Hybrid Update/Invalidate Schemes for Cache Coherence Protocols

TL;DR

This paper introduces hybrid cache coherence schemes that dynamically switch between updating and invalidating data blocks during processor writes, based on runtime program conditions, aiming to optimize cache performance.

Contribution

It proposes novel hybrid schemes for cache coherence that adapt at runtime, supported by a custom simulator and benchmark analysis.

Findings

Hybrid schemes outperform traditional methods in certain scenarios

Runtime switching improves cache efficiency

Benchmark results validate the proposed approach

Abstract

In general when considering cache coherence, write back schemes are the default. These schemes invalidate all other copies of a data block during a write. In this paper we propose several hybrid schemes that will switch between updating and invalidating on processor writes at runtime, depending on program conditions. We created our own cache simulator on which we could implement our schemes, and generated data sets from both commercial benchmarks and through artificial methods to run on the simulator. We analyze the results of running the benchmarks with various schemes, and suggest further research that can be done in this area.