English

Warp-STAR: High-performance, Differentiable GPU-Accelerated Static Timing Analysis through Warp-oriented Parallel Orchestration

Distributed, Parallel, and Cluster Computing 2026-03-31 v1

Abstract

Static timing analysis (STA) is crucial for Electronic Design Automation (EDA) flows but remains a computational bottleneck. While existing GPU-based STA engines are faster than CPU, they suffer from inefficiencies, particularly intra-warp load imbalance caused by irregular circuit graphs. This paper introduces Warp-STAR, a novel GPU-accelerated STA engine that eliminates this imbalance by orchestrating parallel computations at the warp level. This approach achieves a 2.4X speedup over previous state-of-the-art (SoTA) GPU-based STA. When integrated into a timing-driven global placement framework, Warp-STAR delivers a 1.7X speedup over SoTA frameworks. The method also proves effective for differentiable gradient analysis with minimal overhead.

Keywords

Cite

@article{arxiv.2603.28381,
  title  = {Warp-STAR: High-performance, Differentiable GPU-Accelerated Static Timing Analysis through Warp-oriented Parallel Orchestration},
  author = {En-Ming Huang and Shih-Hao Hung},
  journal= {arXiv preprint arXiv:2603.28381},
  year   = {2026}
}

Comments

7 pages, 6 figures, The Chips to System Conference (DAC'26) 2026

R2 v1 2026-07-01T11:44:03.052Z