Branch Prediction as a Reinforcement Learning Problem: Why, How and Case Studies
Machine Learning
2021-06-28 v1 Artificial Intelligence
Abstract
Recent years have seen stagnating improvements to branch predictor (BP) efficacy and a dearth of fresh ideas in branch predictor design, calling for fresh thinking in this area. This paper argues that looking at BP from the viewpoint of Reinforcement Learning (RL) facilitates systematic reasoning about, and exploration of, BP designs. We describe how to apply the RL formulation to branch predictors, show that existing predictors can be succinctly expressed in this formulation, and study two RL-based variants of conventional BPs.
Keywords
Cite
@article{arxiv.2106.13429,
title = {Branch Prediction as a Reinforcement Learning Problem: Why, How and Case Studies},
author = {Anastasios Zouzias and Kleovoulos Kalaitzidis and Boris Grot},
journal= {arXiv preprint arXiv:2106.13429},
year = {2021}
}
Comments
6 pages, appeared in ML workshop for Computer Architecture and Systems 2021