Arsenal of Hardware Prefetchers

TL;DR

Arsenal is a dynamic prefetching framework that combines multiple hardware prefetchers, selecting the most effective one in real-time to improve latency tolerance across diverse workloads.

Contribution

It introduces a novel framework that adaptively switches between different prefetchers using Bloom filters, enhancing versatility and performance over individual prefetchers.

Findings

Achieves 44.29% speedup on single-core workloads.

Provides 19.5% average improvement on multi-core workloads.

Outperforms individual prefetchers in diverse access patterns.

Abstract

Hardware prefetching is one of the latency tolerance optimization techniques that tolerate costly DRAM accesses. Though hardware prefetching is one of the fundamental mechanisms prevalent on most of the commercial machines, there is no prefetching technique that works well across all the access patterns and different types of workloads. Through this paper, we propose Arsenal, a prefetching framework which allows the advantages provided by different data prefetchers to be combined, by dynamically selecting the best-suited prefetcher for the current workload. Thus effectively improving the versatility of the prefetching system. It bases on the classic Sandbox prefetcher that dynamically adapts and utilizes multiple offsets for sequential prefetchers. We take it to the next step by switching between prefetchers like Multi look Ahead Offset Prefetching and Timing SKID Prefetcher on the run. Arsenal utilizes a space-efficient pooling filter, Bloom filters, that keeps track of useful prefetches of each of these component prefetchers and thus helps to maintain a score for each of the component prefetchers. This approach is shown to provide better speedup than anyone prefetcher alone. Arsenal provides a performance improvement of 44.29% on the single-core mixes and 19.5% for some of the selected 25 representative multi-core mixes.