@@ -339,6 +339,10 @@ We did not use pre-trained models in our study. Note that it is impossible to re
- We replicated RePlAce results and believe our SA obtains similar results. However, there is no code or data available to reproduce S.B.’s reported CT results, or proxy costs of SA results.
**11. Did it matter that Circuit Training used an initial placement from a physical synthesis tool?**
Yes. Circuit Training benefits **substantially** from its use of the placement locations that it obtains from physical synthesis. An ablation study is reported in Section 5.2.1 of our [ISPD-2023 paper](https://vlsicad.ucsd.edu/Publications/Conferences/396/c396.pdf). To test the effect of initial placement on CT outcomes, we generated three “vacuous” input placements for the Ariane-NG45 design. These three cases (1), (2) and (3) respectively have all standard cells and macros located at (600, 600), at the lower-left corner (0, 0), and at the upper-right corner (1347.1, 1346.8) of the layout canvas. For each case, we generate the clustered netlist, run CT and collect Nature Table 1 metrics ([Link](https://github.com/TILOS-AI-Institute/MacroPlacement/tree/main/Docs/OurProgress#Question1) to all three Nature Table 1 metrics). **We find that placement information in the input provides significant benefit to CT**. When given locations from (Cadence CMP + Genus iSpatial) physical synthesis, CT’s routed wirelength decreases by 10.32%, 7.24% and 8.17% compared to Cases (1), (2) and (3), respectively. See the [Link](https://github.com/TILOS-AI-Institute/MacroPlacement/tree/main/Docs/OurProgress#circuit-training-baseline-result-on-our-ariane133-nangate45_68) to Nature Table 1 metrics.
## **Related Links**
- C.-K. Cheng, A. B. Kahng, S. Kundu, Y. Wang and Z. Wang, "Assessment of Reinforcement Learning for Macro Placement", ([.pdf](https://vlsicad.ucsd.edu/Publications/Conferences/396/c396.pdf)), *Proc. ACM/IEEE Intl. Symp. on Physical Design*, 2023, to appear.
