Timing-Driven Global Placement by Efficient Critical Path Extraction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shi, Yunqi, Xu, Siyuan, Kai, Shixiong, Lin, Xi, Xue, Ke, Yuan, Mingxuan, Qian, Chao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917958023905280
author Shi, Yunqi
Xu, Siyuan
Kai, Shixiong
Lin, Xi
Xue, Ke
Yuan, Mingxuan
Qian, Chao
author_facet Shi, Yunqi
Xu, Siyuan
Kai, Shixiong
Lin, Xi
Xue, Ke
Yuan, Mingxuan
Qian, Chao
contents Timing optimization during the global placement of integrated circuits has been a significant focus for decades, yet it remains a complex, unresolved issue. Recent analytical methods typically use pin-level timing information to adjust net weights, which is fast and simple but neglects the path-based nature of the timing graph. The existing path-based methods, however, cannot balance the accuracy and efficiency due to the exponential growth of number of critical paths. In this work, we propose a GPU-accelerated timing-driven global placement framework, integrating accurate path-level information into the efficient DREAMPlace infrastructure. It optimizes the fine-grained pin-to-pin attraction objective and is facilitated by efficient critical path extraction. We also design a quadratic distance loss function specifically to align with the RC timing model. Experimental results demonstrate that our method significantly outperforms the current leading timing-driven placers, achieving an average improvement of 40.5% in total negative slack (TNS) and 8.3% in worst negative slack (WNS), as well as an improvement in half-perimeter wirelength (HPWL).
format Preprint
id arxiv_https___arxiv_org_abs_2503_11674
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Timing-Driven Global Placement by Efficient Critical Path Extraction
Shi, Yunqi
Xu, Siyuan
Kai, Shixiong
Lin, Xi
Xue, Ke
Yuan, Mingxuan
Qian, Chao
Hardware Architecture
Artificial Intelligence
Timing optimization during the global placement of integrated circuits has been a significant focus for decades, yet it remains a complex, unresolved issue. Recent analytical methods typically use pin-level timing information to adjust net weights, which is fast and simple but neglects the path-based nature of the timing graph. The existing path-based methods, however, cannot balance the accuracy and efficiency due to the exponential growth of number of critical paths. In this work, we propose a GPU-accelerated timing-driven global placement framework, integrating accurate path-level information into the efficient DREAMPlace infrastructure. It optimizes the fine-grained pin-to-pin attraction objective and is facilitated by efficient critical path extraction. We also design a quadratic distance loss function specifically to align with the RC timing model. Experimental results demonstrate that our method significantly outperforms the current leading timing-driven placers, achieving an average improvement of 40.5% in total negative slack (TNS) and 8.3% in worst negative slack (WNS), as well as an improvement in half-perimeter wirelength (HPWL).
title Timing-Driven Global Placement by Efficient Critical Path Extraction
topic Hardware Architecture
Artificial Intelligence
url https://arxiv.org/abs/2503.11674