GPU-Accelerated Gate-Level Time-Based Power Analysis via Event-Density-Aware Partitioning and Kernel Fusion
TL;DR
This paper presents the first GPU-accelerated gate-level time-based power analysis framework, and proposes a novel data structure to enable efficient state-dependent power retrieval to enable efficient state-dependent power retrieval.
Abstract
Power analysis is crucial in modern chip design flow. Particularly, the time-based power analysis can provide fine-grained power consumption information to facilitate the diagnosis of power issues and guide power optimization accordingly. However, it may take tens of hours to conduct time-based power analysis on modern large-scale circuits, which greatly slows down the power optimization flow. In this paper, we present the first GPU-accelerated gate-level time-based power analysis framework. We propose a novel data structure to enable efficient state-dependent power retrieval. To accommodate the imbalanced event distribution across gates, we propose an event-density-aware partitioning strategy that allocates GPU threads based on gate event density. Finally, we fuse the power computation into a single kernel invocation to reduce redundant work in separate kernels. Experimental results show that our proposed framework achieves high accuracy while delivering up to 37.63 × end-to-end speedup compared to multi-threaded Synopsys PrimeTime PX.