GAP-LA: GPU-Accelerated Performance-Driven Layer Assignment

TL;DR

GAP-LA is a GPU-accelerated framework that optimizes layer assignment in VLSI routing, improving timing metrics while balancing power and congestion for large-scale circuits.

Contribution

It introduces a holistic, GPU-based layer assignment method that simultaneously optimizes timing, power, and congestion, outperforming existing approaches on large designs.

Findings

Achieves up to 9.9% improvement in worst negative slack

Improves total negative slack by up to 5.4%

Maintains competitive runtime on large-scale circuits

Abstract

Layer assignment is critical for global routing of VLSI circuits. It converts 2D routing paths into 3D routing solutions by determining the proper metal layer for each routing segments to minimize congestion and via count. As different layers have different unit resistance and capacitance, layer assignment also has significant impacts to timing and power. With growing design complexity, it becomes increasingly challenging to simultaneously optimize timing, power, and congestion efficiently. Existing studies are mostly limited to a subset of objectives. In this paper, we propose a GPU-accelerated performance-driven layer assignment framework, GAP-LA, for holistic optimization the aforementioned objectives. Experimental results demonstrate that we can achieve 0.3%-9.9% better worst negative slack (WNS) and 2.0%-5.4% better total negative slack (TNS) while maintaining power and congestion with competitive runtime compared with ISPD 2025 contest winners, especially on designs with up to 12 millions of nets.