2020 journal article

The Case for Domain-Specialized Branch Predictors for Graph-Processing

IEEE COMPUTER ARCHITECTURE LETTERS, 19(2), 101–104.

By: A. Samara n & J. Tuck n 

co-author countries: United States of America πŸ‡ΊπŸ‡Έ
author keywords: Graph-processing; branch prediction
Source: Web Of Science
Added: August 10, 2020

Branch prediction is believed by many to be a solved problem, with state-of-the-art predictors achieving near-perfect prediction for many programs. In this article, we conduct a detailed simulation of graph-processing workloads in the GAPBS benchmark suite and show that branch mispredictions occur frequently and are still a large limitation on performance in key graph-processing applications. We provide a detailed analysis of which branches are mispredicting and show that a few key branches are the main source of performance degradation across the graph-processing benchmarks we looked at. We also propose a few ideas for future work to improve branch prediction accuracy on graph workloads.