ChiPFormer: Transferable Chip Placement via Offline Decision Transformer

Yao Lai, Jinxin Liu, Zhentao Tang, Bin Wang, Jianye Hao, Ping Luo
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18346-18364, 2023.

Abstract

Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time and low transfer ability in unseen chip circuits. To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data. ChiPFormer has several advantages that prior arts do not have. First, ChiPFormer can exploit offline placement designs to learn transferable policies more efficiently in a multi-task setting. Second, ChiPFormer can promote effective finetuning for unseen chip circuits, reducing the placement runtime from hours to minutes. Third, extensive experiments on 32 chip circuits demonstrate that ChiPFormer achieves significantly better placement quality while reducing the runtime by 10x compared to recent state-of-the-art approaches in both public benchmarks and realistic industrial tasks. The deliverables are released at https://sites.google.com/view/chipformer/home.

Cite this Paper


BibTeX
@InProceedings{pmlr-v202-lai23c, title = {{C}hi{PF}ormer: Transferable Chip Placement via Offline Decision Transformer}, author = {Lai, Yao and Liu, Jinxin and Tang, Zhentao and Wang, Bin and Hao, Jianye and Luo, Ping}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {18346--18364}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/lai23c/lai23c.pdf}, url = {https://proceedings.mlr.press/v202/lai23c.html}, abstract = {Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time and low transfer ability in unseen chip circuits. To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data. ChiPFormer has several advantages that prior arts do not have. First, ChiPFormer can exploit offline placement designs to learn transferable policies more efficiently in a multi-task setting. Second, ChiPFormer can promote effective finetuning for unseen chip circuits, reducing the placement runtime from hours to minutes. Third, extensive experiments on 32 chip circuits demonstrate that ChiPFormer achieves significantly better placement quality while reducing the runtime by 10x compared to recent state-of-the-art approaches in both public benchmarks and realistic industrial tasks. The deliverables are released at https://sites.google.com/view/chipformer/home.} }
Endnote
%0 Conference Paper %T ChiPFormer: Transferable Chip Placement via Offline Decision Transformer %A Yao Lai %A Jinxin Liu %A Zhentao Tang %A Bin Wang %A Jianye Hao %A Ping Luo %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-lai23c %I PMLR %P 18346--18364 %U https://proceedings.mlr.press/v202/lai23c.html %V 202 %X Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time and low transfer ability in unseen chip circuits. To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data. ChiPFormer has several advantages that prior arts do not have. First, ChiPFormer can exploit offline placement designs to learn transferable policies more efficiently in a multi-task setting. Second, ChiPFormer can promote effective finetuning for unseen chip circuits, reducing the placement runtime from hours to minutes. Third, extensive experiments on 32 chip circuits demonstrate that ChiPFormer achieves significantly better placement quality while reducing the runtime by 10x compared to recent state-of-the-art approaches in both public benchmarks and realistic industrial tasks. The deliverables are released at https://sites.google.com/view/chipformer/home.
APA
Lai, Y., Liu, J., Tang, Z., Wang, B., Hao, J. & Luo, P.. (2023). ChiPFormer: Transferable Chip Placement via Offline Decision Transformer. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:18346-18364 Available from https://proceedings.mlr.press/v202/lai23c.html.

Related Material