Abstract:Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability. However, identifying optimal topologies remains a persistent bottleneck, as conventional exhaustive search methods become computationally intractable with increasing circuit complexity in advanced nodes. This paper introduces TOPCELL, a novel and scalable framework that reformulates high-dimensional topology exploration as a generative task using Large Language Models (LLMs). We employ Group Relative Policy Optimization (GRPO) to fine-tune the model, aligning its topology optimization strategy with logical (circuit) and spatial (layout) constraints. Experimental results within an industrial flow targeting an advanced 2nm technology node demonstrate that TOPCELL significantly outperforms foundation models in discovering routable, physically-aware topologies. When integrated into a state-of-the-art (SOTA) automation flow for a 7nm library generation task, TOPCELL exhibits robust zero-shot generalization and matches the layout quality of exhaustive solvers while achieving an 85.91x speedup.
| Comments: | Accepted to the 63rd ACM/IEEE Design Automation Conference (DAC 2026). 7 pages, 4 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.14237 [cs.LG] |
| (or arXiv:2604.14237v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.14237 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1145/3770743.3804365
DOI(s) linking to related resources |
From: Zhan Song [view email]
[v1]
Wed, 15 Apr 2026 00:19:07 UTC (401 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。