path] [-corner corner] [-cond_use min|max|min_max]\r\n [-unescaped_dividers] filename\r\nread_spef [-corner corner] [-min] [-max] [-path path] [-pin_cap_included]\r\n [-keep_capacitive_coupling] [-coupling_reduction_factor factor]\r\n [-reduce_to pi_elmore|pi_pole_residue2] [-delete_after_reduce] [-quiet]\r\n [-save] filename\r\nread_upf [-file file]\r\nread_verilog filename\r\nremove_buffers\r\nremove_fillers\r\nremove_from_physical_cluster\r\n [-parent_module module_name -modinst modinst_name | -inst inst_name | -physical_cluster cluster_name]\r\n cluster_name\r\nrepair_antennas [diode_cell/diode_port] [-iterations iterations]\r\n [-ratio_margin ratio_margin]\r\nrepair_clock_inverters\r\nrepair_clock_nets [-max_wire_length max_wire_length]\r\nrepair_design [-max_wire_length max_wire_length] [-max_utilization util]\r\n [-slew_margin slack_margin] [-cap_margin cap_margin]\r\nrepair_pdn_vias [-net net_name] -all\r\nrepair_tie_fanout lib_port [-separation dist] [-verbose]\r\nrepair_timing [-setup] [-hold] [-setup_margin setup_margin]\r\n [-hold_margin hold_margin] [-allow_setup_violations]\r\n [-repair_tns tns_end_percent] [-max_buffer_percent buffer_percent]\r\n [-max_utilization util]\r\nreplace_cell instance lib_cell\r\nreport_annotated_check [-setup] [-hold] [-recovery] [-removal] [-nochange]\r\n [-width] [-period] [-max_skew] [-max_line lines] [-list_annotated]\r\n [-list_not_annotated] [-constant_arcs]\r\nreport_annotated_delay [-cell] [-net] [-from_in_ports] [-to_out_ports]\r\n [-max_line lines] [-list_annotated] [-list_not_annotated] [-constant_arcs]\r\nreport_arrival pin\r\nreport_cell [-connections] [-verbose] instance_path [> filename] [>> filename]\r\nreport_check_types [-violators] [-verbose] [-corner corner]\r\n [-format slack_only|end] [-max_delay] [-min_delay] [-recovery] [-removal]\r\n [-clock_gating_setup] [-clock_gating_hold] [-max_slew] [-min_slew]\r\n [-max_fanout] [-min_fanout] [-max_capacitance] [-min_capacitance]\r\n [-min_pulse_width] [-min_period] [-max_skew] [-net net] [-digits digits]\r\n [-no_line_splits] [> filename] [>> filename]\r\nreport_checks [-from from_list|-rise_from from_list|-fall_from from_list]\r\n [-through through_list|-rise_through through_list|-fall_through through_list]\r\n [-to to_list|-rise_to to_list|-fall_to to_list] [-unconstrained]\r\n [-path_delay min|min_rise|min_fall|max|max_rise|max_fall|min_max]\r\n [-corner corner] [-group_count path_count] [-endpoint_count path_count]\r\n [-unique_paths_to_endpoint] [-slack_max slack_max] [-slack_min slack_min]\r\n [-sort_by_slack] [-path_group group_name]\r\n [-format full|full_clock|full_clock_expanded|short|end|summary]\r\nreport_clock_min_period [-clocks clocks] [-include_port_paths]\r\nreport_clock_properties [clocks]\r\nreport_clock_skew [-setup|-hold] [-clock clocks] [-corner corner]]\r\n [-digits digits]\r\nreport_clock_skew_metric [-setup] | [-hold]\r\nreport_constant pin|instance|net\r\nreport_cts [-out_file file]\r\nreport_dcalc [-from from_pin] [-to to_pin] [-corner corner] [-min] [-max]\r\n [-digits digits]\r\nreport_design_area\r\nreport_design_area_metrics\r\nreport_disabled_edges\r\nreport_edges [-from from_pin] [-to to_pin]\r\nreport_erc_metrics\r\nreport_floating_nets [-verbose]\r\nreport_global_connect\r\nreport_instance [-connections] [-verbose] instance_path [> filename]\r\n [>> filename]\r\nreport_lib_cell cell_name [> filename] [>> filename]\r\nreport_long_wires count\r\nreport_net [-connections] [-verbose] [-corner corner] [-digits digits]\r\n [-hier_pins] net_path [> filename] [>> filename]\r\nreport_object_full_names objects\r\nreport_object_names objects\r\nreport_parasitic_annotation -report_unannotated\r\nreport_path [-min|-max]\r\n [-format full|full_clock|full_clock_expanded|short|end|summary]\r\nreport_physical_clusters\r\nreport_pin [-corner corner] [-digits digits] pin [> filename] [>> filename]\r\nreport_power [-instances instances] [-corner corner] [-digits digits]\r\n [> filename] [>> filename]\r\nreport_power_metric [-corner corner_name]\r\nreport_pulse_width_checks [-verbose] [-corner corner] [-digits digits]\r\n [-no_line_splits] [pins] [> filename] [>> filename]\r\nreport_required pin\r\nreport_slack pin\r\nreport_slews [-corner corner] pin\r\nreport_tns [-digits digits]\r\nreport_tns_metric [-setup] | [-hold]\r\nreport_units\r\nreport_units_metric\r\nreport_voltage_domains\r\nreport_wire_length [-net net_list] [-file file] [-global_route]\r\n [-detailed_route] [-verbose]\r\nreport_wns [-digits digits]\r\nreport_worst_negative_slack_metric [-setup] | [-hold]\r\nreport_worst_slack [-min] [-max] [-digits digits]\r\nreport_worst_slack_metric [-setup] | [-hold]\r\nrestructure [-slack_threshold slack] [-depth_threshold depth]\r\n [-target area|timing] [-liberty_file liberty_file] [-tielo_port tielow_port]\r\n [-tiehi_port tiehigh_port] [-work_dir workdir_name]\r\nrtl_macro_placer -max_num_macro max_num_macro -min_num_macro min_num_macro\r\n -max_num_inst max_num_inst -min_num_inst min_num_inst -tolerance tolerance\r\n -max_num_level max_num_level -coarsening_ratio coarsening_ratio\r\n -num_bundled_ios num_bundled_ios -large_net_threshold large_net_threshold\r\n -signature_net_threshold signature_net_threshold -halo_width halo_width\r\n -fence_lx fence_lx -fence_ly fence_ly -fence_ux fence_ux -fence_uy fence_uy\r\n -area_weight area_weight -outline_weight outline_weight -wirelength_weight\r\n wirelength_weight -guidance_weight guidance_weight -fence_weight fence_weight\r\n -boundary_weight boundary_weight -notch_weight notch_weight\r\n -macro_blockage_weight macro_blockage_weight -pin_access_th pin_access_th\r\n -target_util target_util -target_dead_space target_dead_space -min_ar min_ar\r\n -snap_layer snap_layer -report_directory report_directory\r\nrun_load_balancer [-host host] [-port port] [-workers_domain workers_domain]\r\nrun_worker [-host host] [-port port] [-i]\r\nsave_image [-area {x0 y0 x1 y1}] [-resolution microns_per_pixel]\r\n [-display_option option] path\r\nselect -type object_type [-name name_regex] [-case_insensitive]\r\n [-highlight group]\r\nset_assigned_check -setup|-hold|-recovery|-removal [-rise] [-fall]\r\n [-corner corner] [-min] [-max] [-from from_pins] [-to to_pins]\r\n [-clock rise|fall] [-cond sdf_cond] check_value\r\nset_assigned_delay -cell|-net [-rise] [-fall] [-corner corner] [-min] [-max]\r\n [-from from_pins] [-to to_pins] delay\r\nset_assigned_transition [-rise] [-fall] [-corner corner] [-min] [-max] slew pins\r\nset_bump -row row -col col [(-power|-ground|-net) net_name] [-remove]\r\nset_bump_options [-pitch pitch] [-bump_pin_name pin_name]\r\n [-spacing_to_edge spacing] [-offset {x_offset y_offset}]\r\n [-array_size {rows columns}] [-cell_name bump_cell_table]\r\n [-num_pads_per_tile value] [-rdl_layer name] [-rdl_width value]\r\n [-rdl_spacing value] [-rdl_route_style (45|90|under)]\r\n [-padcell_to_rdl list_of_vias] [-rdl_to_bump list_of_vias]\r\n [-rdl_cover_file_name rdl_file_name]\r\nset_case_analysis 0|1|zero|one|rise|rising|fall|falling pins\r\nset_clock_gating_check [-setup setup_time] [-hold hold_time] [-rise] [-fall]\r\n [-low] [-high] [objects]\r\nset_clock_groups [-name name] [-logically_exclusive] [-physically_exclusive]\r\n [-asynchronous] [-allow_paths] [-comment comment] -group clocks\r\nset_clock_latency [-source] [-clock clock] [-rise] [-fall] [-min] [-max]\r\n [-early] [-late] delay objects\r\nset_clock_sense [-positive] [-negative] [-pulse pulse_type] [-stop_propagation]\r\n [-clock clocks] pins\r\nset_clock_transition [-rise] [-fall] [-min] [-max] transition clocks\r\nset_clock_uncertainty [-from|-rise_from|-fall_from from_clock]\r\n [-to|-rise_to|-fall_to to_clock] [-rise] [-fall] [-setup] [-hold] uncertainty\r\n [objects]\r\nset_cmd_units [-capacitance cap_unit] [-resistance res_unit] [-time time_unit]\r\n [-voltage voltage_unit] [-current current_unit] [-power power_unit]\r\n [-distance distance_unit]\r\nset_data_check [-from from_pin] [-rise_from from_pin] [-fall_from from_pin]\r\n [-to to_pin] [-rise_to to_pin] [-fall_to to_pin] [-setup | -hold]\r\n [-clock clock] margin\r\nset_debug_level tool group level\r\nset_disable_inferred_clock_gating objects\r\nset_disable_timing [-from from_port] [-to to_port] objects\r\nset_domain_area domain_name -area\r\nset_dont_touch nets_instances\r\nset_dont_use lib_cells\r\nset_drive [-rise] [-fall] [-min] [-max] resistance ports\r\nset_driving_cell [-lib_cell cell] [-library library] [-rise] [-fall] [-min]\r\n [-max] [-pin pin] [-from_pin from_pin] [-input_transition_rise trans_rise]\r\n [-input_transition_fall trans_fall] [-multiply_by factor] [-dont_scale]\r\n [-no_design_rule] ports\r\nset_false_path [-setup] [-hold] [-rise] [-fall] [-reset_path] [-comment comment]\r\n [-from from_list] [-rise_from from_list] [-fall_from from_list]\r\n [-through through_list] [-rise_through through_list]\r\n [-fall_through through_list] [-to to_list] [-rise_to to_list]\r\n [-fall_to to_list]\r\nset_fanout_load fanout ports\r\nset_global_routing_layer_adjustment layer adj\r\nset_global_routing_random [-seed seed]\r\n [-capacities_perturbation_percentage percent] [-perturbation_amount value]\r\nset_global_routing_region_adjustment region [-layer layer]\r\n [-adjustment adjustment]\r\nset_hierarchy_separator seperator\r\nset_ideal_latency [-rise] [-fall] [-min] [-max] delay objects\r\nset_ideal_net nets\r\nset_ideal_network [-no_propagation] objects\r\nset_ideal_transition [-rise] [-fall] [-min] [-max] transition_time objects\r\nset_input_delay [-rise] [-fall] [-max] [-min] [-clock clock] [-clock_fall]\r\n [-reference_pin ref_pin] [-source_latency_included]\r\n [-network_latency_included] [-add_delay] delay port_pin_list\r\nset_input_transition [-rise] [-fall] [-min] [-max] transition ports\r\nset_io_pin_constraint [-direction direction] [-pin_names names] [-region region]\r\n [-mirrored_pins pins]\r\nset_isolation [-domain domain] [-applies_to applies_to]\r\n [-clamp_value clamp_value] [-isolation_signal isolation_signal]\r\n [-isolation_sense isolation_sense] [-location location] [-update] name\r\nset_layer_rc [-layer layer] [-via via_layer] [-capacitance cap]\r\n [-resistance res] [-corner corner]\r\nset_level_shifter_strategy [-rule rule_type]\r\nset_level_shifter_threshold [-voltage volt]\r\nset_load [-rise] [-fall] [-max] [-min] [-subtract_pin_load] [-pin_load]\r\n [-wire_load] capacitance objects\r\nset_logic_dc port_list\r\nset_logic_one port_list\r\nset_logic_zero port_list\r\nset_macro_extension extension\r\nset_max_area area\r\nset_max_capacitance cap objects\r\nset_max_delay [-rise] [-fall] [-ignore_clock_latency] [-reset_path]\r\n [-comment comment] [-from from_list] [-rise_from from_list]\r\n [-fall_from from_list] [-through through_list] [-rise_through through_list]\r\n [-fall_through through_list] [-to to_list] [-rise_to to_list]\r\n [-fall_to to_list] delay\r\nset_max_dynamic_power power [unit]\r\nset_max_fanout fanout objects\r\nset_max_leakage_power power [unit]\r\nset_max_time_borrow limit objects\r\nset_max_transition [-clock_path] [-data_path] [-rise] [-fall] slew objects\r\nset_min_capacitance cap objects\r\nset_min_delay [-rise] [-fall] [-ignore_clock_latency] [-reset_path]\r\n [-comment comment] [-from from_list] [-rise_from from_list]\r\n [-fall_from from_list] [-through through_list] [-rise_through through_list]\r\n [-fall_through through_list] [-to to_list] [-rise_to to_list]\r\n [-fall_to to_list] delay\r\nset_min_pulse_width [-low] [-high] value [objects]\r\nset_multicycle_path [-setup] [-hold] [-rise] [-fall] [-start] [-end]\r\n [-reset_path] [-comment comment] [-from from_list] [-rise_from from_list]\r\n [-fall_from from_list] [-through through_list] [-rise_through through_list]\r\n [-fall_through through_list] [-to to_list] [-rise_to to_list]\r\n [-fall_to to_list] path_multiplier\r\nset_operating_conditions [-analysis_type single|bc_wc|on_chip_variation]\r\n [-library lib] [condition] [-min min_condition] [-max max_condition]\r\n [-min_library min_lib] [-max_library max_lib]\r\nset_output_delay [-rise] [-fall] [-max] [-min] [-clock clock] [-clock_fall]\r\n [-reference_pin ref_pin] [-source_latency_included]\r\n [-network_latency_included] [-add_delay] delay port_pin_list\r\nset_padring_options [-type (flipchip|wirebond)] [-power power_nets]\r\n [-ground ground_nets] [-core_area core_area] [-die_area die_area]\r\n [-offsets offsets] [-pad_inst_pattern pad_inst_pattern]\r\n [-pad_pin_pattern pad_pin_pattern] [-pad_pin_layer pin_layer_name]\r\n [-pin_layer layer_name] [-connect_by_abutment signal_list]\r\n [-allow_filler_overlap]\r\nset_pdnsim_net_voltage [-net net_name] [-voltage volt]\r\nset_pin_length [-hor_length h_length] [-ver_length v_length]\r\nset_pin_length_extension [-hor_extension h_ext] [-ver_extension v_ext]\r\nset_pin_offset offset\r\nset_pin_thick_multiplier [-hor_multiplier h_mult] [-ver_multiplier v_mult]\r\nset_placement_padding -global|-masters masters|-instances insts\r\n [-right site_count] [-left site_count] [instances]\r\nset_pocv_sigma_factor factor\r\nset_port_fanout_number [-max] [-min] fanout ports\r\nset_power_activity [-global] [-input] [-input_ports ports] [-pins pins]\r\n [-activity activity] [-duty duty]\r\nset_propagated_clock objects\r\nset_pvt insts [-min] [-max] [-process process] [-voltage voltage]\r\n [-temperature temperature]\r\nset_resistance [-min] [-max] resistance nets\r\nset_routing_alpha alpha [-net net_name] [-min_fanout fanout] [-min_hpwl hpwl]\r\n [-clock_nets]\r\nset_routing_layers [-signal layers] [-clock layers]\r\nset_sense [-type clock|data] [-positive] [-negative] [-pulse pulse_type]\r\n [-stop_propagation] [-clocks clocks] pins\r\nset_timing_derate -early|-late [-rise] [-fall] [-clock] [-data] [-net_delay]\r\n [-cell_delay] [-cell_check] derate [objects]\r\nset_units [-time time_unit] [-capacitance cap_unit] [-resistance res_unit]\r\n [-voltage voltage_unit] [-current current_unit] [-power power_unit]\r\n [-distance distance_unit]\r\nset_voltage_domain -name domain_name -power power_net_name -ground\r\n ground_net_name [-region region_name]\r\n [-secondary_power secondary_power_net_name]\r\n [-switched_power switched_power_net_name]\r\nset_wire_load_min_block_size block_size\r\nset_wire_load_mode top|enclosed|segmented\r\nset_wire_load_model -name model_name [-library lib_name] [-min] [-max] [objects]\r\nset_wire_load_selection_group [-library lib] [-min] [-max] group_name [objects]\r\nset_wire_rc [-clock] [-signal] [-layer layer_name] [-resistance res]\r\n [-capacitance cap] [-corner corner]\r\nshow_copying\r\nshow_splash\r\nshow_warranty\r\nsource [-echo] [-verbose] filename [> filename] [>> filename]\r\nsuppress_message tool id\r\ntapcell [-tapcell_master tapcell_master] [-tap_prefix tap_prefix]\r\n [-endcap_master endcap_master] [-endcap_cpp endcap_cpp]\r\n [-endcap_prefix endcap_prefix] [-distance dist] [-halo_width_x halo_x]\r\n [-halo_width_y halo_y] [-tap_nwin2_master tap_nwin2_master]\r\n [-tap_nwin3_master tap_nwin3_master] [-tap_nwout2_master tap_nwout2_master]\r\n [-tap_nwout3_master tap_nwout3_master]\r\n [-tap_nwintie_master tap_nwintie_master]\r\n [-tap_nwouttie_master tap_nwouttie_master]\r\n [-cnrcap_nwin_master cnrcap_nwin_master]\r\n [-cnrcap_nwout_master cnrcap_nwout_master]\r\n [-incnrcap_nwin_master incnrcap_nwin_master]\r\n [-incnrcap_nwout_master incnrcap_nwout_master] [-tbtie_cpp tbtie_cpp]\r\n [-no_cell_at_top_bottom]\r\ntapcell_ripup [-tap_prefix tap_prefix] [-endcap_prefix endcap_prefix]\r\ntriton_part_design [-num_parts num_parts]\r\n [-balance_constraint balance_constraint] [-seed seed]\r\n [-solution_file file_name] [-paths_file file_name]\r\n [-hypergraph_file file_name]\r\ntriton_part_hypergraph -hypergraph_file hypergraph_file [-fixed_file fixed_file]\r\n [-num_parts num_parts] [-balance_constraint balance_constraint]\r\n [-vertex_dimension vertex_dimension]\r\n [-hyperedge_dimension hyperedge_dimension] [-seed seed]\r\nunset_case_analysis pins\r\nunset_clock_groups [-logically_exclusive] [-physically_exclusive]\r\n [-asynchronous] [-name names] [-all]\r\nunset_clock_latency [-source] [-clock clock] objects\r\nunset_clock_transition clocks\r\nunset_clock_uncertainty [-from|-rise_from|-fall_from from_clock]\r\n [-to|-rise_to|-fall_to to_clock] [-rise] [-fall] [-setup] [-hold] [objects]\r\nunset_data_check [-from from_pin] [-rise_from from_pin] [-fall_from from_pin]\r\n [-to to_pin] [-rise_to to_pin] [-fall_to to_pin] [-setup | -hold]\r\n [-clock clock]\r\nunset_disable_inferred_clock_gating objects\r\nunset_disable_timing [-from from_port] [-to to_port] objects\r\nunset_dont_touch nets_instances\r\nunset_dont_use lib_cells\r\nunset_generated_clock [-all] clocks\r\nunset_input_delay [-rise] [-fall] [-max] [-min] [-clock clock] [-clock_fall]\r\n port_pin_list\r\nunset_output_delay [-rise] [-fall] [-max] [-min] [-clock clock] [-clock_fall]\r\n port_pin_list\r\nunset_path_exceptions [-setup] [-hold] [-rise] [-fall] [-from from_list]\r\n [-rise_from from_list] [-fall_from from_list] [-through through_list]\r\n [-rise_through through_list] [-fall_through through_list] [-to to_list]\r\n [-rise_to to_list] [-fall_to to_list]\r\nunset_propagated_clock objects\r\nunset_timing_derate\r\nuse_interface_cell [-domain domain] [-strategy strategy] [-lib_cells lib_cells]\r\nuser_run_time\r\nwith_output_to_variable var\r\nwrite_abstract_lef [-bloat_factor amount|-bloat_occupied_layers] filename\r\nwrite_cdl [-include_fillers] -masters masters_filenames out_filename\r\nwrite_db filename\r\nwrite_def [-version version] filename\r\nwrite_guides filename\r\nwrite_lef filename\r\nwrite_path_spice -path_args path_args -spice_directory spice_directory\r\n -lib_subckt_file lib_subckts_file -model_file model_file -power power -ground\r\n ground\r\nwrite_pg_spice [-vsrc vsrc_file ] [-outfile out_file] [-net net_name]\r\n [-dx bump_pitch_x] [-dy bump_pitch_y]\r\nwrite_rules [-file filename] [-dir dir] [-name name] [-pattern pattern]\r\nwrite_sdc [-map_hpins] [-digits digits] [-gzip] [-no_timestamp] filename\r\nwrite_sdf [-corner corner] [-divider /|.] [-include_typ] [-digits digits]\r\n [-gzip] [-no_timestamp] [-no_version] filename\r\nwrite_spef [-net_id net_id] [-nets nets] filename\r\nwrite_timing_model [-corner corner] [-library_name lib_name]\r\n [-cell_name cell_name] filename\r\nwrite_verilog [-sort] [-include_pwr_gnd] [-remove_cells cells] filename\r\nopenroad>\r\n```\r\n
\r\n\r\n---\r\nThank you so much,\r\nVic P."}, {"assistant": "1. OpenROAD only supports verilog netlists.\r\n2. Your SDC file mentions a clock that does not exist. You have `[get_ports clk]` but there is no `clk` input in your design.\r\n\r\nYou should probably be using [OpenROAD Flow Scripts](https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts) to run a flow instead of manually running yosys."}]} +{"messages": [{"user": "I was running the riscv model with default setup. When I was trying to find wns for hold after the full run (or in cts, route). It is returning as INF.\r\n\r\nCommand:\r\n```\r\nreport_worst_slack -min\r\n```\r\nReturns `worst slack INF`\r\n\r\n**pdk:** asap7\r\n**design:** riscv32i\r\n\r\nAny idea why is that and how to solve it?"}, {"assistant": "In which PDK? How did you load the design? Please give specific steps to reproduce the issue."}, {"assistant": "I guess you meant ```make gui_6_final.odb``` without the 'e'. I get:\r\n\r\n```\r\n>>> report_worst_slack -min\r\nworst slack 40.29\r\n```\r\n\r\nWhat commit id are you using for OR & ORFS? This would have worked better as an issue with the required info."}]} +{"messages": [{"user": "Hi OpenRoad devs,\r\n\r\nPart of the scan architect step (to create the scan chains) is to see what clock is driving each one of the cells of the design. I was wondering: what is the best way in OpenRoad to find out what is the clock driver and the edge (Rising or Falling) of a given cell?.\r\n\r\nI can always traverse back the nets from a clock pin but maybe there is already some infra that I can use for this.\r\n\r\nThanks!,\r\nFelipe"}, {"assistant": "I think Sta::clocks(const Pin *pin) is what you want."}]} +{"messages": [{"user": "I was successfully able to run cmake and then make. However, output of cmake has following two messages which seems problematic to me. How do I resolve these?\r\n\r\n-- GUI is not enabled\r\n-- Could NOT find VTune (missing: VTune_LIBRARIES VTune_INCLUDE_DIRS)\r\n\r\nI ran following command\r\ncmake .. -DCMAKE_INSTALL_PREFIX=/home/msingh/openRoad -DPYTHON_INCLUDE_DIR=$(python3 -c \"import sysconfig; print(sysconfig.get_path('include'))\") -DPYTHON_LIBRARY=$(python3 -c\\\r\n \"import sysconfig; print(sysconfig.get_config_var('LIBDIR'))\")\r\n\r\nI also ran make afterwards, which seems to finish. There are bunch of warnings but no error message. Where do I find the executable. I don't find it in CMAKE_INSTALL_PREFIX/bin directory.\r\n\r\nDoes it mean that installation didn't complete? \r\n\r\nI am looking for some help because I am stuck in the installation.\r\n\r\nI just cleared the buffer that has log, but I can redo those steps if you need the complete log output."}, {"assistant": "Vtune is unimportant unless you are a developer of OR.\r\n\r\nThe GUI suggests that you don't have Qt installed. Did you run the dependency installer?"}, {"user": "Thanks Maliberty for response.\r\n\r\nI followed the steps \"https://openroad-flow-scripts.readthedocs.io/en/latest/user/BuildLocally.html\" and was able to build with hiccups. \r\nHow do I make sure Qt is installed? BTW - I am trying to install it on Linux RH8. Is it supported platform?\r\n\r\nWhen I try to invoke it, I get this missing library error.\r\nopenroad -help\r\nopenroad: error while loading shared libraries: libortools.so.9: cannot open shared object file: No such file or directory\r\n"}, {"assistant": "I don't know what OS you are on and you haven't included any logs. If you look at https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/etc/DependencyInstaller.sh it you'll see it references Qt libraries."}, {"user": "I am trying to build it on RH8. I am really stuck at this point now. I ran \"sudo ./DependencyInstaller.sh\" successfully. \r\n\r\nI can check that qt5 is installed.\r\n\r\n[msingh@lnx-msingh cv6 /tmp]$ sudo yum -y install qt5-srpm-macros.noarch\r\nLast metadata expiration check: 0:07:51 ago on Sun 12 Mar 2023 12:19:34 AM PST.\r\nPackage qt5-srpm-macros-5.12.5-3.el8.noarch is already installed.\r\nDependencies resolved.\r\nNothing to do.\r\n\r\nWhen I run cmake to create build files, I get that \"GUI is not enabled\". Is there a switch I need to pass to cmake. Here is my command and it's output.\r\n\r\n[msingh@lnx-msingh cv6 build]$ cmake .. -DPYTHON_INCLUDE_DIR=/cv6/tools2/tv2/release/Python3/3.9.0/include/python3.9 -DPYTHON_LIBRARY=/cv6/tools2/tv2/release/Python3/3.9.0/lib -Dortools_DIR=/opt/or-tools\r\n-- OpenROAD version: v2.0-7131-g1d8d24209\r\n-- System name: Linux\r\n-- Compiler: GNU 8.3.1\r\n-- Build type: RELEASE\r\n-- Install prefix: /usr/local\r\n-- C++ Standard: 17\r\n-- C++ Standard Required: ON\r\n-- C++ Extensions: OFF\r\n-- TCL library: /usr/lib64/libtcl.so\r\n-- TCL header: /usr/include/tcl.h\r\n-- TCL readline library: /usr/lib64/libtclreadline.so\r\n-- TCL readline header: /usr/include\r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found version \"1.80.0\")\r\n-- boost: 1.80.0\r\n-- spdlog: 1.8.1\r\n-- STA version: 2.4.0\r\n-- STA git sha: f84e617fc435d2d280a3f76045aa461afa386e2b\r\n-- System name: Linux\r\n-- Compiler: GNU 8.3.1\r\n-- Build type: RELEASE\r\n-- Build CXX_FLAGS: -O3 -DNDEBUG\r\n-- Install prefix: /usr/local\r\n-- TCL library: /usr/lib64/libtcl.so\r\n-- TCL header: /usr/include/tcl.h\r\n-- SSTA: 0\r\n-- STA executable: /dump/vlsidump302/msingh/OpenROAD/src/sta/app/sta\r\n-- GPU is not enabled\r\n-- GUI is not enabled\r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found version \"1.80.0\") found components: serialization\r\n-- Could NOT find VTune (missing: VTune_LIBRARIES VTune_INCLUDE_DIRS)\r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found suitable version \"1.80.0\", minimum required is \"1.78\")\r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found version \"1.80.0\") found components: serialization system thread\r\n-- TCL readline enabled\r\n-- Tcl Extended disabled\r\n-- Python3 disabled\r\n-- Configuring done\r\n-- Generating done\r\n-- Build files have been written to: /dump/vlsidump302/msingh/OpenROAD/build\r\n"}, {"assistant": "What OS are you using? Is qt in the default location?"}, {"assistant": "@msingh9 \r\nCan you try docker based installation [steps](https://openroad-flow-scripts.readthedocs.io/en/latest/user/BuildWithDocker.html) ?"}, {"user": "Thank you everyone for support. I finally managed to make it work on RH8. It is exciting to see this tool in action. I really like to appreciate everyone effort to make this open-source magic. I will post my results once I can make it work."}]} +{"messages": [{"user": "Hi!\r\n\r\nI would like to call the TCL command `save_image` and include the heatmap values on the layout.\r\n\r\nI noticed that by manually clicking on the visibility of a heatmap (such as \"Placement Density\") the image provided by `save_image` will include the heatmap.\r\n\r\nMy question is how to do this programmatically? I have a TCL script where I save the data with `gui::dump_heatmap` and I would like to also save the image with heat values afterwards. How can I toggle the visibility of heatmaps with my TCL script?"}, {"assistant": "See gui::set_display_controls in https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/gui \r\n\r\nOur nightly CI uses https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/blob/master/flow/scripts/save_images.tcl which is a good reference. "}]} +{"messages": [{"user": "HI All,\r\n\r\nAfter installing the dependencies we re stuck with cmake errors and would appreciate your help in fixing them. Attaching the error snippet for reference.\r\n\"Cmake\r\n"}, {"assistant": "attach log `build_openroad.log`"}, {"user": "[openroad_build.log](https://github.com/The-OpenROAD-Project/OpenROAD/files/10897535/openroad_build.log)\r\n"}, {"user": "Following the install instruction mentioned on git hub.\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD"}, {"user": "Hi Vitor,\n\nRecloned the repository and tried again, getting below errors now.\n\n\n\nOn Mon, Mar 6, 2023 at 7:32\u202fPM Vitor Bandeira ***@***.***>\nwrote:\n\n> @vijayank88 , this warning is not a\n> problem with CMake; this indicates that the folder is not a git repo.\n> @mdzaki-git , can you make sure that the\n> clone ended fine? Maybe check the output of git status --long, the output\n> of this command should look something like this:\n>\n> > git status --long\n> On branch master\n> Your branch is up to date with 'origin/master'.\n> nothing to commit, working tree clean\n>\n> Also, try to do a clean build and in case of any errors upload the new log\n> file.\n>\n> ./etc/Build.sh -clean\n>\n> \u2014\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n> You are receiving this because you were mentioned.Message ID:\n> github.com>\n>\n"}, {"user": "[openroad_build.log](https://github.com/The-OpenROAD-Project/OpenROAD/files/10899446/openroad_build.log)\r\n"}, {"assistant": "Looks like you missed the `--recursive` when cloning. Please run\n\n```\ngit submodule update --init\n```\n\nIn the future you should use `git clone --recursive` to also clone the submodules `abc` and `sta`. "}, {"user": "Hi All,\n\nThanks it works now.\n\nOn Mon, Mar 6, 2023 at 9:37\u202fPM Vitor Bandeira ***@***.***>\nwrote:\n\n> Looks like you missed the --recursive when cloning. Please run\n>\n> git submodule update --init\n>\n> In the future you should use git clone --recursive to also clone the\n> submodules abc and sta.\n>\n> \u2014\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n> You are receiving this because you were mentioned.Message ID:\n> github.com>\n>\n"}]} +{"messages": [{"user": "Hi, I am looking to use OpenROAD and have tried to install it on my computer.\r\n\r\nIt is an M2 Pro Macbook Pro, 32 GB RAM, 1TB SSD. I am running an Ubuntu VM through UTM which has 8GB RAM and 64 GB SSD. \r\n\r\nI am having trouble with building OpenROAD because one of the dependencies is `or-tools`, which does not appear to have Ubuntu support for the ARM architecture. I was wondering if anyone had similar issues or would know how to resolve this.\r\n\r\nSpecifically, does OpenROAD support the ARM architecture, and if not, is that a priority in the future? \r\n\r\nThanks!"}, {"assistant": "Can you try OpenROAD-flow-scripts with docker based: https://openroad-flow-scripts.readthedocs.io/en/latest/user/BuildWithDocker.html#clone-and-build"}, {"assistant": "We do not officially support it as we don't have the hardware resources to test on that platform. We do try to make sure we can compile on mac M1 based systems. That said or-tools is available for arm64 as Vijayan pointed out."}, {"assistant": "> Note: OR-Tools only provides archives for the x86_64 (also known as amd64) architecture.\r\nSource: https://developers.google.com/optimization/install/cpp/binary_linux\r\n\r\n@DylanTom If you are already using a VM, you can create a x86_64 VM and avoid this issue."}, {"assistant": "If you're on M2, why not give \"native\" OR a try ?\r\n\r\nI've been compiling it on and off using HomeBrew for dependencies (including or-tools) for a while now.\r\nor-tools and mpl2 keep on breaking the build and mpl2 is still be disabled.\r\n>> -- Removing MPL2 and PAR to avoid run time fatal error.\r\n\r\nSo occasionally it doesn't work, but most of the times I got it to compile in < 15min on a M1.\r\n\r\netc/DependencyInstaller.sh (unforunately now installs x86 klayout, I prefer building it natively)\r\n./build_openroad.sh --local --latest --clean-force (breaks today in a mpl2 test)\r\n./build_openroad.sh --local (when run again it finishes, go figure)\r\n"}]} +{"messages": [{"user": "Hi everybody,\r\n\r\nI already build OpenROAD GUI to run on Ubuntu Linux. Now I'm looking for a sample project that can open directly via main menu `File > Open DB` in OpenROAD GUI (like the below image), I have spent a lot of time to find the way (reading read-me, watching video, etc) to do it, but I did not complete.\r\nI found a data test at https://github.com/TILOS-AI-Institute/MacroPlacement/tree/main/Flows/NanGate45/ariane133 but seems it cannot open directly by OpenROAD and maybe need to do several pre-processing steps before can open in OpenROAD GUI.\r\nCould you please help me to know how to do it or give me detail instructions to open this test data in the OpenROAD GUI?\r\nThanks.\r\n\r\n![sample](https://user-images.githubusercontent.com/5672864/222308822-2fc0204a-440c-4593-a04b-a4e82f591073.png)\r\n"}, {"assistant": "Hi @vic4key,\r\n\r\nIt's not clear what's failing, and what you would like to see? It would also be helpful if you uploaded the data you could upload your test data in a zip folder and post it here. So that we can debug th issue."}, {"assistant": "@vic4key \r\nSame design implemented in OpenROAD-flow-scripts. https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/tree/master/flow/designs/nangate45/ariane136\r\nAll you need to install OpenROAD-flow-scripts and run the design and view it in OpenROAD GUI.\r\nInstallation document available here: https://openroad-flow-scripts.readthedocs.io/en/latest/user/BuildLocally.html"}, {"assistant": "cuda will make almost no difference to runtime. I would start by running gcd as it is the smallest test case."}]} +{"messages": [{"user": "I am trying to build Openroad with cmake .. -DGPU=true and I get the following output\r\n\r\n```\r\n-- GPU is enabled\r\n-- CUDA is found\r\n-- The CUDA compiler identification is NVIDIA 10.1.243\r\n-- Detecting CUDA compiler ABI info\r\n-- Detecting CUDA compiler ABI info - done\r\n-- Check for working CUDA compiler: /usr/bin/nvcc - skipped\r\n-- Detecting CUDA compile features\r\n-- Detecting CUDA compile features - done\r\n-- Found re2: /opt/or-tools/lib/cmake/re2/re2Config.cmake (found version \"9.0.0\") \r\n-- Found Clp: /opt/or-tools/lib/cmake/Clp/ClpConfig.cmake (found version \"1.17.7\") \r\n-- Found Cbc: /opt/or-tools/lib/cmake/Cbc/CbcConfig.cmake (found version \"2.10.7\") \r\n-- Found Eigen3: /usr/local/share/eigen3/cmake/Eigen3Config.cmake (found version \"3.4.0\") \r\n-- Found SCIP: /opt/or-tools/lib/cmake/scip/scip-config.cmake (found version \"8.0.1\") \r\n-- GUI is enabled\r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found version \"1.80.0\") found components: serialization \r\n-- Found OpenMP_CXX: -fopenmp (found version \"4.5\") \r\n-- Found OpenMP: TRUE (found version \"4.5\") \r\n-- Could NOT find VTune (missing: VTune_LIBRARIES VTune_INCLUDE_DIRS) \r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found suitable version \"1.80.0\", minimum required is \"1.78\") \r\n-- Found Boost: /usr/local/lib/cmake/Boost-1.80.0/BoostConfig.cmake (found version \"1.80.0\") found components: serialization system thread \r\n-- TCL readline enabled\r\n-- Tcl Extended disabled\r\n-- Python3 enabled\r\n-- Configuring done\r\nCMake Warning (dev) in src/gpl/CMakeLists.txt:\r\n Policy CMP0104 is not set: CMAKE_CUDA_ARCHITECTURES now detected for NVCC,\r\n empty CUDA_ARCHITECTURES not allowed. Run \"cmake --help-policy CMP0104\"\r\n for policy details. Use the cmake_policy command to set the policy and\r\n suppress this warning.\r\n\r\n CUDA_ARCHITECTURES is empty for target \"gpl\".\r\nThis warning is for project developers. Use -Wno-dev to suppress it.\r\n\r\nCMake Error in src/gpl/CMakeLists.txt:\r\n Target \"gpl\" requires the language dialect \"CUDA17\" . But the current\r\n compiler \"NVIDIA\" does not support this, or CMake does not know the flags\r\n to enable it.\r\n\r\n\r\n-- Generating done\r\nCMake Generate step failed. Build files cannot be regenerated correctly.\r\n```\r\n\r\nI have Cuda installed and on `nvidia-smi` I get \r\n\r\n```\r\n+-----------------------------------------------------------------------------+\r\n| NVIDIA-SMI 525.85.12 Driver Version: 525.85.12 CUDA Version: 12.0 |\r\n|-------------------------------+----------------------+----------------------+\r\n| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\r\n| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\r\n| | | MIG M. |\r\n|===============================+======================+======================|\r\n| 0 NVIDIA GeForce ... On | 00000000:01:00.0 On | N/A |\r\n| N/A 51C P5 18W / 115W | 187MiB / 6144MiB | 19% Default |\r\n| | | N/A |\r\n+-------------------------------+----------------------+----------------------+\r\n \r\n+-----------------------------------------------------------------------------+\r\n| Processes: |\r\n| GPU GI CI PID Type Process name GPU Memory |\r\n| ID ID Usage |\r\n|=============================================================================|\r\n| 0 N/A N/A 1211 G /usr/lib/xorg/Xorg 52MiB |\r\n| 0 N/A N/A 1875 G /usr/lib/xorg/Xorg 133MiB |\r\n+-----------------------------------------------------------------------------+\r\n```\r\n\r\nand on `nvcc -V`\r\n\r\n```\r\nnvcc: NVIDIA (R) Cuda compiler driver\r\nCopyright (c) 2005-2019 NVIDIA Corporation\r\nBuilt on Sun_Jul_28_19:07:16_PDT_2019\r\nCuda compilation tools, release 10.1, V10.1.243\r\n```\r\nAny help on how to get the setup working is really appreciated and thanks in advanced.\r\n\r\n\r\n\r\n\r\n\r\n"}, {"assistant": "Please install a newer version of `nvcc` and try again. As per NVIDIA docs, you will require at least v11; see more [here](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#c-17-language-features)."}, {"assistant": "If we bump to cmake 3.10 then https://cmake.org/cmake/help/latest/module/FindCUDA.html suggests we can use the usual VERSION keyword.\r\n\r\nFYI - the use of CUDA is quite minimal and probably not worth the bother at this point."}]} +{"messages": [{"user": "Hello. I am wondering what is the metrics naming conventions. I am noticing that it is mostly `__`. What I am unsure about is how to name the `` part. There is a mix usage of double underscore and single underscore as separators. For example there are `route__drc_errors`, `route__vias__singlecut` and `timing__drv__hold_violation_count`."}, {"assistant": "The naming is described at https://github.com/ieee-ceda-datc/datc-rdf-Metrics4ML. @ravi-varadarajan can help with questions."}]} +{"messages": [{"user": "I would like to iterate on the floorplan of the top level of our design. In doing so, I want to change the pin constraints for the macros used at the top level.\r\n\r\nHowever, ```make generate_abstract``` goes all the way to detailed routing before producing a .gds, .lef and .lib file. This takes a long time.\r\n\r\nIs there a way to run generate_abstract after IO pin placement on the macro without going through detailed route?\r\n"}, {"assistant": "The flow itself doesn't have a mechanism but the command should work at that point (though it hasn't been tested). You could add a flow option if needed."}, {"user": "Solution implemented: `make skip_cts skip_route generate_abstract`"}]} +{"messages": [{"user": "What does this error message mean?"}, {"assistant": "@eder-matheus please respond"}, {"assistant": "@oharboe That means the guides don't cover at least one pin of this net. I will update this error message to clarify what pin is not covered.\r\nCould you share what commit you are using in this run? This error should not be happening at all and could be a side effect of an update I've made."}, {"user": "I don't recall the details, but this was fixed on master."}]} +{"messages": [{"user": "How can I get a list of the names of the pins, such that I can pass in a list of names to set_io_pin_constraint that match a regex?\r\n\r\nSomething like:\r\n\r\n```\r\nset_io_pin_constraint ... -names [lsearch -all -inline $pins $regex]\r\n```\r\n\r\nAnswering myself..\r\n\r\nThis will do it:\r\n\r\n```\r\nproc match_pins { regex } {\r\n set pins {}\r\n foreach pin [sta::find_port_pins_matching $regex 1 0] {\r\n lappend pins [get_property $pin name]\r\n }\r\n return $pins\r\n}\r\n\r\nset_io_pin_constraint -region top:* -pin_names [match_pins someregex]\r\n```\r\n"}, {"assistant": "See discussion in https://github.com/The-OpenROAD-Project/OpenROAD/pull/2839"}, {"assistant": "The point being there isn't a default mechanism right now but rather a discussion of how best to do it. get_pins will return a list of pins objects rather than names. You could convert them to names or you could use the odb APIs to traverse the db yourself."}, {"user": "This will do it:\r\n\r\n```\r\nset_io_pin_constraint ... -names [sta::find_port_pins_matching $regex 1 0]\r\n```\r\n\r\n"}, {"assistant": "What do you mean by \"verilog pin names\"? Those look ok to me for instance pins"}, {"assistant": "Perhaps you want get_ports? I would call those port names as Verilog includes the instance pins as well."}]} +{"messages": [{"user": "Can I create a purely combinational logic macro?\r\n\r\nThat is a macro without a clock input.\r\n\r\n```\r\n[WARNING STA-0337] port 'clock' not found.\r\n```"}, {"assistant": "You can. When creating the clock you don't give a port, just the name is enough"}]} +{"messages": [{"user": "What does this step actually do?\r\n\r\nAny hints on how to figure out what is going on here, what to look at?\r\n\r\nWhen I zoom in on the design, I see an ocean of thinly spread fiddlybits:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/218471305-7312e5f8-afbf-454d-9dbd-87a75d5197e5.png)\r\n"}, {"assistant": "GRT is the global router. It means your design is very dense (at least within some areas). It is attempting to assign nets to routing tracks, but there are too many nets within an area (overflow) so it is trying to reroute nets to avoid this.\r\n\r\nGRT runs for a fixed number of iterations before giving up and erroring if it can't resolve the overflow.\r\n\r\nThe best first thing to check is the global routing heatmap to see congestion hotspots. In your case, it is likely that the density is simply too high and you need to reduce the placement density %."}, {"assistant": "You should also check how many buffers are being inserted as it possible that can cause extra congestion if you have very bad timing."}]} +{"messages": [{"user": "I have some violations that detailed routing isn't able to deal with, that I really think it should be able to deal with.\r\n\r\nNormally, deltaDebug.py needs an error message to look for to do it's bisection.\r\n\r\nHowever, a detailed route can succeed after 64 iterations, even if all violations are not sorted out, so there's no error message for deltaDebug.py to use for it's bisection.\r\n\r\nTips?"}, {"assistant": "Can you use --use_stdout & --error_string to check the final drcs?"}, {"assistant": "You could make a temporary change to scripts/detail_route.tcl to call detailed_route_num_drvs and issue an error message if >0. Then you could delta on that."}, {"user": "Various bugs have been fixed and improvements made to deltaDebug.py since this post."}]} +{"messages": [{"user": "Is it possible to run `estimate_parasitics -global_routing` on a post-global_route design that's been loaded via the `read_db` command? As in, `global_route` has been run on the design before it was saved with `write_db`, but `global_route` has not been run in this current OpenROAD session. I keep getting this error:\r\n\r\n```\r\n>>> read_db post_global_route\r\n>>> estimate_parasitics -global_routing\r\n[ERROR RSZ-0005] Run global_route before estimating parasitics for global routing.\r\n```"}, {"assistant": "@eder-matheus I thought this was possible. Please comment"}, {"assistant": "Are you using a very old version of OR for this? The guides should be saved in the db."}, {"assistant": "OR improves a lot over time so it is a good practice to test with a current version when you find a problem."}]} +{"messages": [{"user": "Below are two macros next to eachother where I have mirrored the pins, so the connections are nice and horizontal.\r\n\r\nThe pins are on ASAP7 M4, but the route is on M2.\r\n\r\nLooking at the image, I'm curious as to why M4 wasn't just used in a straight line across? Why go via M2?\r\n\r\nThe reason I'm asking about this is that my design does detailed routing quickly when I scale it down, but as I scale up, add more macros and a wider data path, it seems like detailed routing has to spend more time(ca. 20x longer) getting signals from M2, to M4 and back to M2 to do the routing between macros. I believe there is non-linear increase(with datapath width) in complexity with getting signals from M4 to M2 and back to M2.\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/217489650-65aa3930-5241-4c6f-affe-adc68a99a9be.png)\r\n"}, {"assistant": "does this happen on the mock array?"}, {"assistant": "If you select one of the nets, in the inspector there is an option to show the route guide. It would be interesting to see what the guide for one of these nets looks like."}, {"assistant": "The global router prefers to put wires on lower layers, which is a good strategy for standard cell connections. It isn't so good here.\r\n\r\n@eder-matheus I think we should update the 3d embedding in grt to handle the case where the pins being connected are all at layer N or above to avoid layers below N if possible. Would you take care of this or work with Luis or Arthur to do so."}, {"assistant": "@oharboe Could you try this branch: https://github.com/eder-matheus/OpenROAD/tree/grt_upper_layer_nets?"}, {"assistant": "@eder-matheus he does not have access to the private repo. Please sync it to public in a PR."}, {"assistant": "If you had an obs that you couldn't go over or around then it could be an issue. However it is similar to the clock net constraints we already have that are similar. Probably we would need to introduce a costing scheme to allow out of range layers to be used in extreme cases but that seems like a separate enhancement.\r\n\r\nThe motivating case is simply two m4 pins that have an easy planar connection but we drop down to m2 for no good reason (the router prefers lower layers on the erroneous assumption that pins are on the lower layer)."}, {"user": "Master is MUCH better with this now. If the route is not straight, there's generally a reason, like powergrid in the way, buffers added at edge of design before pins, or something."}]} +{"messages": [{"user": "I'm trying to find out valid coordinates to put macros onto. The pins of the macros must align on the routing grid.\r\n\r\nFrom ASAP 7 LEF files, I see that pins are on M4 and M5 layer. From make_tracks.tcl, I see offsets and pitches.\r\n\r\nFrom that information, I should be able to come up with some formulae of valid macro positions....\r\n\r\nI just seem to be unable to connect the dots here to what the formulae should be:\r\n\r\nM4 is horizontal pins and M5 is vertical pins (or vice versa, I could see in the GUI, but I don't know how to tell from the LEF file):\r\n\r\n\r\nThe pins are from a macro, so I know the pin coordinates below are correct:\r\n\r\n```\r\n PIN foo[50]\r\n DIRECTION INPUT ;\r\n USE SIGNAL ;\r\n PORT\r\n LAYER M4 ;\r\n RECT 144.818 86.208 145.152 86.232 ;\r\n END\r\n END foo[50]\r\n\r\n PIN bar\r\n DIRECTION INPUT ;\r\n USE SIGNAL ;\r\n PORT\r\n LAYER M5 ;\r\n RECT 101.76 144.818 101.784 145.152 ;\r\n END\r\n END bar\r\n```\r\n\r\nfrom make_tracks.tcl:\r\n\r\n```\r\nmake_tracks M4 -x_offset [expr 0.009 * $multiplier] -x_pitch [expr 0.036 * $multiplier] -y_offset [expr 0.012 * $multiplier] -y_pitch [expr 0.048 * $multiplier]\r\nmake_tracks M5 -x_offset [expr 0.012 * $multiplier] -x_pitch [expr 0.048 * $multiplier] -y_offset [expr 0.012 * $multiplier] -y_pitch [expr 0.048 * $multiplier]\r\n```\r\n"}, {"assistant": "@maliberty mentioned in our discussion yesterday that the routing grid is defined in the tech lef for the PDK. For ASAP7 we have to look at the [generated tech lef in ORFS](https://github.com/The-OpenROAD-Project/asap7/issues/19#issuecomment-1115712485) which should be `OpenROAD-flow-scripts/flow/platforms/asap7/lef/asap7_tech_1x_201209.lef`:\r\n\r\n```\r\nLAYER M4\r\n TYPE ROUTING ;\r\n DIRECTION HORIZONTAL ;\r\n PITCH 0.048 ;\r\n WIDTH 0.024 ;\r\n SPACING 0.024 ;\r\n\r\n OFFSET 0.003 ;\r\n\r\n AREA 0.008 ;\r\n\r\n PROPERTY LEF58_SPACING \"\r\n SPACING 0.024 ENDOFLINE 0.025 WITHIN 0.04 ENDTOEND 0.04 ; \" ;\r\n\r\n PROPERTY LEF58_WIDTHTABLE\r\n \" WIDTHTABLE 0.024 0.12 0.216 0.312 0.408 ; \" ;\r\n\r\n PROPERTY LEF58_CORNERSPACING \"\r\n CORNERSPACING CONVEXCORNER CORNERONLY 0.048\r\n WIDTH 0.0 SPACING 0.04 ;\r\n \" ;\r\n\r\n PROPERTY LEF58_EOLKEEPOUT \"\r\n EOLKEEPOUT 0.025 EXTENSION 0.048 0.02425 0.048 CORNERONLY ;\r\n \" ;\r\n\r\n # spacing table is required for the rule that has wide metal requires a 72nm (288 scaled)\r\n # spacing between wide and minimum metals \r\n\r\n SPACINGTABLE\r\n PARALLELRUNLENGTH 0.0\r\n WIDTH 0.0 0.024\r\n WIDTH 0.025 0.072 ;\r\n\r\n PROPERTY LEF58_RIGHTWAYONGRIDONLY \"\r\n RIGHTWAYONGRIDONLY ;\r\n \" ;\r\n\r\n PROPERTY LEF58_RECTONLY \"\r\n RECTONLY ;\r\n \" ;\r\n\r\nEND M4\r\n```\r\n\r\nFrom this we can indeed see that M4 is horizontal and M5 is vertical (not shown above but the definitions for M5 are below those for M4 in the file). We can also see that the pitch is `0.048` which lines up with the `-y_pitch` arg in the `make_tracks.tcl` code above, among other things. However, I'm also a bit confused at how to use this information.\r\n\r\nSome specific questions:\r\n\r\n - Where does `0.012` for the `-y_offset` arg in `make_tracks.tcl` come from? I would have assumed it would be `0.003` from the `OFFSET` in the tech lef.\r\n - How does offset/pitch relate to macro position? I would assume that the bottom-left of a macro is the origin (0, 0), and that if we respect `PITCH` and `OFFSET` from the tech lef above for IO y-positions (eg. `my_io_y = OFFSET + some_integer * PITCH`) we can then place that macro at a position which ensures those constraints are still respected (eg. `my_macro_y = some_integer * PITCH - OFFSET`). Is this correct?\r\n\r\n\"Bonus\" question: What's the difference between the 1x and 4x .lef files in the PDK?\r\n"}, {"assistant": "In the LEF you can see the preferred routing direction from:\r\n```\r\nLAYER M4\r\n DIRECTION HORIZONTAL ;\r\n\r\nLAYER M5\r\n DIRECTION VERTICAL ;\r\n```\r\n\r\nIf you look at M1 you'll see it has an offset of 0 which makes the first track unusable (a wire would be half outside the bounds if that track were used). So in make_tracks it was setup to make the first track usable by using a 1/2 width offset. Similarly the other layers need adjusting. Its mostly a matter of style and either could have been used. \r\n\r\nM2 has a track pattern too complex to express in the LEF format so make_tracks.tcl is required in any case.\r\n\r\nIf you place a macro a (0,0) the tracks should align since they would be built the way way. Moving the macro by a multiple of the pitch should keep it aligned. You would use the m4 pitch vertically and the m5 pitch horizontally.\r\n\r\nYou can check your work by turning on m4 & m5 visibility in the GUI, turning on the display of the preferred tracks and look at your pins to see that the tracks go through the center."}, {"assistant": "Bonus: 1X and 4X can be ignored as OR is only using 1X. The origin is that some academic users may not have the advanced node licenses for proprietary tools required to use a 7nm process. The 4X library makes it appear like a 28nm library by making all dimensions 4X larger as a workaround. Since OR has no licensing 4X is not required."}]} +{"messages": [{"user": "Hi -- I'm looking through a draft for the upcoming ISPD \"Assessment of Reinforcement Learning\" paper.\r\n\r\nIf there are placement results for the ICCAD04 testcases handy, I'd appreciate a link to them. I'd love to see the actual placements from CT, SA, and RePLAce, but don't have the time and resources (and expertise) to run all of the experiments myself. Bookshelf format is preferred, but I could probably figure out a way to convert from ProtoBuf if needed. There seem to have been some slight tweaks to the macro block sizes over the years -- so input files would be helpful too.\r\n\r\nThanks to everyone for all the work on this. I've done a lot of benchmarking over the years, and know that it's generally a thankless task -- so seriously, thanks very much for all the work. I'm sure it's zero fun and a huge time sink."}, {"assistant": "I'm not aware of such results being handy unless @mgwoo has some."}]} +{"messages": [{"user": "I was curious what was difficult about detailed routing for a design, so I stopped detailed routing after 4 iterations, using https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/791, then looked at 5_route_drc.rpt.\r\n\r\nHere it seems like there is a lot of congestion at the top of macros because the power strip is running inside the halo (?) of the macro.\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/215082762-af8767ce-7118-48cb-a7a3-c9913369defc.png)\r\n\r\nHowevever here is a macro, just like the one above where detailed routing doesn't seem to have a problem dealing with this issue:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/215083592-634bcdef-9a15-45c7-ad5b-b34820f0a94e.png)\r\n\r\n\r\nPerhaps nothing is wrong here and it just takes a while to do detailed routing.\r\n\r\nIs there anything to learn or that I can do different here?"}, {"assistant": "How many iterations does it take to complete? In general drt is the slowest step of the flow but it also looks like something is going on here.\r\n\r\nIn the lower picture the wires appear to go straight in on m5 but in the upper the go up to a higher layer and then try to drop down (which is blocked by the strap). I'm not clear why they can't go straight in from the image. Can you tell?"}, {"user": "I can see the same problem on https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/tree/master/flow/designs/asap7/mock-array-big\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/215114565-abeebeab-8247-4fb0-81eb-8259fbad3390.png)\r\n\r\n\r\nZooming in, we can see that different metal is being used:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/215114709-80ae1615-95c6-4bb3-bfaa-a25c3bc339b9.png)\r\n\r\n\r\nTo reproduce the image above, first build, but abort after 5 iterations in detailed routing, then load the 5_route_drc.rpt and zoom in:\r\n\r\n```\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/Element/config.mk generate_abstract\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk DETAILED_ROUTE_ARGS=\\\"-bottom_routing_layer M2 -top_routing_layer M7 -save_guide_updates -verbose 1 -droute_end_iter 5\\\"\r\nmake DESIGN_CONFIG=designs/asap7/mock-array-big/config.mk\r\n```\r\n\r\n\r\n\r\n\r\n\r\n"}, {"assistant": "@osamahammad21 I think looking at this issue in the context of asap7/mock-array-big fits with your other drt performance work."}, {"assistant": "Your pins are off the routing grid:\r\n![image](https://user-images.githubusercontent.com/761514/215116042-68838f95-3670-47af-8cc8-e03d6748a470.png)\r\n\r\nwhich I guess is why the router is gyrating to hit them."}, {"assistant": "@osamahammad21 with the PRs from this morning this case now finishes with 0 drvs. However it reaches 2 drvs by the end of iter 4 but takes until iter 13 to reach zero. At the end of iter5 I see two cut spacing violations. They both look easy to fix, eg\r\n![image](https://user-images.githubusercontent.com/761514/216147952-499d6ec6-11d2-4d60-b8e7-27cdf28104ef.png)\r\n\r\nyou should readily move the via to the right by one track. I guess this is a costing issue.\r\n"}, {"assistant": "I missed this because it was hiding in discussions. I have noticed various issues with via spacing in drt, eg https://github.com/The-OpenROAD-Project/OpenROAD/issues/2827 and https://github.com/The-OpenROAD-Project/OpenROAD/pull/2844, so likely issues in both route cost and GC (drc)."}, {"user": "Near as I know all of these issues are resolved on master."}]} +{"messages": [{"user": "In this pull request, I've added a design that has a problem with detailed routing. I *suspect* there are some alignment requirements for macro positioning, but I don't understand what those requirements are.\r\n\r\nAny tips?\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/782\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/213920736-10b8a7f8-0b71-466a-9357-178dbb9b52b7.png)\r\n"}, {"assistant": "My first guess would be to look at the macro pins and whether they are on grid"}, {"assistant": "Same issue, any solution reached yet?"}, {"user": "We're not seeing these problems currently with latest master"}]} +{"messages": [{"user": "I presume for errors in C++ test code (e.g. fixtures and similar) it's ok to throw more \"bare\" errors (vs the scheme used with the logger and explicitly enumerated exceptions) -- that is, it's ok to throw a derived class from `std::runtime_error` if something goes wrong in test fixture scaffolding?\r\n\r\nIf so I'll update the developer docs with a small note, but I wanted to check this seemed ok.\r\n\r\nCC @maliberty "}, {"user": "(Or if non-exception-code is preferred in test code, that'd be fine too, just let me know what the preferred way to fatal-error-with-message would be.)"}, {"user": "(Or possibly we use logger with an error ID of 0 for a testing use cases like this?)\r\n\r\nApologies for the stream of conscious of possibilities. :-)"}, {"assistant": "What do you mean by \"explicitly enumerated exceptions\"? In general I'm ok with your initial statement."}]} +{"messages": [{"user": "Is it expected that inserting PDN (last part of make floorplan) should take a lot of time for designs that start to approach 1mm^2 in ASAP7?\r\n\r\nIt would be helpful if \"make floorplan\" was faster, because then it is quicker to iterate on the floorplan, after which the build can normally be left alone without human interaction for longer runs.\r\n\r\nI ran it in the debugger and it looks like a lot of time is spent building this ShapeTree: https://github.com/The-OpenROAD-Project/OpenROAD/blob/b99d7d2c3db8b72a3fc35da9bd6c3a203c3b8306/src/pdn/src/shape.cpp#L637 \r\n\r\nAfterwards, this line seems to almost always return false https://github.com/The-OpenROAD-Project/OpenROAD/blob/b99d7d2c3db8b72a3fc35da9bd6c3a203c3b8306/src/pdn/src/shape.cpp#L640) \r\n\r\nI made a few fleeting vain attempts to rewrite the code, such that the common case, https://github.com/The-OpenROAD-Project/OpenROAD/blob/b99d7d2c3db8b72a3fc35da9bd6c3a203c3b8306/src/pdn/src/shape.cpp#L627, returning false, would not require building the ShapeTree.\r\n\r\n\r\n"}, {"assistant": "There could be a lot of factors. Are you using the asap7 default pdn?\r\n@gadfort "}, {"user": "Still running, 1 hr 35 minutes...\r\n\r\n```\r\n01:35:49 /OpenROAD-flow-scripts/tools/install/OpenROAD/bin/openroad -exit -no_init ./scripts/pdn.tcl -metrics ./logs/asap7/doohickey/base/2_6_pdn.json\r\n```"}, {"assistant": "In asap7 the m1/m2 stripes introduce a ton of vias. @gadfort could help skip the add_pdn_connect for M1/M2 or would that produce an error. It wouldn't matter much for prototyping whether we have the vias or not."}, {"assistant": "@oharboe @maliberty it shouldn't take that long, there has always been some inefficiency when building those obstruction sets and maybe it's a good idea to revisit how that is done and find a better solution that is faster."}, {"user": "@maliberty @gadfort Example of ```[INFO PDN-0001] Inserting grid: top``` taking at least 12 hours, after which I stopped it. https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/779"}, {"user": "PDN insertion is MUCH faster than it used to be, but it can still be an issue."}]} +{"messages": [{"user": "Hello OpenROAD devs,\r\n\r\nI am planning on contributing a new tool (following https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/docs/contrib/DeveloperGuide.md, I will call this \"dft\") for DFT insertion into OpenROAD and I would like to discuss the user facing API.\r\n\r\n# User facing API\r\n\r\nI think we should create two new main commands for DFT: preview_dft and insert_dft:\r\n\r\n* preview_dft: will show a summary of what scan chains are we going to create (after scan architect) but will not apply any changes to the design. This is an immutable command and will not perform any modifications to the design or database. This is useful for debugging proposes and to help users to iterate any DFT option that could change the creation of the scan chains.\r\n* insert_dft: will run again from scratch the immutable part of preview_dft, including scan architect and perform scan stitching. The result of insert_dft should be the same that the one presented by preview_dft but applied to the design.\r\n\r\nI would say that it is better to configure the DFT compiler with commands like \"set_dft_*\" instead of receiving any argument in \"preview_dft\" or \"insert_dft\". For example: set_dft_no_scan (for cells that we don't want to scan replace), set_dft_chain_count (for the number of scan chains to be created) or set_dft_clock_mix (if we want or not to mix clock domains).\r\n\r\nNow, I am not sure if this is going to be something you expect to see in the Python interface, this is a very TCL oriented API and I would like to see if you have any suggestion on doing this more programmatically for Python scripting (maybe this is totally fine as we can have a different API for Python?).\r\n\r\n# Where in the flow is DFT insertion going to be?\r\n\r\n![OpenROAD's flow](https://user-images.githubusercontent.com/1619948/213331834-76ea8bb9-a63b-4576-90ff-5e6eca6e5647.png)\r\n\r\nLooking into OpenROAD's flow, I think the best part to perform DFT insertion is between \"Logic Synthesis\" and \"Floorplanning\". That way we floorplanning will have all the info about DFT to perform optimizations in the design.\r\n\r\nFeel free to suggest something different here :).\r\n\r\n# What is the plan?\r\n\r\nFor now, I will only be creating \"insert_dft\" and \"set_no_scan\" for scan replacement: I will replace sequential cells (excluding black boxes as we don't have support for [CTLs](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=966626) yet!) in the design with scan equivalents if they are available and nothing more inside insert_dft. I will keep of of the scope adding scan muxes or any other kind of scan stitching as this is my first approach to OpenROAD.\r\n\r\nPlease, let me know if there is something I should be aware of or anything related to this idea or the user interface.\r\n\r\nThanks!,\r\nFelipe\r\n"}, {"assistant": "I think it is best to do scan chain after global placement. You want to put the ff in the best placement for timing and only then construct the chain ordering based on neighbors. \r\n\r\nIt would be helpful to know what commands you intend to implement to define the chains. A small complete example would clarify the use model.\r\n\r\nFor python API please see the discussion in https://github.com/The-OpenROAD-Project/OpenROAD/discussions/2745"}, {"assistant": "@rovinski @msaligane @louiic @Colin-Holehouse any comments?"}, {"assistant": "Very cool! Always excited to see more functionality contributed \ud83d\ude03"}, {"assistant": "Would you say more about scandef and how you intend to generate it?"}, {"assistant": "Note that odb doesn't store any scan information from DEF today so you'll have to plan on enhancing it as part of this project."}, {"assistant": "In case its useful: http://vlsicad.eecs.umich.edu/BK/Slots/cache/vlsicad.ucsd.edu/GSRC/Bookshelf/Slots/ScanOpt/"}, {"user": "Hey @maliberty , \r\n\r\nI am trying to write a function to perform the scan replace and I need to find a scan equivalent cell in the DB.\r\n\r\nI am iterating over the libs in the odb::dbDatabase like this:\r\n\r\n```\r\nbool IsLibScanCell(odb::dbLib* lib) {\r\n for (odb::dbMaster* master: lib->getMasters()) {\r\n for (odb::dbMTerm* mterm: master->getMTerms()) {\r\n std::cout << mterm->getSigType().getString() << std::endl;\r\n }\r\n }\r\n return false;\r\n}\r\n```\r\n\r\nBut looks like the enum of getSigType does not have enough information to see if a pin is scan_enable or scan_in. Is this something that I need to implement or is there another way to access this information inside the lib? I see that in sta/ there are some parsing to detect scan signals, but I do not see them being used in any place outside sta/.\r\n\r\n"}, {"user": "For scan replace, I have a working demo where I collect the scan lib cells and then I try to iterate over the design's blocks applying \"sta::dbNetwork\" replaceCell, but I found that this and some methods in sta:: check before performing the replace if both cells are \"equivalent\" by counting the number of ports in each cell (See inDbInstSwapMasterBefore in dbSta/src/dbSta.cc ).\r\n\r\nThis is not really true when you try to replace a cell with an scan equivalent because the scan one will have additional ports like scan in and scan enable.\r\n\r\nI was wondering if there is a function that I am missing that could help me with this kind of replace.\r\n\r\nIf not, should I provide a new method for dbSta and odb that checks for functional equivalent ports instead of index/name based matching (See swapMaster in odb/src/db/dbInst.cpp) or roll one myself just for DFT? Would you prefer this method to be available in odb or maybe just complete change the way we do the replaceCell?\r\n\r\nThanks!"}, {"user": "Hi @maliberty,\r\n\r\nDo you know how to test if two ports/pins are functional equivalent?, I am trying to use sta::LibertyPort's function() and sta::FuncExpr::equiv() but looks like sta::LibertyPort's function() returns most of the time nullptr. I see that in odb/src/db/dbInst.cpp:1201, we test that mterms are equivalent by checking that the name of the ports is the same (line 1236). \r\n\r\nI can work with that but I think my scan replace function will be more robust if I can check if the ports are functional equivalent.\r\n"}, {"user": "Implemented basic DFT in #2900, #3079 and #3356"}]} +{"messages": [{"user": "Old congestion.rpt files are not deleted upon success, which can be confusing.\r\n\r\nIs this intentional?\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/blob/9d17aaf662bcc3266ff452b7be2e6936f9221e76/src/grt/src/GlobalRouter.cpp#L282"}, {"assistant": "I think this is a bug."}]} +{"messages": [{"user": "Any tips?\r\n\r\nI'm trying a larger version & different version of https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/743 and it fails in global routing.\r\n\r\n```\r\n[INFO GRT-0101] Running extra iterations to remove overflow.\r\n[WARNING GRT-0227] Reached 20 congestion iterations with less than 15% of reduction between iterations.\r\n[INFO GRT-0197] Via related to pin nodes: 1126254\r\n[INFO GRT-0198] Via related Steiner nodes: 39\r\n[INFO GRT-0199] Via filling finished.\r\n[INFO GRT-0111] Final number of vias: 2236520\r\n[INFO GRT-0112] Final usage 3D: 15578444\r\n[ERROR GRT-0118] Routing congestion too high. Check the congestion heatmap in the GUI.\r\nError: global_route.tcl, 19 GRT-0118\r\n```\r\n\r\nThe most recent .odb file to be written is 4_cts.odb, but when I load it and look at the routing congestion map, I don't see anything suspicious. Such arrays have a lot of routing to do, but the routing is simple conceptually: point to point between the array elements.\r\n\r\nI'm learning a few tricks with OpenROAD-flow-scripts:\r\n\r\n1. read documentation, if you can find it.\r\n2. read the OpenROAD-flow-scripts/flow/*.tcl script for the step. It is normally quite short. From here you can find out what reports are being saved and also what to search for in other examples.\r\n\r\n\r\nLooking at congestion.rpt, it is full of these. There's nothing in that area, just filler cells. Sometimes overflow is as high as 20.\r\n\r\n```\r\nviolation type: Horizontal congestion\r\n\tsrcs: \r\n\tcongestion information: capacity:16 usage:17 overflow:1\r\n\tbbox = ( 1544.4, 45.9 ) - ( 1544.94, 46.44) on Layer -\r\n```\r\n\r\n"}, {"assistant": "The violations are related to routing congestion so they can occur over fill cells. Do you not see congested areas in the heatmap? I'm not sure what \"anything suspicious\" means.\r\n\r\nAlso you could play with the layer derates in grt. Reducing them makes it more likely you'll get past grt but also more likely you'll have trouble in drt. We set them more conservatively in the PDK."}, {"assistant": "Something doesn't make sense. It fails to route due to congestion but you don't see any in the congestion map. If you load the congestion report in the drc viewer you should be able to see where the congestion is."}, {"assistant": "Can you show a local image of the area? If you click the underlined heat map you'll get an options dialog. You can investigate on what layers/directions the congestion is happening in."}, {"user": "I'm going to investigate something else... Could it be that the PDN is overlaying the pins at the top of the macro?\r\n\r\nHere the blue line (from PDN) is not overlaying the pins at the top of the macro.\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/212607947-ac115c6b-dec6-47e2-87f1-17f8da092f63.png)\r\n\r\nThe vertical PDN lines go all the way to the top, but the horizontal not all the way to the right edge. That's an assymetry that I find puzzling.\r\n\r\nThe screenshot below is the upper right corner of the design I'm tinkering with:\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/212608610-bb1d7d24-7eb3-4d7f-9a1d-6815b7689330.png)\r\n\r\nThe routing congestion heat map shows that there's a lot of routing at the top (orange). There's nothing there...\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/212611152-9861946b-337e-43cb-9153-671785c873a8.png)\r\n\r\n"}, {"user": "I scaled down the design (fewer wires) and then I can see gui_route.\r\n\r\nAlthough there's only horizontal routes between the inner macro's right edge and the top level design's right edge, there's this spagetti just before the input/outputs on the right side...\r\n\r\nNo wonder this doesn't work if you scale up the number of wires.\r\n\r\nI wonder what is going on here...\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/212673682-743d7cf8-fe27-435a-9982-f709a7e6ef42.png)\r\n\r\nzoom in:\r\n\r\n\r\n![image](https://user-images.githubusercontent.com/2798822/212674518-062cec9c-ab11-4eeb-92d1-2902cbd6419a.png)\r\n\r\n\r\n\r\n\r\n```\r\nset sdc_version 2.0\r\ncreate_clock [get_ports clock] -period 4000 -waveform {0 2000}\r\n\r\nset clk_name clock\r\nset clk_port_name clock\r\nset clk_period 250\r\nset clk_io_pct 0.2\r\n\r\nset clk_port [get_ports $clk_port_name]\r\n\r\nset non_clock_inputs [lsearch -inline -all -not -exact [all_inputs] $clk_port]\r\n\r\nset_input_delay [expr $clk_period * $clk_io_pct] -clock $clk_name $non_clock_inputs\r\nset_output_delay [expr $clk_period * $clk_io_pct] -clock $clk_name [all_outputs]\r\n\r\n```"}, {"user": "@rovinski @maliberty I've polished up a test case https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/764. \r\n\r\nThis array is open source and big enough to exhibit the problems, though less pronounced, seen above that will appear as you go from from mock-array-big to a bigger version, yet it will build in a more reasonable amount of time.\r\n\r\nIn this pull request, I increase the datapath from 8 to 64 bits, at which point global routing fails: https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/774\r\n\r\n\r\n"}, {"assistant": "I looked at https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts/pull/764. I see a path like:\r\n![image](https://user-images.githubusercontent.com/761514/212960378-5042926e-b92f-4ea5-8493-1424c25f7294.png)\r\n\r\nThe input arrives at 50ps (20% of your 250ps clock period). The capture clock path is at nearly 200ps with 44ps of hold from the liberty:\r\n```\r\n>>> report_checks -through hold2693/A -path_delay min -format full_clock_expanded\r\nStartpoint: io_insVertical_0_2[4] (input port clocked by clock)\r\nEndpoint: ces_2_7 (rising edge-triggered flip-flop clocked by clock)\r\nPath Group: clock\r\nPath Type: min\r\n\r\n Delay Time Description\r\n---------------------------------------------------------\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock network delay (propagated)\r\n 50.00 50.00 ^ input external delay\r\n 0.00 50.00 ^ io_insVertical_0_2[4] (in)\r\n 10.10 60.10 ^ hold3918/Y (BUFx2_ASAP7_75t_R)\r\n 11.76 71.86 ^ hold2691/Y (BUFx2_ASAP7_75t_R)\r\n 11.77 83.63 ^ hold3919/Y (BUFx2_ASAP7_75t_R)\r\n 11.61 95.24 ^ hold1087/Y (BUFx2_ASAP7_75t_R)\r\n 11.64 106.88 ^ hold2692/Y (BUFx2_ASAP7_75t_R)\r\n 11.81 118.69 ^ hold245/Y (BUFx2_ASAP7_75t_R)\r\n 11.74 130.43 ^ hold2693/Y (BUFx2_ASAP7_75t_R)\r\n 11.65 142.08 ^ hold1088/Y (BUFx2_ASAP7_75t_R)\r\n 11.75 153.83 ^ hold2694/Y (BUFx2_ASAP7_75t_R)\r\n 11.95 165.78 ^ input149/Y (BUFx2_ASAP7_75t_R)\r\n 12.04 177.82 ^ hold2695/Y (BUFx2_ASAP7_75t_R)\r\n 12.02 189.84 ^ hold1089/Y (BUFx2_ASAP7_75t_R)\r\n 12.10 201.94 ^ hold2696/Y (BUFx2_ASAP7_75t_R)\r\n 12.11 214.05 ^ hold246/Y (BUFx2_ASAP7_75t_R)\r\n 12.07 226.12 ^ hold2697/Y (BUFx2_ASAP7_75t_R)\r\n 11.89 238.01 ^ hold1090/Y (BUFx2_ASAP7_75t_R)\r\n 12.17 250.19 ^ hold2698/Y (BUFx2_ASAP7_75t_R)\r\n 0.05 250.24 ^ ces_2_7/io_ins_1[4] (Element)\r\n 250.24 data arrival time\r\n\r\n 0.00 0.00 clock clock (rise edge)\r\n 0.00 0.00 clock source latency\r\n 0.00 0.00 ^ clock (in)\r\n 16.72 16.72 ^ wire1/Y (BUFx12f_ASAP7_75t_R)\r\n 74.94 91.66 ^ clkbuf_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 51.85 143.51 ^ clkbuf_2_1_0_clock/Y (BUFx4_ASAP7_75t_R)\r\n 44.16 187.67 ^ clkbuf_3_3__f_clock/Y (BUFx4_ASAP7_75t_R)\r\n 8.97 196.64 ^ ces_2_7/clock (Element)\r\n 0.00 196.64 clock reconvergence pessimism\r\n 44.22 240.86 library hold time\r\n 240.86 data required time\r\n---------------------------------------------------------\r\n 240.86 data required time\r\n -250.24 data arrival time\r\n---------------------------------------------------------\r\n 9.39 slack (MET)\r\n```\r\n\r\nSo you'll need 200ps of hold buffering to make this pass. BUFx2 is ~12ps so you need a good number to meet your hold constraint. I don't see anything wrong here other than inputs that arrive quite early relative to the macro's requirements.\r\n\r\nThe clock path doesn't look unreasonable:\r\n![image](https://user-images.githubusercontent.com/761514/212962157-a2e3bc6e-911d-4243-a648-39f7e10343d2.png)\r\n"}, {"assistant": "The most forgiving would be to put no i/o timings at all aside from clock. Then only paths internal to the block would be checked. Another option would be to give different min/max timings where they are both forgiving."}]} +{"messages": [{"user": "The python api differs from tcl in being more OO (objects/methods) rather than command oriented. I'd like to discuss standardizing how that API accept options. Current APIs are variable:\r\n- Some use state building commands. For example pdn has define_pdn_grid, add_pdn_stripe, etc.\r\n- Some persistently hold an options object that can be modified by the user. For example TritonCTS::getParms()\r\n- Some take their options as arguments. For example Resizer::repairHold(...)\r\n\r\nComplicating cases are:\r\n- Tools that call other tools. For example gpl calls grt and rsz\r\n- Incremental operations that retain state between invocations. For example grt and sta\r\n\r\nMy best thought on how to standardize is to have a persistent set of default options and the ability to pass an overriding set. A sketch of the idea:\r\n```\r\nclass ToolOptions\r\n{\r\npublic:\r\n ToolOptions(); // a well-defined default state\r\n void setOptionA(int value);\r\n void setOptionB(bool value);\r\n};\r\n\r\nclass Tool\r\n{\r\npublic:\r\n static ToolOptions* getDefaultOptions();\r\n\r\n // if options is nullptr then the default options are used.\r\n void task(ToolOptions* options = nullptr);\r\n\r\nprivate:\r\n static ToolOptions* default_options_;\r\n};\r\n```\r\n\r\nOne use model would be pre-configuration (in C++ but similarly in python)\r\n```\r\n// setup\r\nauto default_options = Tool::getDefaultOptions();\r\ndefault_options.setOptionB(false);\r\n\r\n// later\r\ntool->task();\r\n```\r\n\r\nAnother use model could be\r\n```\r\nToolOptions options;\r\noptions.setOptionB(false);\r\ntool->task(options);\r\n```\r\n\r\nThis can be extended to the case of one tool calling another internally with an API like:\r\n```\r\nvoid task(ToolOptions* options = nullptr,\r\n AnotherToolOptions* options = nullptr);\r\n```\r\n\r\nFor a sufficiently complicated tool the options object could itself become a sub-configuration builder. For example:\r\n```\r\nclass PdnOptions\r\n{\r\npublic:\r\n RingOptions* add_ring();\r\n};\r\n```\r\n\r\nThe case of an incremental tool is tricky. If asked to do an update I think it should do so according to the last set of options (default or not) that it used. This implies that it must keep a copy of any non-default options object.\r\n\r\nI'm open to other ideas or improvements. I'd love to hear from folks @gadfort @macd @QuantamHD @cdleary @osamahammad21 @antonblanchard @donn @rovinski "}, {"user": "@proppy "}, {"assistant": "I like the idea, but I think I would make a modification to a builder architecture, which I think makes sense for two reasons.\r\n\r\n1. It allows you to do more validation in your builder which would give us the ability ensure that a user can never create an invalid tool configuration. For example creating a PDN that has straps repeat at a greater pitch than the width of the chip (Which I've run into)\r\n2. I like the idea of `ToolOptions` being an Immutable object. It means that a tool cannot modify the options which I think reduces the possibility of tools doing weird things with user provided options.\r\n\r\n```c++\r\nclass ToolOptionsBuilder : OptionBuilder {\r\npublic:\r\n /*\r\n * Not necessarily required in all cases, but could help build default options for a particular PDK, or\r\n * core size etc.\r\n */\r\n ToolOptionsBuilder(Design *);\r\n\r\n void setOptionA(int A);\r\n void setOptionB(bool B);\r\n ErrorOr create(); // could also throw an exception.\r\n}\r\n\r\nclass ToolOptions : ToolOption{\r\nprivate:\r\n ToolOptions(int A, bool B); // a well-defined default state\r\n\r\npublic:\r\n int getOptionA();\r\n bool getOptionB();\r\n};\r\n \r\nclass Tool {\r\npublic:\r\n static ToolOptions* getDefaultOptions(); // calls ToolOptionsBuilder(...).create(); \r\n \r\n // if options is nullptr then the default options are used.\r\n void task(ToolOptions* options = nullptr); \r\n};\r\n```\r\n\r\n\r\n\r\n> ```c++\r\n> // setup\r\n> auto default_options = Tool::getDefaultOptions();\r\n> default_options.setOptionB(false);\r\n> \r\n> // later\r\n> tool->task();\r\n> ```\r\nI don't like the idea of modifying the default options object, seems very error prone.\r\n\r\n\r\n\r\n> Another use model could be\r\n> \r\n> ```c++\r\n> ToolOptionsBuilder options;\r\n> options.setOptionB(false);\r\n> tool->task(options.create());\r\n> ```\r\nI like this model, but with the builder pattern.\r\n\r\n\r\n> This can be extended to the case of one tool calling another internally with an API like:\r\n> \r\n> ```c++\r\n> void task(ToolOptions* options = nullptr,\r\n> AnotherToolOptions* options = nullptr);\r\n> ```\r\nI think this is a greate idea too.\r\n\r\n\r\n> For a sufficiently complicated tool the options object could itself become a sub-configuration builder. For example:\r\n> \r\n> ```c++\r\n> class PdnOptions\r\n> {\r\n> public:\r\n> RingOptions* getRing();\r\n> };\r\n> ```\r\nI like this but again should be constructed using builders.\r\n\r\n\r\n> The case of an incremental tool is tricky. If asked to do an update I think it should do so according to the last set of options (default or not) that it used. This implies that it must keep a copy of any non-default options object.\r\n\r\nI think there's also another problem\r\n1. The common use mode of the tools is to do one step then dump an ODB file. I don't think we can get rid of this use mode, because then it would be impossible to run the tool incrementally. Which is making me feel like we need to serialize them into the database.\r\n\r\nI've thought about it a bunch, and I think storing a hidden only history from a user is probably not the right API instead I suggest. \r\n\r\n```c++\r\nclass Tool {\r\npublic:\r\n static ToolOptions* getDefaultOptions(); // calls ToolOptionsBuilder(...).create();\r\n set incrementalOptions(ToolOptions* options);\r\n \r\n // if options is nullptr then the default options are used.\r\n void task(ToolOptions* options = nullptr);\r\n \r\nprivate:\r\n ToolOptions* incremental_options_;\r\n\r\n};\r\n```\r\n\r\nOn construction the incrementalOptions are set to what's provided in the constructor, or can be updated by the user.\r\n\r\nThis brings up another question about incremental APIs. @maliberty how do you envision a tool getting access to a `Tool` object will the user need to pass one into the options, or something else?\r\n"}, {"assistant": "It's a very interesting question and I feel like I've become jaded because of how inconsistent commercial tools are. It seems like tools (both commercial and OpenROAD) always consist of some combination of the three options you mentioned. What's worse is that commercial tools can be some kind of weird blend of global variables, app variables, tool variables, etc. all with different methods for accessing them... it can get overwhelming.\r\n\r\nI think for the most part, I like the idea of doing away with arguments to commands and having all options passed through some kind of options object. The caveat is that I am split on whether that's appropriate for very simple commands that only take one parameter, like `read_odb [filename]`.\r\n\r\nWhatever the decision is, I _definitely_ want to see a common command / interface that lets a user easily query all parameters that can be set for a tool. For example:\r\n```\r\nopenroad> list_parameters Tool\r\nParameters for command 'Tool':\r\nParameter Type Value Default Description\r\n-------------------------------------------\r\nA int 1 1 Short description of A\r\nB bool 1 0 Short description of B\r\n-------------------------------------------\r\nUse 'help Tool' for more information on this command's parameters\r\n\r\nopenroad> help Tool\r\nParameter Definition\r\n------------------------\r\nA This is a long-form description of A. Here are the valid values, maybe some tips, etc.\r\n The description could be multiple lines.\r\n\r\nB This is a long-form description of B. Here are the valid values, maybe some tips, etc.\r\n\r\nUse 'list_parameters Tool' to list the current values for this command's parameters\r\n```\r\n\r\nHidden state / parameters is one of the things I hate the most about commercial tools. At the same time, a user definitely shouldn't _need_ to set parameters they don't know about, like bin grid size for GPL.\r\n\r\nThese comments are mostly concerning the user-side interface. As for the developer / C++ API, I don't think I have strong opinions. I think the proposed interface sounds ok."}, {"user": "I'm lukewarm on a builder. Your two arguments for it were:\r\n\r\n\"It allows you to do more validation in your builder\". You can just as easily do this validation in the task. If you want to do it in the builder then you will have to restrict when it can be used (ie not before the db is populated) which seems awkward. The builder itself will have to be constructed by the tool to give it enough state for validation.\r\n\r\n\"I like the idea of ToolOptions being an Immutable object. It means that a tool cannot modify the options which I think reduces the possibility of tools doing weird things with user provided options.\" I see two problems. The tool can always clone the options object and do \"weird things\". In gpl for example we set options before calling grt (see https://github.com/The-OpenROAD-Project/OpenROAD/blob/b632f9f5177bc27fe7323beb1e5a97a8c904ccee/src/gpl/src/routeBase.cpp#L374). I wouldn't want to force the user to know to do so."}, {"user": "re \"I don't like the idea of modifying the default options object, seems very error prone.\"\r\n\r\nI have a somewhat similar feeling but I'm also afraid of producing very complex API calls (eg gpl). I think some people would prefer to setup the tools upfront. Also interactively it will save a lot of typing. However I am fine to remove it if there is a consensus that it isn't useful."}, {"user": "Putting the options in the db will open it up to tons of schema updates which is undesirable. Or we would have to make the storage extremely generic which will push the validation on load problem to each tool which isn't much better. Its also error prone for the user.\r\n\r\nI lean toward saying that on reload you don't get any incremental operations. We are living with that today, sta is not incremental across restart."}, {"assistant": "Sorry it's taken me a minute to respond to this- perhaps I can offer a bit of a different perspective being more on the user side, but:\r\n\r\n* Lukewarm on the builder, too. I don't see the utility outside of a niche case where I may elect to build and serialize the options in OpenLane then use it in OpenROAD, but I'm fairly sure that won't be possible regardless.\r\n* I like the idea of immutability vs. modifying a global variable. I get that means more typing, but I think it's worth it just to have less surprises. i.e. I wholeheartedly endorse this model:\r\n```c++\r\nToolOptions options;\r\noptions.setOptionB(false);\r\ntool->task(options);\r\n```\r\n\r\nFrom where I stand, the above model would let me write a single common file to convert OpenLane variables to an OpenROAD ToolOptions object generator, which can then be passed onto other tools. "}, {"user": "@rovinski tcl is a completely different API with lots of manual coding. Converting it look like python, if possible, would introduce the same friction of it looking nothing like usual EDA tools' tcl interface. I don't think it is worth the effort to maintain two sets of APIs. Klayout supporting both python & ruby is much simpler since they are both OO languages. We could do that too more easily (though I have no desire to)."}, {"user": "Based on the discussions I'm wondering if it is preferrable to eliminate the global state and use only explicit options with a default arg:\r\n```\r\nclass Tool\r\n{\r\npublic:\r\n void task(const ToolOptions& options = ToolOptions());\r\n void complex_task(const ToolOptions& options = ToolOptions(),\r\n const AnotherToolOptions& other_options = AnotherToolOptions());\r\n};\r\n```"}, {"assistant": "Should probably add- syntactic sugar in the form of\r\n\r\n```c++\r\nauto options = ToolOptions {\r\n {\"a\", \"value1\"},\r\n {\"b\", \"value2\"}\r\n};\r\n```\r\n\r\ni.e., one that basically takes a dict, with the appropriate bridging to python:\r\n\r\n```python\r\noptions = ToolOptions(\r\n a=\"value1\",\r\n b=\"value2\",\r\n)\r\n```\r\n\r\nwould be pretty cool"}, {"user": "For a next step I want to make a concrete example. Looking at gpl it fits this model well is it is a single task (placement) with many options. \r\n\r\nWhen I look at ifp it is more problematic. It is a tool with multiple semi-related tasks: initFloorplan, insertTieCells, and makeTracks. I don't feel it makes sense to have a single options object to cover such diverse tasks. Perhaps this would be better formulated as TaskOptions rather than ToolOptions. A TaskOptions could replace the need for overloaded methods.\r\n\r\nThis does run the risk of a proliferation of classes - worst case is one for every method. I am hopeful that the number of tasks is fairly limited per tool today."}, {"user": "I created https://github.com/The-OpenROAD-Project/OpenROAD/pull/2809 as a example of what the revised API for gpl could look like. The user tcl layer is unchanged but python and c++ see a new options object. Replace has way too many options so it produces a very large object interface.\r\n\r\nHaving made the change I'm a bit on the fence about keeping it like this versus making either (1) a code generator from a description file or (2) a more weakly typed interface using string (or enum) keys with a variant value and a single get/set method. I'm glad to hear opinions."}, {"user": "Any thoughts on either the existing approach or my other suggestion?"}]} +{"messages": [{"user": "How can I install and run the OpenROAD GUI locally?\r\n\r\nI want the advantages of Docker, not having to install everything, easy to deploy upgrades, but when I run the OpenROAD GUI from docker, the experience is pretty good, but not quite as good as running locally on Ubuntu.\r\n\r\nAnother problem is that the OpenROAD-flow-scripts sets up a TON of environment variables, even if I had OpenROAD GUI installed locally, how could I get the envioronment set up correctly as I build various designs?\r\n\r\nExample of how I run the OpenROAD GUI in Docker. To run my own designs, I map results, log, objects, designs to my local drive by modifying the script in the github issue below.\r\n\r\nhttps://github.com/The-OpenROAD-Project/OpenROAD/issues/2675#issue-1513733033\r\n\r\n\r\nIdeally I'd like a debian package for the OpenROAD GUI. It seems like it should be possible to host a debian package on github, but it is a bit of work, especially considering that it probably needs to be built nightly to be truely useful in the open soruce development process: https://assafmo.github.io/2019/05/02/ppa-repo-hosted-on-github.html\r\n\r\n"}, {"assistant": "Creating a snap package in the CI might be a good option https://ubuntu.com/tutorials/create-your-first-snap#1-overview"}, {"assistant": "You would run the [dependency installer](https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/etc/DependencyInstaller.sh) and then compiler OR locally (build_openroad.sh --local).\r\n\r\nI'm surprised using docker makes much of a difference for the GUI. What do you see?\r\n\r\nYou can always mount your directory in docker so envars shouldn't be a big issue."}, {"assistant": "Have you tried the conda packages?"}]} +{"messages": [{"user": "When I have violations in TritonRoute that can't be resolved, it would be helpful to have some tricks on how to debug this and find the root cause in the RTL.\r\n\r\nIn my case, I eventually found a problem by wandering around in the OpenROAD GUI: I had to tweak my RTL to allow setting some pin constraints.\r\n\r\nIn FPGA tools, knowing the failing timing path start and end register can often, but not always be useful.\u202fSometimes the problem is somewhere completely else in the design and the actual failing timing paths are just a symptom.\r\n\r\nEven so, is there a similar list available somewhere for TritonRoute? A list of start/end registers for problematic routes?"}, {"assistant": "TR generates markers in \"-output_drc $::env(REPORTS_DIR)/5_route_drc.rpt\". They can be loaded in the GUI using the 'drc viewer'. There is also a timing path viewer in the GUI."}]} +{"messages": [{"user": "@jjcherry56 @maliberty \r\nOne of fpga design has custom SDC constraints.\r\n```\r\nset_input_delay 0.0 -clock [get_clocks config_clk_i] [get_ports config_shift_i]\r\n```\r\nIn the final STA report \r\n```\r\nStartpoint: config_shift_i (input port clocked by config_clk_i)\r\nEndpoint: _3723_ (rising edge-triggered flip-flop clocked by config_clk_i)\r\nPath Group: config_clk_i\r\nPath Type: min\r\n\r\nFanout Cap Slew Delay Time Description\r\n-----------------------------------------------------------------------------\r\n 0.00 0.00 clock config_clk_i (rise edge)\r\n 0.00 0.00 clock network delay (propagated)\r\n 0.00 0.00 ^ input external delay\r\n 0.04 0.02 0.02 ^ config_shift_i (in)\r\n 1 0.00 config_shift_i (net)\r\n 0.04 0.00 0.02 ^ hold2/A (sky130_fd_sc_hd__dlygate4sd3_1)\r\n 0.05 0.49 0.51 ^ hold2/X (sky130_fd_sc_hd__dlygate4sd3_1)\r\n 1 0.00 net11 (net)\r\n 0.05 0.00 0.51 ^ hold1/A (sky130_fd_sc_hd__dlygate4sd3_1)\r\n 0.05 0.50 1.01 ^ hold1/X (sky130_fd_sc_hd__dlygate4sd3_1)\r\n 1 0.00 net10 (net)\r\n 0.05 0.00 1.01 ^ _3723_/D (sky130_fd_sc_hd__dfxtp_1)\r\n 1.01 data arrival time\r\n\r\n 0.00 0.00 clock config_clk_i (rise edge)\r\n 0.00 0.00 clock source latency\r\n 0.47 0.34 0.34 ^ config_clk_i (in)\r\n 1 0.04 config_clk_i (net)\r\n 0.47 0.00 0.34 ^ clkbuf_0_config_clk_i/A (sky130_fd_sc_hd__clkbuf_16)\r\n 0.09 0.29 0.63 ^ clkbuf_0_config_clk_i/X (sky130_fd_sc_hd__clkbuf_16)\r\n 4 0.07 clknet_0_config_clk_i (net)\r\n 0.09 0.00 0.63 ^ clkbuf_2_1__f_config_clk_i/A (sky130_fd_sc_hd__clkbuf_16)\r\n 0.11 0.21 0.84 ^ clkbuf_2_1__f_config_clk_i/X (sky130_fd_sc_hd__clkbuf_16)\r\n 7 0.09 clknet_2_1__leaf_config_clk_i (net)\r\n 0.11 0.00 0.85 ^ clkbuf_leaf_6_config_clk_i/A (sky130_fd_sc_hd__clkbuf_16)\r\n 0.08 0.19 1.04 ^ clkbuf_leaf_6_config_clk_i/X (sky130_fd_sc_hd__clkbuf_16)\r\n 21 0.06 clknet_leaf_6_config_clk_i (net)\r\n 0.08 0.00 1.04 ^ _3723_/CLK (sky130_fd_sc_hd__dfxtp_1)\r\n 0.00 1.04 clock reconvergence pessimism\r\n -0.03 1.01 library hold time\r\n 1.01 data required time\r\n-----------------------------------------------------------------------------\r\n 1.01 data required time\r\n -1.01 data arrival time\r\n-----------------------------------------------------------------------------\r\n 0.00 slack (VIOLATED)\r\n```\r\n\r\n\r\nDue to this flow fails with below error in OpenLane:\r\n```\r\n[ERROR]: There are hold violations in the design at the typical corner. Please refer to 'reports/signoff/25-rcx_sta.min.rpt'.\r\n```\r\nIs that must value `> 0.00` required to print slack `MET`?"}, {"assistant": "My guess is that it is something like -0.001 which when rounded to two digits for display appears as zero but is in fact negative. Try -digits 10 to see."}]} +{"messages": [{"user": "Hi, do you know the role of macro that has only OBS without pin. This question is actually irrelevant to OpenROAD, but I\r\nneed a help to understand this.\r\nI found that some of macros, described in the section of \"COMPONENTS\" in def file, is actually included in none of net.\r\nAnd I also found that those weird macros have only OBS without PIN in LEF. I am quite new in VLSI filed, so I don't understand the meaning of this kind of macros at all.\r\nI would be glad if any one can help.\r\n\r\nThanks. "}, {"assistant": "There are a few uses for macros without pins. The primary one is for metrology cells: cells that the fab requires you to insert in order to fabricate the chip. These cells can be marker cells which are used to optically align the chip between lithography steps. There can also be cells for measuring the process steps, e.g. whether an etch or lithography step was within the fab's process parameters or not, and to tune equipment.\r\n\r\nI can also imagine there being cells which are meant to be contacts (or breakers) to the substrate. Technically, these should have the substrate contacts defined as pins, but never doubt that a PDK has been poorly defined. On that note, don't rule out that the PDK could simply have an error in it and the cell was improperly extracted.\r\n\r\n[Here](https://www.mems-exchange.org/users/masks/intro-equipment.html) is a decent reference on alignment markers."}]} +{"messages": [{"user": "Hi, when I enter the command `openroad -gui` to check the results of [OpenFASOC](https://github.com/idea-fasoc/OpenFASOC), I meet this error:\r\n`[ERROR] This code was compiled with the GUI disabled. Please recompile with Qt5 if you want the GUI.`\r\n`%` \r\nSO, how to rebuild openroad with Qt5? Thanks."}, {"assistant": "When you built OR couldn't find Qt installed so it compiles without it. Please make sure you have Qt installed on your system. The easiest way it to use https://github.com/The-OpenROAD-Project/OpenROAD/blob/master/etc/DependencyInstaller.sh to get all needed dependencies."}]} +{"messages": [{"user": "Hello,\r\n\r\nI am trying to do floorplanning with OpenROAD with ISPD benchmark superblue16, but I am struggling with so many problems.\r\nI am quite new to this filed, so my knowledge for this filed is not high enough.\r\nI uploaded .lef, .def. and .v field given by ISPD and tried to do floorplan, but this error line \"LEF MASTER ~CELL HAS NO LIBERTY CELL\" appeared and does not work at all. \r\nI am glad if anyone has any idea about this error and how to work with this kind of open bench mark.\r\n\r\nThanks"}, {"assistant": "I don't see any uploaded files. Based on the message you have a cell called \"~CELL\" that exists in LEF but for which you have no .lib."}, {"user": "Thanks to all of you\r\nI followed the order of commands that @QuantamHD recommended and it worked although LEF file seems to have some syntax errors.\r\nGlobal placement (GPL) worked well, so I am very happy with this result. As @rovinski mentioned, global placement also worked without importing .lib file. Regarding with global placement, I have none of problem. I appreciate to all of you.\r\n\r\nI am also trying to run floorplanning with openroad as I want to follow the paper (https://vlsicad.ucsd.edu/Publications/Conferences/389/c389.pdf), embedded in the floorplan machine for openroad.\r\n\r\nAlthough the ISPD contest porblem is provided as \"floorplan\" finished, I want to re-floorplan with openroad and\r\ncompare the results between openroad and as it is given. \r\n\r\nI tried the commands as shown below,\r\n```\r\nread_verilog superblue16.v\r\nread_lef tech.lef\r\nread_lef superblue16.lef\r\nread_lib superblue16_Early.lib\r\nlink_design superblue16\r\nwrite_def superblue16.def\r\nread_def superblue16.def -floorplan_initialize\r\npartition_design -max_num_inst 1000 -min_num_inst 200 -max_num_macro 1 -min_num_macro 0 -net_threshold 0 -virtual_weight 500 -report_directory . -report_file report\r\n```\r\nAm I on the right track?\r\n\r\n"}]} +{"messages": [{"user": "After install, trying to run the docker I get the following. ny ideas?\r\n\r\nUnable to find image 'openroad/flow-scripts:latest' locally\r\ndocker: Error response from daemon: pull access denied for openroad/flow-scripts, repository does not exist or may require 'docker login': denied: requested access to the resource is denied."}, {"assistant": "How did you 'install' it? What command did you run that gave this message?"}, {"user": "Thanks for you response, but I decided to do a local install of OpenROAD-flow-scripts instead, since I would have a learning curve with docker. \r\n\r\n"}]} +{"messages": [{"user": "Hi, guys. I have some problem, when I cmake openSTA, as well as replace/openROAD. Error in Main.cc saying 'Tcl_Main' is not defined."}, {"assistant": "Exactly what steps are you running and with which commit id?"}]} +{"messages": [{"user": "Hi Folks,\r\n\r\njust a heads up for anybody using an Apple M1 with the most recent Xcode 14.0.1\r\n\r\nApple clang 14.0.0 randomly coredumps compiling abc .c files. But not deterministically, restarting ./build_openroad.sh will eventually compile some of them til it finally always coredumps compiling extraUtilMisc.c.\r\n\r\nI was able to compile OpenROAD on this machine before, but not with the latest and greatest Xcode.\r\n\r\nI'm curious whether there are other M1/Xcode users out there with similar experience.\r\n\r\nStefan\r\n\r\ngmake[2]: Entering directory '/Users/user/OpenROAD-flow-scripts/tools/OpenROAD/build'\r\n[ 0%] Building CXX object third-party/abc/CMakeFiles/libabc.dir/src/misc/extra/extraUtilMisc.c.o\r\ncd /Users/user/OpenROAD-flow-scripts/tools/OpenROAD/build/third-party/abc && /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/c++ -I/Users/user/OpenROAD-flow-scripts/tools/OpenROAD/third-party/abc/src -O3 -DNDEBUG -arch arm64 -isysroot /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX12.3.sdk -Wall -Wno-array-bounds -Wno-nonnull -Wno-unused-variable -Wno-unused-function -Wno-write-strings -Wno-sign-compare -Wno-deprecated -Wno-c++11-narrowing -Wno-register -Wno-format -Wno-reserved-user-defined-literal -DABC_USE_STDINT_H=1 -DABC_MEMALIGN=4 -DABC_NAMESPACE=abc -fpermissive -DABC_USE_CUDD=1 -DABC_USE_PTHREADS -Wno-unused-but-set-variable -std=c++17 -MD -MT third-party/abc/CMakeFiles/libabc.dir/src/misc/extra/extraUtilMisc.c.o -MF CMakeFiles/libabc.dir/src/misc/extra/extraUtilMisc.c.o.d -o CMakeFiles/libabc.dir/src/misc/extra/extraUtilMisc.c.o -c /Users/user/OpenROAD-flow-scripts/tools/OpenROAD/third-party/abc/src/misc/extra/extraUtilMisc.c\r\nclang: error: unable to execute command: Segmentation fault: 11\r\nclang: error: clang frontend command failed due to signal (use -v to see invocation)\r\nApple clang version 14.0.0 (clang-1400.0.29.102)\r\nTarget: arm64-apple-darwin21.6.0\r\nThread model: posix\r\nInstalledDir: /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin\r\n"}, {"user": "downgrading the command line tools to 13.4 allows to build the project"}, {"user": "Here's some feedback from https://developer.apple.com/forums/thread/717259\r\n\r\n> It only happens with optimized code. An alternative workaround for building openroad is to patch the abc cmake file to include -g\r\n\r\nthird-party/CMakeLists.txt @@ -46,6 +46,10 @@ if (NOT USE_SYSTEM_ABC)\r\nreadline is not needed since we call abc from c++\r\nset(READLINE_FOUND FALSE)\r\n+# apple clang 14.0.0 seg faults on abc without -g +add_compile_options(\r\n$<$:-g>\r\n+) add_subdirectory(abc)\r\nendif()"}, {"user": "clang-1400.0.29.202 as part of Xcode 14.1.0 compiles OpenRoad without issues"}]} +{"messages": [{"user": "Hey guys! I am getting the following compilation error:\r\n\r\n> [100%] Linking CXX executable openroad\r\n> cd /home/gudeh/Documents/OpenROAD-flow-scripts/tools/OpenROAD/build/src && /usr/local/bin/cmake -E cmake_link_script CMakeFiles/openroad.dir/link.txt --verbose=1\r\n> /usr/bin/c++ -O3 -DNDEBUG -Wl,--export-dynamic -rdynamic CMakeFiles/openroad.dir/Design.cc.o CMakeFiles/openroad.dir/Tech.cc.o CMakeFiles/openroad.dir/OpenRoad.cc.o CMakeFiles/openroad.dir/Main.cc.o -o openroad ifp/src/ifp.a openroad_swig.a gpl/gpl.a dpl/dpl.a dpo/dpo.a fin/fin.a rsz/src/rsz.a ppl/ppl.a stt/stt.a dbSta/src/dbSta.a ../../src/sta/app/libOpenSTA.a odb/src/db/libodb.a odb/src/swig/tcl/odbtcl.a rcx/src/rcx.a rmp/src/rmp.a cts/src/cts.a grt/grt.a tap/src/tap.a gui/gui.a drt/drt.a dst/dst.a mpl/mpl.a mpl2/mpl2.a psm/src/psm.a ant/src/ant.a par/par.a utl/utl.a pdn/src/pdn.a ../third-party/abc/libabc.a /usr/lib/x86_64-linux-gnu/libtcl.so -lpthread /usr/lib/x86_64-linux-gnu/libtclreadline.so /usr/lib/x86_64-linux-gnu/libz.so _openroad_swig_py.a odb/src/swig/python/_odbpy.a ifp/src/_ifp_py.a /usr/lib/x86_64-linux-gnu/librt.so ppl/src/munkres/libMunkres.a -lm -ldl -lrt rsz/src/rsz.a grt/grt.a ant/src/ant.a grt/grt.a ant/src/ant.a dpl/dpl.a grt/src/fastroute/libFastRoute4.1.a stt/stt.a sta/sta_swig.a /usr/local/lib/libboost_serialization.a /usr/local/lib/libboost_system.a /usr/local/lib/libboost_thread.a /usr/lib/gcc/x86_64-linux-gnu/9/libgomp.so /usr/lib/x86_64-linux-gnu/libpthread.so /usr/local/lib/libboost_serialization.a mpl/src/ParquetFP/libParquetFP.a par/src/MLPart/libMLPart.a dbSta/src/dbSta.a gui/gui.a /usr/lib/x86_64-linux-gnu/libQt5Widgets.so.5.12.8 /usr/lib/x86_64-linux-gnu/libQt5Gui.so.5.12.8 /usr/lib/x86_64-linux-gnu/libQt5Core.so.5.12.8 ../../src/sta/app/libOpenSTA.a odb/src/db/libodb.a odb/src/defout/libdefout.a odb/src/lefout/liblefout.a odb/src/tm/libtm.a /usr/lib/x86_64-linux-gnu/libtcl.so odb/src/cdl/libcdl.a odb/src/swig/common/libodb_swig_common.a odb/src/defin/libdefin.a odb/src/def/libdef.a odb/src/def/libdefzlib.a odb/src/lefin/liblefin.a odb/src/zutil/libzutil.a utl/utl.a /usr/local/lib/libspdlog.a -lpthread odb/src/lef/liblef.a odb/src/lef/liblefzlib.a /usr/lib/x86_64-linux-gnu/libz.so /usr/lib/x86_64-linux-gnu/libpython3.8.so \r\n> /usr/bin/ld: drt/drt.a(TritonRoute.cpp.o): in function \\`boost::archive::basic_binary_iarchive::init()':\r\n> TritonRoute.cpp:(.text._ZN5boost7archive21basic_binary_iarchiveIN2fr10frIArchiveEE4initEv[_ZN5boost7archive21basic_binary_iarchiveIN2fr10frIArchiveEE4initEv]+0xc4): undefined reference to `boost::archive::detail::basic_iarchive::set_library_version(boost::archive::library_version_type)'\r\n> collect2: error: ld returned 1 exit status\r\n> make[2]: *** [src/CMakeFiles/openroad.dir/build.make:210: src/openroad] Error 1\r\n> make[2]: Leaving directory '/home/gudeh/Documents/OpenROAD-flow-scripts/tools/OpenROAD/build'\r\n> make[1]: *** [CMakeFiles/Makefile2:449: src/CMakeFiles/openroad.dir/all] Error 2\r\n> make[1]: *** Waiting for unfinished jobs....\r\n> [100%] Linking CXX executable trTest\r\n> cd /home/gudeh/Documents/OpenROAD-flow-scripts/tools/OpenROAD/build/src/drt && /usr/local/bin/cmake -E cmake_link_script CMakeFiles/trTest.dir/link.txt --verbose=1\r\n> /usr/bin/c++ -O3 -DNDEBUG CMakeFiles/trTest.dir/test/gcTest.cpp.o CMakeFiles/trTest.dir/test/fixture.cpp.o CMakeFiles/trTest.dir/test/stubs.cpp.o CMakeFiles/trTest.dir/__/gui/src/stub.cpp.o -o trTest drt.a ../odb/src/db/libodb.a ../stt/stt.a ../dst/dst.a ../sta/sta_swig.a /usr/local/lib/libboost_serialization.a /usr/local/lib/libboost_system.a /usr/local/lib/libboost_thread.a ../dbSta/src/dbSta.a ../gui/gui.a ../odb/src/db/libodb.a ../odb/src/cdl/libcdl.a ../odb/src/defin/libdefin.a ../odb/src/def/libdef.a ../odb/src/def/libdefzlib.a ../odb/src/defout/libdefout.a ../odb/src/lefin/liblefin.a ../odb/src/lef/liblef.a ../odb/src/lef/liblefzlib.a ../odb/src/lefout/liblefout.a ../odb/src/tm/libtm.a ../odb/src/zutil/libzutil.a /usr/lib/x86_64-linux-gnu/libtcl.so /usr/lib/x86_64-linux-gnu/libQt5Widgets.so.5.12.8 /usr/lib/x86_64-linux-gnu/libQt5Gui.so.5.12.8 /usr/lib/x86_64-linux-gnu/libQt5Core.so.5.12.8 ../../../src/sta/app/libOpenSTA.a ../utl/utl.a /usr/local/lib/libspdlog.a -lpthread /usr/lib/gcc/x86_64-linux-gnu/9/libgomp.so /usr/lib/x86_64-linux-gnu/libpthread.so /usr/local/lib/libboost_serialization.a /usr/lib/x86_64-linux-gnu/libz.so \r\n> make[2]: Leaving directory '/home/gudeh/Documents/OpenROAD-flow-scripts/tools/OpenROAD/build'\r\n> [100%] Built target trTest\r\n> make[1]: Leaving directory '/home/gudeh/Documents/OpenROAD-flow-scripts/tools/OpenROAD/build'\r\n> make: *** [Makefile:133: all] Error 2\r\n\r\nThe error I pasted here is from a clean clone from the flow repository. I did the following commands to get to this error:\r\n\r\n> git clone --recursive https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts\r\n> cd OpenROAD-flow-scripts\r\n> sudo ./tools/OpenROAD/etc/DependencyInstaller.sh -dev\r\n> ./build_openroad.sh --local\r\n\r\nI noticed that if I run DepdencyInstaller multiple times it actually updates and compile Boost everytime. Not sure how to proceed, any help is welcome."}, {"assistant": "What OS and what compiler?"}, {"assistant": "The log unfortunately doesn't have the boost version so I just added print that in the OR master branch. What version of boost do you have installed?"}, {"user": "Hi everyone, I was able to solve the issue by manually updating Boost. I used the links from [this stackoverflow page](https://stackoverflow.com/questions/2829523/upgrading-boost-version) and set the \"-prefix=\" with the same location my Boost was already installed. Also, I had to clean my previous build from OR.\r\n\r\nIt seems that for some reason the DependencyInstaller didn't fetch the correct Boost version to upgrade to."}, {"assistant": "@vvbandeira any idea about \" for some reason the DependencyInstaller didn't fetch the correct Boost version to upgrade to.\"?"}]} +{"messages": [{"user": "Hi, i want to understand how my Verilog after synthesis is replaced by transistor (of sky130 by example).\r\nWhere can I found this information ?\r\nWhat's tools do that in the flow ?\r\n\r\nThanks a lot !"}, {"assistant": "yosys maps the verilog to gates. OpenRoad places and routes the gates. Klayout substitutes the gates with their gds equivalent layout that contains transistors."}]} +{"messages": [{"user": "Is there a mechanism I can use to select which nets to route or not route with the global and detail routers?"}, {"assistant": "There is no user control currently. The only trick you could play is to temporarily mark the nets not to route as special nets and then rest when done routing. \r\n\r\nWhat is your use case?"}]} +{"messages": [{"user": "Is there a way to get unidirectional routing?"}, {"assistant": "If your LEF has a RECTONLY constraint or multiple masks then you will get unidirectional routing. We don't have a direct user knob for that. You can also create the constraint directly using the odb APIs."}]} +{"messages": [{"user": "Hi, There is any way to contribute to the openRoad project?"}, {"assistant": "They accepted code changes through PRs.\r\n\r\nIs there something you are interested in working on? "}, {"assistant": "We are glad to have contributors. Do you want some suggestions or do you have something in mind?"}, {"assistant": "To help narrow it a bit are you more interested in development, testing, documentation, outreach? If you are willing to share a bit about yourself it would help to find a task of appropriate complexity.\r\n\r\nOn the development side one idea that comes to mind is to improve write_abstract_lef written by @QuantamHD to give more precise obstructions. I can describe that further if it is of interest."}, {"assistant": "The LEF abstract is a physical model of a block that is intended to be used at a higher level in the hierarchy to model the interface and obstructions in the block. The current code starts from https://github.com/The-OpenROAD-Project/OpenROAD/blob/c4a8479c341c31fd0db26a17f4a909f59285cf58/src/odb/src/lefout/lefout.cpp#L1213\r\n\r\nThe current code is rather simplistic in its modeling of obstructions. If you look at lefout::getTechLayerObstructions it just gathers a set of layers that have any shapes on them and then blocks the entire layer.\r\n\r\nI think it would be better to use Boost polygon to OR together the shapes on each layer; do a bloat then shrink cycle to merge them into simpler shapes and then write out the result as the layer obstruction. The amount of bloating could be a user control with a reasonable default (say 2*pitch). \r\n\r\nThe goal is to balance model size with precision. Does this make sense? I can go into more detail where needed."}, {"assistant": "Please keep in mind that there are two types of abstracts used by $$$ tools. The \u201ccutout\u201d where obstructions are cut out around pins and the \u201ccover everything\u201d where the pins are at the edges and the block is completely covered with obstruction. For the latter to work, the router has to be smart enough to route to covered pins and drc has to know that covered pins on the edge are ok too. It\u2019s good practice to have pins on the edge of blocks anyways."}, {"assistant": "You can see gcd_abstract* in https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/odb/test for two examples. \r\n\r\nThe idea of the bloat/shrink cycle is to merge nearby shapes. I've tried to quickly illustrate it with:\r\n![image](https://user-images.githubusercontent.com/761514/180689779-273f4b34-d299-4251-a372-10437d7c246a.png)\r\n\r\nYou can learn about Boost polygon at https://www.boost.org/doc/libs/1_79_0/libs/polygon/doc/index.htm (the docs aren't great)."}, {"assistant": "The red boxes in the middle image merge together into a single polygon"}, {"user": "Hi, I will love to get some help in 2 issues.\r\nFirst I will need to import to boost::polygon library, in which file can I do it? Do other part of the code already import it?\r\n\r\nSecond, I having trouble to understand how can I test my change, I gather all the shapes into kind of list and I now write it into the lef file instead the whole block boundary bbox, but I probably got some mistake so I want to run some test to debug it.\r\nThere is any tutorial how can I do it? "}, {"user": "Hi, So I make some progress with the abstract lef.\r\nBut I encounter on some problem that I would like to get some help.\r\n\r\nSo I modify the abstract lef that in order to write the merge between all the rect that intersect ( after bloat ).\r\nTo demonstrate it I edit the picture from above:\r\n \r\n![image](https://user-images.githubusercontent.com/61157132/186626392-73d8ee81-e11e-4ba1-8e75-b7668e319b47.png)\r\n\r\nThe green rect is currently my OBS which isn't very efficient, but i didn't found any easy way to do it with the utils in the rect class.\r\n\r\nSo I am guessing that I need to go back to your first suggestion which is use boost polygon to OR all the rect, my problem is that is after that I will need to convert it back into different rects, there is any easy way to do that?\r\n\r\n"}, {"assistant": "https://www.boost.org/doc/libs/1_79_0/libs/polygon/doc/gtl_polygon_90_set_concept.htm\n\nHave a look at get_rectangles and get_max_rectangles\n\nOn Aug 25, 2022, at 02:20, niv280 ***@***.***> wrote:\n\n\ufeff\nHi, So I make some progress with the abstract lef.\nBut I encounter on some problem that I would like to get some help.\n\nSo I modify the abstract lef that contained the merge between all the rect that intersect.\nTo demonstrate I edit the picture above:\n\n\n\nThe green rect is currently my OBS which isn't very efficient, but i didn't found any easy way to do it with the utils in the rect class.\nSo I am guessing that I need to go back to your first suggestion which is use boost polygon to OR all the rect, my problem is that is after that I will need to convert is back into different rects, there is any easy way to do that?\n\n\u2014\nReply to this email directly, view it on GitHub, or unsubscribe.\nYou are receiving this because you commented."}, {"assistant": "get_rectangles would be the better choice as get_max_rectangles may produce overlapping rectangles. You an experiment with the slicing direction to see what produces a more minimal result. My guess is the non-preferred routing direction will work best."}]} +{"messages": [{"user": "Hi all, I am trying to execute the OpenROAD in a cluster machine. However, in this machine, I am not able to install the dependencies to compile the OpenROAD or even use the docker image to run the OpenROAD.\r\n\r\nI was wondering if it is possible to set a cmake flag to generate a static binary (without any dependencies) for the OpenROAD project. With this, I will be able to run this binary on every machine that I need.\r\n\r\nDoes someone know how to do this? "}, {"assistant": "@vvbandeira Any suggestion?"}, {"assistant": "Bazel rules hdl supports fully static builds of openroad.\r\n\r\nJust download bazel, git clone https://github.com/hdl/bazel_rules_hdl\r\n\r\nAnd run bazel build @org_theopenroadproject//:openroad in the git repo. \r\n\r\nIt also statically builds the entire dependency chain of openroad from source."}]} +{"messages": [{"user": "When I run any of the test files such as gcd_ sky130hd.tcl file on the GUI, I realized that there are no Pad cells in the layout. So I am asking if there is a way to source the Pads within the TCL file. "}, {"assistant": "@OmarLOay99 \r\nAre you looking for the test case with pads?\r\n\r\nIf yes then check this: https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/pad/test"}]} +{"messages": [{"user": "Just to share my experience, I found 2 ways to setup the layer map table from LEF to GDS within the OpenROAD flow :\r\n\r\n - in the klayout .lyt file, in the statement, you need this line to describe the layer_map table for each layer of the LEF tech file :\r\n layer_map('METAL1:1/0'; 'METAL1.LABEL:1/3'; 'METAL1.PIN:1/9'; 'METAL2:2/0'; 'METAL2.LABEL:2/3'; 'METAL2.PIN:2/9'; 'METAL3:3/0'; 'METAL3.LABEL:3/3'; 'METAL3.PIN:3/9'; 'VIA1:5/0'; 'VIA2:6/0'; 'OUTLINE:10/0')\r\n\r\n- you can describe it in a separate file stated in the platform/my_tech/config.mk file with : \r\n export GDS_LAYER_MAP = $(PLATFORM_DIR)/layermap.txt\r\n then, you need to write that file : platform/my_tech/layermap.txt as described here :\r\n https://www.klayout.de/forum/discussion/2092/syntax-for-layoutoptions-lefdef-config-map-file :\r\n \r\n \r\n # KLayout LEF mapping file for my_tech\r\n DIEAREA ALL 10 0\r\n MET1 NET,VIA 1 0\r\n NAME MET1/PIN 1 3\r\n MET1 PIN 1 9\r\n MET2 NET,VIA 2 0\r\n NAME MET2/PIN 2 3\r\n MET2 PIN 2 9\r\n MET3 NET,VIA 3 0\r\n NAME MET3/PIN 3 3\r\n MET3 PIN 3 9\r\n VIA1 NET,VIA 5 0\r\n VIA2 NET,VIA 6 0\r\n OUTLINE LEFPIN 10 0\r\n\r\nBRgds,\r\nLaurent"}, {"user": "For the sky130hs and sky130hs process and libraries, the only way I have found to get the proper GDS layers in the 6_final.gds is to add the file layermap.txt (below) in the platforms/sky130hs and platforms/sky130hs and add the following line :\r\n\r\nexport GDS_LAYER_MAP = ../../../../$(PLATFORM_DIR)/layermap.txt\r\n\r\nin the files platforms/sky130hs/config.mk and platforms/sky130hd/config.mk\r\n\r\nBRgds,\r\nLaurent\r\n\r\nlayermap.txt file : also in : https://github.com/laurentc2/SKY130_for_KLayout/blob/main/layermap.txt :\r\n\r\n # KLayout mapping file for sky130\r\nDIEAREA ALL 100 0\r\n\r\nli1 NET,SPNET,VIA 67 20\r\nNAME li1/PIN 67 5\r\nli1 PIN,LEFPIN 67 16\r\n\r\nmcon VIA 67 44\r\nmcon PIN,LEFPIN 67 48\r\n\r\nmet1 NET,SPNET,VIA 68 20\r\nNAME met1/PIN 68 5\r\nmet1 PIN,LEFPIN 68 16\r\n\r\nvia VIA 68 44\r\nvia PIN,LEFPIN 68 58\r\n\r\nmet2 NET,SPNET,VIA 69 20\r\nNAME met2/PIN 69 5\r\nmet2 PIN 69 16\r\n\r\nvia2 VIA 69 44\r\nvia2 PIN,LEFPIN 69 58\r\n\r\nmet3 NET,SPNET,VIA 70 20\r\nNAME met3/PIN 70 5\r\nmet3 PIN,LEFPIN 70 16\r\n\r\nvia3 VIA 70 44\r\nvia3 PIN 70 58\r\n\r\nmet4 NET,SPNET,VIA 71 20\r\nNAME met4/PIN 71 5\r\nmet4 PIN 71 16\r\n\r\nvia4 VIA 71 44\r\nvia4 PIN,LEFPIN 71 48\r\n\r\nmet5 NET,SPNET,VIA 72 20\r\nNAME met5/PIN 72 5\r\nmet5 PIN,LEFPIN 72 16\r\n\r\n"}]} +{"messages": [{"user": "Hello, I am testing the global placement of RePlAce with the testcases in [standalone branch](https://github.com/The-OpenROAD-Project/RePlAce/tree/standalone) version, and I find the result is not quite what I suppose it should be.\r\n\r\nI tried [gcd_nontd_test.tcl](https://github.com/The-OpenROAD-Project/RePlAce/blob/standalone/test/gcd_nontd_test.tcl), and I opened the result def file along with [gcd.v](https://github.com/The-OpenROAD-Project/RePlAce/blob/standalone/test/design/nangate45/gcd/gcd.v) in Cadence Innovus.\r\nThe resulting layout is like this:\r\n![image](https://user-images.githubusercontent.com/55183618/169835277-233c17d0-a033-474d-835f-f7b7660ce5ed.png)\r\n![image](https://user-images.githubusercontent.com/55183618/169835295-c3641baf-b217-4851-aff8-93cad86c7295.png)\r\n\r\nHere are my questioins:\r\n(1) Why are the standard cells not on the \"row\" the input lef/def file has defined?\r\nIn fact, none of the cells is on the correct y-coordinate of any of the predefined rows.\r\n\r\n(2) Why is there overlapping?\r\n\r\n(3) How can I get a result like the GIF in [README.md](https://github.com/The-OpenROAD-Project/RePlAce/blob/standalone/README.md)? \r\nShould I add any options when executing the binary file? If yes, what should I do exactly?\r\n\r\n(4) I have noticed the limitation mentioned in [README.md](https://github.com/The-OpenROAD-Project/RePlAce/blob/standalone/README.md): *Mixed-sized RePlAce with (LEF/DEF/Verilog) interface does not generate legalized placement*. \r\nDoes it mean that RePlAce is not capable of generating legal placement for either single-size or mixed-sized standard cells placement? \r\nOr, does it mean that RePlAce can generate legal placement for single-size standard cells placement but cannot for mixed-sized standard cells placement? \r\n\r\np.s. I only need the GPL results. DPL is not neccesary for me."}, {"assistant": "Replace is a global placer; you need to run detailed placement to see non-overlapping, in-row placement. The gif will have overlaps if you could zoom in."}]} +{"messages": [{"user": "Hello everyone!\r\n\r\nI'm in the process of bringing up a new platform which is going well. I am running into a problem with a local interconnect layer which is specified as a `MASTERSLICE` with `LEF58_TYPE` = `MEOL`, so it is not specified as a `ROUTING` layer as is the case with the sky130 PDK. OpenDB complains that there is a parse mismatch for this `lil` layer.\r\n\r\nIf I add this `lil` layer as a routing layer to `make_tracks.tcl` then OpenDB complains that it is not a routing layer. If I don't add `lil` as a routing layer, then TritonRoute gives an error that it cannot find layer `lil` for viarule that connects `lil` to the first metal layer.\r\n\r\nDid anyone else run into a similar problem? If so, how did you solve it?"}, {"assistant": "Please include the odb message. You should not add tracks if it is not a routing layer."}, {"assistant": "We need to add support for MEOL. You can workaround it my making it a masterslice layer temporarily."}]} +{"messages": [{"user": "I have seen an example of a via/cut spacing rule between different layers.\r\nFor example : v4 space v5 >= 38\r\nCan/does the detailed router support this?"}, {"assistant": "Its helpful to ask about a specific LEF rule but yes it does support cut spacing between layers."}, {"assistant": "![image](https://user-images.githubusercontent.com/761514/169117659-453ea3a8-10cb-4794-bb41-16558182e3f8.png)\r\n"}]} +{"messages": [{"user": "This #openlane slack channel conversation. https://skywater-pdk.slack.com/archives/C016H8WJMBR/p1652291545428459\r\n\r\nUser want to create a placement blockage to avoid placement of standard cells in that particular area.\r\n\r\nIs that feature available?\r\n\r\nIf yes please point us command...\r\n\r\n@maliberty fyi"}, {"assistant": "We support them coming from DEF. You can use the odb api to create them in the database directly (dbBlockage_create) but we don't have a user-level command to make that nicer."}]} +{"messages": [{"user": "Hello, \r\nI would like to know if the grid can be exported after the processing of the global router output and/or the TA step.\r\n\r\nI'm planning on trying some other AI based approaches instead of Heuristics. And if I can export the grid or the clips it would be more helpful.\r\n\r\nAny idea/help will be much appreciated!"}, {"assistant": "Do you mean the gcell grid? There are messages\r\n\r\n\"GCELLGRID X {} DO {} STEP {} ;\",\r\n\"GCELLGRID Y {} DO {} STEP {} ;\",\r\n\r\nthat will give you those values. They don't change during drt."}, {"assistant": "The post-processed guides are generated as output_guide.mod in ORFS (controlled by -output_guide). Other internal state of the router is not exported today."}, {"assistant": "Its the same guide format as the input guide file"}, {"user": "Hello again,\r\nI would like to get the access points to each pin in a net and I saw [this on another discussion](https://github.com/The-OpenROAD-Project/OpenROAD/discussions/625?sort=new#discussioncomment-636424), however, when I tried it the coordinates didn't make sense.\r\nFor example when I try it on the nangate45 gcd, for the _000_ net we have: `_000_ ( _672_ D ) ( _504_ ZN ) + USE SIGNAL`\r\nand the components in the net are `_672_ DFF_X2 + PLACED ( 107540 145600 ) N ;` and `_504_ OAI21_X1 + PLACED ( 107540 148400 ) FS ;`\r\nand this is the output of the code\r\nnet _000_ \r\n( 46930 141260 ) layerNum 2 metal1 \r\n( 46930 141120 ) layerNum 2 metal1\r\n( 46740 141260 ) layerNum 2 metal1\r\n( 51490 146580 ) layerNum 2 metal1\r\n( 51490 146860 ) layerNum 2 metal1\r\n( 51490 147140 ) layerNum 2 metal1\r\n( 51490 147420 ) layerNum 2 metal1\r\n( 50730 147420 ) layerNum 2 metal1\r\n( 51870 147420 ) layerNum 2 metal1\r\n( 51870 147700 ) layerNum 2 metal1\r\n( 51870 147980 ) layerNum 2 metal1\r\n( 51110 147420 ) layerNum 2 metal1\r\n\r\nSo from what I see these coordinates can't be correct, any idea why is this happening?"}]} +{"messages": [{"user": "Hi guys, congratulations on all the great job done with the OpenROAD project!! I want to use it to develop my ideas during my Ph.D.\r\n\r\nI am trying to build a dataset for graph neural network training. My idea is to perform physical design predictions with a mapped circuit before P&R. I am trying to extract features from Verilog with Yosys, send them to the DGL python library and perform training with DGL. These steps are already operational, but I am missing an essential aspect of the prediction: the label! \r\n\r\nTo solve the mentioned issue **I would like to have the data shown by the heatmaps in the GUI, such as placement density and routing congestion**. I would like them not as images but the actual numeric values. The positions of the cells and wires would also be essential. \r\n\r\n- Can anyone point me to which path I should go to get this data? I understand all of it is already processed by the code to show the images in the GUI. I just need to find it. \r\n- Would there be any TCL command which could help me with that? \r\n- Or my best shot is to try and use the odb database and edit some code? \r\n\r\nI noticed there are some heatmap codes in [./src/gui/src](https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/gui/src), but there are so many attributes and methods. Also, I am not used to the odb database yet. Any help is welcome."}, {"user": "By the way I couldn't find the path `./build/src/swig/tcl/opendbtcl` and `./build/src/swig/tcl/opendb_wrapper.cpp` as mentioned in [the documentation](https://openroad.readthedocs.io/en/latest/main/src/odb/README.html)."}, {"assistant": "The bit of documentation is out of date as we now include the tcl functionality in openroad itself and no longer build standalone executables for odb. (@vvbandeira)\r\n\r\n@arlpetergadfort My first thought was to look at each engine but maybe it would be easier to provide a dump_heatmap command in the GUI since it has already abstracted the interface to each engine. Does that seem reasonable to you?"}, {"assistant": "#1612 is merged so you should be good to go."}, {"assistant": "You are repeating the previous rule and probably want something like:\r\n\r\nmy_gui: my_gui_6_final.def\r\n$(foreach file,$(RESULTS_DEF),my_gui_$(file)): my_gui_%:\r\n\r\nYou are getting the bbox of each instance. You'll have to map that back to the grid you are working with (an instance may be across a boundary as well)."}, {"user": "Hey guys, I have some issues with the heatmap features. I noticed that running the GCD project from a fresh OpenROAD-flow with this exact sequence of commands:\r\n```\r\ngit clone --recursive https://github.com/The-OpenROAD-Project/OpenROAD-flow-scripts.git\r\ncd OpenROAD-flow-scripts/\r\nsudo ./build_openroad.sh --local\r\ncd flow\r\nmake\r\nmake gui_final\r\n```\r\nRenders no output on the circuit's image when clicking on the checkbox for `Placement Density`. The `Power Density` checkbox works fine. Furthermore, clicking on `Routing Congestion` and `IR Drop` gives the error message bellow and shows no heatmap in the image.\r\n```\r\n[WARNING GUI-0066] Heat map \"Routing Congestion\" has not been populated with data.\r\n[WARNING GUI-0066] Heat map \"IR Drop\" has not been populated with data.\r\n```\r\n\r\nIf I run the AES project I can see the Placement and Power heatmaps. Although I have the same errors with Routing and IR Drop.\r\n\r\nThe Routing and IR Drop also gives errors when trying to call gui::dump_heatmap: `[ERROR GUI-0072] \"Routing Congestion\" is not populated with data.`\r\nI also noticed that the CSVs provided by the gui::dump_heatmap command gives bouding boxes with different sizes for Placement and Power, is this expected?\r\n"}, {"assistant": "I don't see any issue with placement density. This is gcd/ng45:\r\n![image](https://user-images.githubusercontent.com/761514/153918958-d33becda-6a06-417a-a685-463e6076575a.png)\r\n"}, {"assistant": "@arlpetergadfort I'm seeing:\r\n```\r\n>>> read_guides results/nangate45/gcd/base/route.guide\r\n[WARNING GUI-0066] Heat map \"Routing Congestion\" has not been populated with data.\r\n```\r\nThis used to work - do you know what has changed?"}, {"user": "Hi again! I am progressing with my dataset generation. Looking real promising. I am only having issues trying to close the gui. Even if I use gui::hide it goes to the `openroad>` command option in terminal. How can I exit it the gui AND the openroad afterwards via a TCL file? [This is what I have tried](https://github.com/gudeh/OpenROAD-flow-scripts/blob/master/flow/scripts/getLabels.tcl). As seen in the last lines.\r\n\r\nBy the way if you uncoment the part where I try to use the Routing and IRdrop heatmaps the gui::hide doesn't work."}, {"user": ""}, {"user": "Hi everyone! I am coming back to this project. I was focusing on other tasks the last months. \r\n \r\nI wanted to share with you an example of what my code is able to generate by editing Yosys and OpenROAD: https://drive.google.com/drive/folders/1xTz4iTuGx0bDD-ZWAOV-MDQWKI0a8XA8?usp=sharing . \r\n\r\nThis pair of CSV files can be used as input for DGL Python library and create a GNN. \r\n\r\nThere is an issue though, I created a [Python script to check for collisions among the heatmaps and logic gate locations,](https://github.com/gudeh/OpenROAD-flow-scripts/blob/master/flow/myStuff/gateToHeat.py) and it is really slow. I made it by comparing the location of all the gates against each of the 4 heat types. I would like to ask any suggestions on how to improve this. Is this able to be solved on the OpenROAD db?"}, {"assistant": "The link to your script is broken. The heatmaps are a grid so it should be easy to compute the index into the map.\r\n\r\nMatt"}, {"user": "Hello again! I found a bug on my code to retrieve learning data using OpenROAD. The logic gate names don't match!\r\n\r\nMy machine learning model features come from the verilog generated during the flow. Optionally I can use the 1_1_yosys.v ( post tech map ) or the 6_final.v ( post route ). Afterwards I get the labels using some TCL commands discussed previously in this post. For example:\r\n\r\n\r\n> set dut gatesPosition_\r\n> set fileName ${designPath}/${dut}${::env(DESIGN_NAME)}.csv\r\n> set outFile [open $fileName w]\r\n> puts $outFile \"Name,xMin,yMin,xMax,yMax\"\r\n> set block [ord::get_db_block]\r\n> foreach inst [$block getInsts] { \r\n> set box [$inst getBBox] \r\n> puts $outFile \"[$inst getName], [ord::dbu_to_microns [$box xMin]], [ord::dbu_to_microns [$box yMin]], [ord::dbu_to_microns [$box xMax]], [ord::dbu_to_microns [$box yMax]]\" \r\n> }\r\n> close $outFile\r\n\r\nAt last, I have to build up my dataset by matching the logic gates names from the verilog, the logic gate names(from the TCL snippet pasted here and the heatmap dumps (positions). **But there is a problem:**\r\n\r\nI noticed that sometimes the flow changes the names of the gates between the verilog and the names retrieved from the TCL command ( `[$inst getName]`) causing unexpected behavior when I build the dataset. For example, the design bp_be_top with nangate45, there is a gate called `\\be_calculator/_09864_` in the 6_final.v, and the name I get with the TCL command is `be_calculator/_09864_` without the `\\`. \r\n\r\n**My question is:** Is there anyway to be sure that OR flow won't change the names of the gates? If not when and how does the tool changes the names of the gates, does it simply remove the starting `\\` or are there any other possible modifications?"}, {"user": "Hi guys, I have another doubt regarding the heatmaps provided by OR. I would like to make sure the behavior is as intended. This is the routing congestion heatmap when executing the Rocket Tile design with standard values (config.mk) given by the repository:\r\n![image](https://user-images.githubusercontent.com/37420320/230185344-17959d7b-05b3-4ee8-ab04-6865fb097f41.png)\r\n\r\nAfter executing the flow, OR inserts a lot of Filler Cells. It seems that the standard core size for Rocket Tile is extremely large, is there a reason for that?\r\n\r\nI ran the flow with the same design, although dividing the max X and max Y core area values in half and leaving the die area as is:\r\n\r\n> export DIE_AREA = 0 0 924.92 799.4\r\n> #export CORE_AREA = 10.07 9.8 914.85 789.6\r\n> export CORE_AREA = 10.07 9.8 457.425 394.8\r\n\r\nAnd this is the routing congestion heatmap after execution. There is still a considerably high congestion between core and die:\r\n![image](https://user-images.githubusercontent.com/37420320/230186482-44fd0f4f-85d4-4fcc-afa1-ed0b05a1635d.png)\r\n\r\nTo confirm, this is the placement density after the same run:\r\n![image](https://user-images.githubusercontent.com/37420320/230188189-c3be97c8-c7a9-4f42-b78d-03918a202baf.png)\r\n\r\n\r\nThis seems strange to me. I wouldn't expect so much routing congestion between die and core area. Furthermore, I couldn't even see metal wires on the green congested area. Is this as supposed to?"}, {"user": "Hello again. I wonder if there is a way to get the heatmaps considering only certain metal layers, is that possible?"}]} +{"messages": [{"user": "Is it possible to change the constrain on the maximum slew and skew for the CTS synthesis?"}, {"assistant": "@eder-matheus please comment."}]} +{"messages": [{"user": "I was trying to customize the CTS parameters using the command \"configure_cts_characterization\", but I don't see any changes is the maximum slew constrain reported in the .log file. Trying to understand if I was doing something wrong I noticed that there's a file called \"CtsOptions.h\" that should set the desired constrains with no \"CtsOptions.cpp\" file to describe the actual function. How can I manage to customize the maximum transition time? Thanks for your attention."}, {"assistant": "All the functions are inlined so there is no need for a cpp.\r\n\r\nWould you give the command you are using and the message you are getting in the log."}, {"user": "Sorry if I made a silly observation.\r\nI was trying to define the maximum limits of slew and maybe I misunderstood the command.\r\nIs it possible to change the values of maximum slew and maximum skew constrain for the CTS synthesis?"}]} +{"messages": [{"user": "Description\r\n\r\ni Have pull the latest Openroad Project, Here is Git log details\r\n\r\n
commit 92dd19146f4fb83f25387b05435a2ee770366afa (HEAD -> master, origin/master, origin/HEAD)\r\nMerge: f45cc928b 2754f4fb9\r\nAuthor: Matt Liberty <mliberty@eng.ucsd.edu>\r\nDate:   Fri Oct 8 22:41:13 2021 -0700\r\n\r\n    Merge pull request #1154 from The-OpenROAD-Project-staging/warnings\r\n    \r\n    fix more compiler warnings\r\n
\r\n\r\nCompile fails with below error:\r\n
cd /home/dinesha/workarea/tools/source/OpenROAD_10012020/build/src/dbSta/src && /usr/bin/c++  -DBOOST_ALL_NO_LIB -DSPDLOG_COMPILED_LIB -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/include -I/usr/include/tcl -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/dbSta/src/../include -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/sta/include/sta -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/sta -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/sta/include -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/include -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/utl/include -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/include/odb -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/src/def/def -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/src/def/defzlib -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/src/lef/lef -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/odb/src/lef/lefzlib -I/home/dinesha/workarea/tools/source/OpenROAD_10012020/src/gui/include  -O3 -DNDEBUG   -pthread -std=c++17 -Wno-cast-qual -o CMakeFiles/dbSta.dir/CMakeFiles/dbSta.dir/dbStaTCL_wrap.cxx.o -c /home/dinesha/workarea/tools/source/OpenROAD_10012020/build/src/dbSta/src/CMakeFiles/dbSta.dir/dbStaTCL_wrap.cxx\r\n/home/dinesha/workarea/tools/source/OpenROAD_10012020/build/src/dbSta/src/CMakeFiles/dbSta.dir/dbStaTCL_wrap.cxx: In function \u2018void find_logic_constants()\u2019:\r\n/home/dinesha/workarea/tools/source/OpenROAD_10012020/build/src/dbSta/src/CMakeFiles/dbSta.dir/dbStaTCL_wrap.cxx:7102:8: error: \u2018class sta::dbSta\u2019 has no member named \u2018findLogicConstants\u2019\r\n 7102 |   sta->findLogicConstants();\r\n      |        ^~~~~~~~~~~~~~~~~~\r\nmake[2]: *** [src/dbSta/src/CMakeFiles/dbSta.dir/build.make:85: src/dbSta/src/CMakeFiles/dbSta.dir/CMakeFiles/dbSta.dir/dbStaTCL_wrap.cxx.o] Error 1\r\nmake[2]: Leaving directory '/home/dinesha/workarea/tools/source/OpenROAD_10012020/build'\r\nmake[1]: *** [CMakeFiles/Makefile2:2637: src/dbSta/src/CMakeFiles/dbSta.dir/all] Error 2\r\nmake[1]: Leaving directory '/home/dinesha/workarea/tools/source/OpenROAD_10012020/build'\r\nmake: *** [Makefile:133: all] Error 2\r\n
\r\nMy System is : Ubuntu 20.04.3 LTS\r\n\r\nI don't see findLogicConstants inside the sta class ?\r\n"}, {"user": "Look like this needed sta submodule git repo update .. After updating the sta folder this issue resolved"}]} +{"messages": [{"user": "Hi,\r\n\r\nI am trying to run OpenROAD/src/ICeWall/test examples. Used below command inside openroad and stopped with error\r\n\r\nopenroad 1> source soc_bsg_black_parrot_nangate45.tcl \r\n[WARNING ODB-0229] Error: library (NangateOpenCellLibrary.mod) already exists\r\n[WARNING ODB-0229] Error: library (dummy_pads) already exists\r\n[WARNING STA-0053] dummy_pads.lib line 7, library dummy_pads_worst_case already exists.\r\nSegmentation fault (core dumped)\r\n\r\nAnyone can explain how to run this flow and to view DEF file klayout to view my chip level io connection created by ICeWall\r\n\r\nThanks in advance\r\n"}, {"assistant": "@Colin-Holehouse @ibrahimkhairy can you help?"}, {"assistant": "@jjcherry56 the crash is in \r\n\r\nsta::ConcreteInstance::deletePin \r\nsta::ConcreteNetwork::deletePin \r\nsta::ConcreteNetwork::deleteInstance \r\nsta::ConcreteNetwork::deleteTopInstance \r\nsta::ConcreteNetwork::linkNetwork \r\nord::dbLinkDesign \r\n\r\nreproduce by going to src/ICeWall/test and running\r\n% openroad soc_bsg_black_parrot_nangate45.tcl\r\n[at OR prompt] source soc_bsg_black_parrot_nangate45.tcl"}, {"user": "[vijayan@ctpl-hp11 test]$ ../../../build/src/openroad \r\nOpenROAD 1 3a8b060d9026de9b35e4f35ee59157ce9416c3ff\r\nThis program is licensed under the BSD-3 license. See the LICENSE file for details.\r\nComponents of this program may be licensed under more restrictive licenses which must be honored.\r\nopenroad 1> source soc_bsg_black_parrot_nangate45.tcl \r\n[INFO ODB-0222] Reading LEF file: NangateOpenCellLibrary.mod.lef\r\n[INFO ODB-0223] Created 22 technology layers\r\n[INFO ODB-0224] Created 27 technology vias\r\n[INFO ODB-0225] Created 134 library cells\r\n[INFO ODB-0226] Finished LEF file: NangateOpenCellLibrary.mod.lef\r\n[INFO ODB-0222] Reading LEF file: dummy_pads.lef\r\n[INFO ODB-0225] Created 24 library cells\r\n[INFO ODB-0226] Finished LEF file: dummy_pads.lef\r\n[INFO IFP-0001] Added 1885 rows of 13893 sites.\r\n[INFO PAD-0053] Creating padring nets: RETN_10, RETN_11, RETN_12, RETN_13, RETN_14, RETN_15, RETN_16, RETN_17, RETN_18, RETN_19, RETN_20, RETN_0, RETN_1, RETN_2, RETN_3, RETN_4, RETN_5, RETN_6, RETN_7, RETN_8, RETN_9, SNS_10, SNS_11, SNS_12, SNS_13, SNS_14, SNS_15, SNS_16, SNS_0, SNS_17, SNS_1, SNS_18, SNS_2, SNS_19, SNS_20, SNS_3, SNS_4, SNS_5, SNS_6, SNS_7, SNS_8, SNS_9, DVSS_0, DVSS_1, DVDD_0, DVDD_1.\r\n[INFO PAD-0051] Creating padring net: VSS.\r\n[INFO PAD-0051] Creating padring net: VDD.\r\nNo differences found.\r\n\r\nIs the above log right?"}, {"assistant": "\"No differences found. \" tells you it is right."}]} +{"messages": [{"user": "Can any one give more details on the these WARNING & also how to solve these issue.\r\n\r\n[WARNING DPL-0004] Placed in rows check failed (4).\r\n[WARNING DPL-0005] Overlap check failed (1).\r\n[WARNING DPL-0006] Site check failed (4).\r\n\r\nI am trying to do detailed placement using openlane flow and 99% of block are hard core, only 32 cells are there at top-level\r\nThere is good amount of free space available. still tool fails with these error.\r\n\r\n"}, {"assistant": "It is a check at the end of placement to make sure the result is non-overlapping. It suggests a placement failure but its hard to say anything more without a test case. Can you provide one?"}, {"user": "The project had 99% hard macro with less than 32 other cells and there was\nmore than 30% free space. Still openroad detailed route was placing\noverlapping cells with hard macros & giving DPL-4/5/6 warning.\n\nFinally I noticed the issue was resolved after changing\ndiamond_search_hight more than *250*.\n\nCan give more details on how increased diamond_search_hight value helped\nhere ?\n\n\n\nOn Thu, Jun 17, 2021 at 7:17 PM Matt Liberty ***@***.***>\nwrote:\n\n> It is a check at the end of placement to make sure the result is\n> non-overlapping. It suggests a placement failure but its hard to say\n> anything more without a test case. Can you provide one?\n>\n> \u2014\n> You are receiving this because you authored the thread.\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n>\n"}, {"assistant": "I would guess that global placement left cells very far from any legal location. You might look at a post global-placement def to see."}]} +{"messages": [{"user": "I git clone --recursive the parent repo \"openroad-flow-scripts\" so I get all the code including submodules in the local. \r\nAnd then I use \"git remote rename origin upstream\" and \"git remote add origin to let it point to my repo. (I only create one repo for the openroad-flow-script. I didn't create repo for submodules.)\r\nAfter I made changes in submodule /tools/openroad/src, I do git `add` and `commit` in the directory of submodule tools/openroad, and then in the parent directory /openroad-flow-scripts, I do `git add tools/openroad`, `commit`, `push`. I can see it does push something to somewhere[![push result](https://i.postimg.cc/jSrTz9Ry/We-Chat-Image-20210526015324.png)](https://postimg.cc/kBwLCT65), but I cannot find it on github.com, on which the directory url points to 404 [![404page](https://i.postimg.cc/FF3DfsHF/404.png)](https://postimg.cc/fkWxpsd1)page. I am wondering where the submodules go when I do the `git remote add origin `. Is there a way to create the submodule repo automatically in my repo?"}, {"assistant": "It isn't clear in which repo you are runing which steps. Please give a specific set of steps to replay to see your problem.\r\n\r\nI think the simplest is to fork ORFS & OR."}, {"assistant": "When the submodule is checked out it will be a specific commit that is checked out not the HEAD. You can just 'it checkout master' and commit your change. Then in ORFS you can update the submodule to point to your new commit."}, {"assistant": "In ORFS you should see that the submodule is modified and you git add/commit it as usual."}, {"assistant": "yes"}, {"user": "When I want to get the update of submodules, I do `git pull --recurse-submodule`, [![gitpullsubmodulecheckout.png](https://i.postimg.cc/hPpJ5z1G/gitpullsubmodulecheckout.png)](https://postimg.cc/svGDB28F),\r\nbut it checkouts the commit id it originally points to. [![submodulepointtocommit.png](https://i.postimg.cc/5tF6yPdH/submodulepointtocommit.png)](https://postimg.cc/Y4MpyzSk).\r\nHow to let it point to my OR git master branch? Otherwise, I need to go into that submodule directory to do the `git checkout master` every time."}]} +{"messages": [{"user": "Does OpenROAD project support any forms of power analysis? Thanks!"}, {"assistant": "There is report_power (power based on liberty) and analyze_power_grid (static IR drop)."}]} +{"messages": [{"user": "Hi, I want to find the step of \"pin access pattern generation\" in the TritonRoute/src/pa code and dump out the pattern information after pin access analysis. I don't see pin access pattern generation function in FlexPA::main(). Could anyone tell me where is this step? \r\nIs there template or sample of extracting pin access points information for TA? Thanks."}, {"assistant": "The calls to init() and prep() do the work of computing the access points. If you just want to dump the result you would do so after those steps finish. You can just look at frInstTerm::getAccessPoints() for the result."}, {"assistant": "Btw, what is your high level goal?"}, {"assistant": "Anything on stdout will be copied to the log file in 5_2_TritonRoute.log.\n\nMatt\n\nOn Tue, May 18, 2021 at 2:02 PM Raynchowkw ***@***.***> wrote:\n\n> Hi, I have built the flow locally and made modification to the\n> FlexPA_prep.cpp to add the \"cout\" code provided by @Stephanommg\n> in previous reply\n> \n> and rebuilt only the openroad tool.\n> I run 'make' for a sample design, and from the output scripts in terminal,\n> I cannot find any information which is assumed to be produced by 'cout'. I\n> look through the part from '[INFO DRT-0194] start detail routing ...' to\n> '[INFO DRT-0198] complete detail routing', also use \"Ctrl+Shift+F\" to find\n> \"layerNum \", but fail to find any aps information.\n> Am I supposed to run TritonRoute individually to output the message?\n>\n> \u2014\n> You are receiving this because you commented.\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n>\n"}, {"user": "How to interpret the aps info printed by 'cout << bp << \"layerNum \" << ap->getLayerNum() << \"\\n\";'?\r\nIt looks like: ( the first paragraph)\r\n```\r\n( ( ( ( ( 84550 23940 )layerNum 2\r\n( 84550 9025072770 23940 )75810layerNum ( ( ( 86450883502 68590 70490 23940\r\n )239402394023800 )( 23940 )layerNum 23940 )layerNum 272770 )layerNum \r\n( 86450238002layerNum )23940layerNum 23800 )2layerNum \r\n )2\r\n( )\r\n( layerNum 70490 23800layerNum 222\r\n( 90250\r\n )2\r\n( 86450 24080 )68590\r\nlayerNum layerNum ( layerNum ( ( 238002275810 23800\r\n```\r\nIt's not something like (X,Y,Z).\r\nWhich part of code should I read to understand this data structure?\r\nHow can I know the net_id, pin_id, pin_x, pin_y, pin_layer according to this?\r\nThanks.\r\n\r\n"}, {"user": "Thanks.\n\nOn Fri, May 28, 2021 at 5:36 PM Stephanommg ***@***.***>\nwrote:\n\n> By container I meant something that contains things. For instance: a\n> vector.\n>\n> Yes this operator.\n>\n> Learning C++ will surely help you. After that you will be better able to\n> understand the code.\n>\n> I really cant code for you right now, and I think my previous comment\n> already answered you last question (at least in part). You will have to use\n> the first code to iterate the access points in combination with the last\n> code to iterate over the nets.\n>\n> for each net\n> for each instTerm\n> get access points like the 1st code\n> for each term\n> get access points like the 1st code (with differences that it is up to up\n> to check)\n>\n> \u2014\n> You are receiving this because you authored the thread.\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n>\n\n\n-- \nBest,\nRaynchow\n"}, {"assistant": "@Raynchowkw the project has limited resources and I think you need to put in more effort to solve your issues before requesting help. Many of the requests don't require in depth knowledge of OpenRoad and are basic software development skills you need to develop."}, {"assistant": "You can think of a term as a port of a verilog module; an instance as an instance of a verilog module; and an instTerm as the connection point on the instance reflecting the port of the module instantiated."}, {"user": "Hi, After working hard on learning C++, I still have some questions. \r\nOne that blocks my understanding is `pin.get()` etc.\r\nWhat's the `.get()` here and where's its definition? I cannot find one in their class def."}, {"assistant": "No problem\n\nOn Thu, Jun 10, 2021 at 11:48 AM Raynchowkw ***@***.***>\nwrote:\n\n> You need to iterate over the frNets and then iterate over their\n> frInstTerms and frTerms (similar to the for I placed here before). Do this\n> after pin access and before DR. You can do this inf FlexDR::main() before\n> the searchRepair functions. To get all nets, use\n> design_->getTopBlock()->getNets().\n>\n> Hi, I want to dump out aps before TA. I check TritonRoute::main. dr is\n> later than ta. So I want to dump out at the end of FlexPA::main. Would that\n> incur unexpected problems?\n>\n> \u2014\n> You are receiving this because you commented.\n> Reply to this email directly, view it on GitHub\n> ,\n> or unsubscribe\n> \n> .\n>\n"}, {"user": "After one week of understanding code, I find the logic of assigning one ap to one pin by this [line](https://github.com/The-OpenROAD-Project/OpenROAD/blob/c27d7cea8981bc917deaaa4d8cc83a6f9285c0e7/src/TritonRoute/src/pa/FlexPA_prep.cpp#L1579) in genInstPattern_commit. \r\nThe code @Stephanommg wrote to get aps is `for (auto& ap : pin->getPinAccess(inst->getPinAccessIdx())->getAccessPoints())`. I had a hard time understanding what frPinAccess is doing. I just find its uses in the [FlexPA::initPinAccess](https://github.com/The-OpenROAD-Project/OpenROAD/blob/c27d7cea8981bc917deaaa4d8cc83a6f9285c0e7/src/TritonRoute/src/pa/FlexPA_init.cpp#L232) in and [FlexPA::prepPoint](https://github.com/The-OpenROAD-Project/OpenROAD/blob/c27d7cea8981bc917deaaa4d8cc83a6f9285c0e7/src/TritonRoute/src/pa/FlexPA_prep.cpp#L1248) in FlexPA::prepPattern and [revertAccessPoints](https://github.com/The-OpenROAD-Project/OpenROAD/blob/c27d7cea8981bc917deaaa4d8cc83a6f9285c0e7/src/TritonRoute/src/pa/FlexPA_prep.cpp#L1455) and [prepPattern_inst](https://github.com/The-OpenROAD-Project/OpenROAD/blob/c27d7cea8981bc917deaaa4d8cc83a6f9285c0e7/src/TritonRoute/src/pa/FlexPA_prep.cpp#L1816). \r\nIt looks like these are before genInstPattern_commit and just for coord manipulation purpose. So I think frPinAccess doesn't filter ap selected for each pin.\r\nSo in order to get ap for each pin in each net, can I do loop through net -> instTerms ->getAccessPoints() ?\r\nI am not sure the meaning of \"net\" and what's relationship between pin and net. Can I understand as this: a net connects some instTerms, each instTerm has some pins, so instTerms' pins are linked to that one net exclusively? Or pins in one instTerm can be linked to \r\ndifferent nets?\r\nThanks."}]}