Scalable N-worst algorithms for dynamic timing and activity analysis

Abstract

As the overheads for ensuring the correctness of electronic designs continue to increase with continued technology scaling and increased variability, better-than-worst-case (BTWC) design has gained significant attention. Many BTWC design techniques utilize dynamic timing and activity information for design analysis and optimization. These techniques rely on path-based analysis that enumerates the exercised paths in a design as targets for analysis and optimization. However, path-based dynamic analysis techniques are not scalable and cannot be used to analyze full processors and full applications. On the other hand, graph-based techniques like those that form the foundational building blocks of electronic design automation tools are scalable and can efficiently analyze large designs. In this paper, we extend graph-based analysis to provide the fundamental dynamic analysis tools necessary for BTWC design, analysis, and optimization. Specifically, we present scalable graph-based techniques to report the N-worst exercised paths in a design for three metrics — timing criticality (slack), activity (toggle count), and activity subject to delay constraints. Compared to existing path-based techniques, our scalable dynamic analysis techniques improve average performance by 977 x, 163 x, and 113 x, respectively, and enable scalable analysis for a full processor design running full applications.