arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07781cs.ARcs.LG
收藏

使用强化学习的IR感知ECO时序优化

IR-Aware ECO Timing Optimization Using Reinforcement Learning

University of Minnesota(明尼苏达大学);Arizona State University(亚利桑那州立大学)

Wenjing Jiang, Vidya A. Chhabria, Sachin S. Sapatnekar

AI总结:

针对后期IR压降导致的时序偏移问题,提出将拉格朗日松弛融入RL框架、用R-GCN智能体调整门尺寸的IR感知ECO时序优化方法,在45nm工艺下实现更优的延迟-功耗权衡、更快速度和更少布局扰动,且模型可迁移。

摘要:

后期阶段的工程变更指令(ECO)会进行最小限度的设计修复,以从由过大IR压降导致的时序偏移中恢复。本文将IR压降感知时序分析与使用强化学习(RL)的ECO时序优化相结合。该方法在物理设计和电网综合之后运行,通过门尺寸调整来修正由IR压降引起的时序退化。它将拉格朗日松弛(LR)技术融入一种新型RL框架中,该框架训练一个关系图卷积网络(R-GCN)智能体来按顺序调整门的尺寸以修复时序违规。该R-GCN智能体优于经典的纯LR算法:在一种开源45nm工艺中,它(a)将延迟-功耗权衡曲线的帕累托前沿向左移动;(b)通过使用训练好的模型运行快速推理,比现有方法节省了运行时间;(c)通过调整更少单元的尺寸,减少了对布局的扰动。该RL模型可跨不同时序规范迁移,也可经微调后迁移到未见过的设计中。

英文摘要:

Engineering change orders (ECOs) in late stages make minimal design fixes to recover from timing shifts due to excessive IR drops. This paper integrates IR-drop-aware timing analysis and ECO timing optimization using reinforcement learning (RL). The method operates after physical design and power grid synthesis, and rectifies IR-drop-induced timing degradation through gate sizing. It incorporates the Lagrangian relaxation (LR) technique into a novel RL framework, which trains a relational graph convolutional network (R-GCN) agent to sequentially size gates to fix timing violations. The R-GCN agent outperforms a classical LR-only algorithm: in an open 45nm technology, it (a) moves the Pareto front of the delay-power tradeoff curve to the left (b) saves runtime over the prior approaches by running fast inference using trained models, and (c) reduces the perturbation to placement by sizing fewer cells. The RL model is transferable across timing specifications and to unseen designs with fine tuning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑