Merge branch 'main' of github.com:TILOS-AI-Institute/MacroPlacement into flow_scripts

.gitignore

@@ -3,3 +3,9 @@ Flows/*/*/run-*
 Flows/job
 Flows/util/__pycache__
 CodeElements/*/*/__pycache__
+CodeElements/Plc_client/test/
+CodeElements/Plc_client/test/*/*
+CodeElements/Plc_client/plc_client_os.py
+CodeElements/Plc_client/__pycache__/*
+CodeElements/Plc_client/proto_reader.py
+CodeElements/Plc_client/plc_client.py

CodeElements/Plc_client/README.md

@@ -9,7 +9,20 @@ curl 'https://raw.githubusercontent.com/google-research/circuit_training/main/ci
 sudo curl https://storage.googleapis.com/rl-infra-public/circuit-training/placement_cost/plc_wrapper_main \
   -o  /usr/local/bin/plc_wrapper_main
 # Run plc testbench
-python -m Plc_client.plc_client_os_test
+# python -m Plc_client.plc_client_os_test [-h] [--helpfull] --netlist NETLIST [--plc PLC] --width WIDTH --height HEIGHT --col COL --row ROW [--rpmh RPMH] [--rpmv RPMV] [--marh MARH] [--marv MARV] [--smooth SMOOTH]
+
+# Example
+python -m Plc_client.plc_client_os_test --netlist ./Plc_client/test/ariane/netlist.pb.txt\
+          --plc ./Plc_client/test/ariane/initial.plc\
+          --width 356.592\
+          --height 356.640\
+          --col 35\
+          --row 33\
+          --rpmh 10\
+          --rpmv 10\
+          --marh 5\
+          --marv 5\
+          --smooth 2
 ```
 
 ## HPWL Computation
@@ -27,15 +40,15 @@ $$
 HPWL(netlist) = \sum_{i}^{N_{netlist}} W_{i\_{source}} \cdot [max_{b\in i}(x_b) - min_{b\in i}(x_b) + max_{b\in i}(y_b) - min_{b\in i}(y_b)]
 $$
 
-## Density  Cost Computation
+## Density Cost Computation
 Density cost is computed from grid cells density.
 
 By default, any given input will have grid col/row set to 10/10 until user later defines in the .plc file.
 
-Grid cell density is represented as an 1D array where the length is set to be 
+Grid cell density is represented as an 1D array where the length is set to be the following:
 
 $$
-grid_\{col} \cdot grid_\{row}
+grid_{col} \cdot grid_{row}
 $$
 
 Each entry of this array represents the current occupied precentage within this cell.

README.md

@@ -201,7 +201,8 @@ while allowing soft macros (standard-cell clusters) to also find good locations.
 - [Hypergraph clustering](./CodeElements/Clustering/) clusters millions of standard cells into a few thousand clusters.  In Circuit Training, the purpose of clustering is to enable an approximate but fast standard cell placement that facilitates policy network optimization.
 - [Force-directed placement](./CodeElements/FDPlacement/) places the center of each standard cell cluster onto  centers of gridcells generated by [Gridding](./CodeElements/Gridding/).
 - [Simulated annealing](./CodeElements/SimulatedAnnealing/) places the center of each macro onto centers of gridcells generated by [Gridding](./CodeElements/Gridding/).  In Circuit Training,  simulated annealing is used as a baseline to show the relative sample efficiency of RL.
-- [LEF/DEF and Bookshelf (OpenDB, RosettaStone) translators](./CodeElements/FormatTranslators/) ease the translation between different representations of the same netlist. 
+- [LEF/DEF and Bookshelf (OpenDB, RosettaStone) translators](./CodeElements/FormatTranslators/) ease the translation between different representations of the same netlist.
+- [Plc client](./CodeElements/Plc_client/) implements all three components of the proxy cost function: wirelength cost, density cost and congestion cost.
 
 
 <!--## **Reproducible Example Solutions** -->
@@ -218,18 +219,16 @@ We provide a competitive baseline for [Google Brain's Circuit Training](https://
 - We do understand that Google has been working hard to complete the open-sourcing of Morpheus, and that this effort continues today. However, as pointed out in [this Doc](https://docs.google.com/document/d/1vkPRgJEiLIyT22AkQNAxO8JtIKiL95diVdJ_O4AFtJ8/edit?usp=sharing), it has been more than a year since "Data and Code Availability" was committed with publication of the [Nature paper](https://www.nature.com/articles/s41586-021-03544-w). We consider our work a "backstop" or "safety net" for Google's internal efforts, and a platform for researchers to build on. 
 
 **What can others contribute?**
-- Our shopping list includes the following. Please join in! 
-  - force-directed placement (and API): documentation and implementation
-  - adjacency matrix generation: documentation and implementation
+- Our shopping list (updated August 2022) includes the following. Please join in!  
   - simulated annealing on the gridded canvas: documentation and implementation
+  - force-directed placement: documentation and implementation
   - donated cloud resources (credits) for experimental studies
   - relevant testcases with reference implementations and implementation flows (Cadence, OpenROAD preferred since scripts can be shared)
-  - protobuf, lef/def, Bookshelf: detailed and confirmed documentation, plus tests and other help to improve our initial versions of translators
-  - "fakeram" generator for the ASAP7 research PDK
-  - qrctechfile for NanGate45
+  - improved "fakeram" generator for the ASAP7 research PDK
 
 **What is your timeline?**
-- We hope to show significant progress at the [DAC-2022 Birds-of-a-Feather](https://59dac.conference-program.com/session/?sess=sess294) meeting (Open-Source EDA and Benchmarking Summit) on July 12, 2022, 7-10pm in Room 3000 of Moscone West in San Francisco.
+- We showed our [progress](https://open-source-eda-birds-of-a-feather.github.io/doc/slides/MacroPlacement-SpecPart-DAC-BOF-v5.pdf) at the Open-Source EDA and Benchmarking Summit birds-of-a-feather [meeting](https://open-source-eda-birds-of-a-feather.github.io/) on July 12 at DAC-2022.
+- We are now (late August 2022) studying benefits and limitations of the CT methodology itself, as noted in [this Doc](https://docs.google.com/document/d/1c-uweo3DHiCWZyBzAdNCqqcOrAbKq1sVIfY0_4bFCYE/edit).
 
 
 ## **Related Links**