ISEGEN: Generation of High-Quality Instruction Set Extensions by Iterative Improvement

TL;DR

ISEGEN is an iterative approach inspired by the Kernighan-Lin heuristic that efficiently generates high-quality instruction set extensions, matching optimal solutions and significantly outperforming genetic algorithms in speed and effectiveness.

Contribution

The paper introduces ISEGEN, a novel iterative method for instruction set extension generation that achieves near-optimal quality with much faster computation than genetic algorithms.

Findings

Matches the quality of exhaustive search solutions.

20x faster than genetic algorithms.

35% more speedup on cryptographic applications.

Abstract

Customization of processor architectures through Instruction Set Extensions (ISEs) is an effective way to meet the growing performance demands of embedded applications. A high-quality ISE generation approach needs to obtain results close to those achieved by experienced designers, particularly for complex applications that exhibit regularity: expert designers are able to exploit manually such regularity in the data flow graphs to generate high-quality ISEs. In this paper, we present ISEGEN, an approach that identifies high-quality ISEs by iterative improvement following the basic principles of the well-known Kernighan-Lin (K-L) min-cut heuristic. Experimental results on a number of MediaBench, EEMBC and cryptographic applications show that our approach matches the quality of the optimal solution obtained by exhaustive search. We also show that our ISEGEN technique is on average 20x faster than a genetic formulation that generates equivalent solutions. Furthermore, the ISEs identified by our technique exhibit 35% more speedup than the genetic solution on a large cryptographic application (AES) by effectively exploiting its regular structure.