面向芯片布局的灵活多目标强化学习
机器学习
2022-04-14 v1 人工智能
摘要
近来，强化学习在芯片布局上的成功应用不断涌现。预训练模型对于提升效率与效果是必要的。当前，目标度量（如线长、拥塞和时序）的权重在预训练期间是固定的。然而，固定权重模型无法生成工程师为满足随时出现的变化需求所需的布局多样性。本文提出灵活多目标强化学习（MORL），仅使用单个预训练模型即可支持具有推理时可变权重的目标函数。我们的宏布局结果表明，MORL 能有效生成多目标的帕累托前沿。
引用
@article{arxiv.2204.06407,
title = {Flexible Multiple-Objective Reinforcement Learning for Chip Placement},
author = {Fu-Chieh Chang and Yu-Wei Tseng and Ya-Wen Yu and Ssu-Rui Lee and Alexandru Cioba and I-Lun Tseng and Da-shan Shiu and Jhih-Wei Hsu and Cheng-Yuan Wang and Chien-Yi Yang and Ren-Chu Wang and Yao-Wen Chang and Tai-Chen Chen and Tung-Chieh Chen},
journal= {arXiv preprint arXiv:2204.06407},
year = {2022}
}
备注
A short version of this article is published in DAC'22:LBR (see ACM DOI 10.1145/3489517.3530617)