Berti: an Accurate Local-Delta Data Prefetcher
1Dept. Informática e Ingeniería de Sistemas - I3A, Universidad de Zaragoza, Spain
2Dept. of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, India
3Computer Engineering Department (DITEC), University of Murcia, Spain
2Dept. of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, India
3Computer Engineering Department (DITEC), University of Murcia, Spain
News
- September, 2022: Web launched.
Abstract
Data prefetching is a technique that plays a crucial role in modern high-performance processors by hiding long latency memory accesses. Several state-of-the-art hardware prefetchers exploit the concept of deltas, defined as the difference between the cache line addresses of two demand accesses. Existing delta prefetchers, such as best offset prefetching (BOP) and multi-lookahead prefetching (MLOP), train and predict future accesses based on global deltas. We observed that the use of global deltas results in missed opportunities to anticipate memory accesses. In this paper, we propose Berti, a first-level data cache prefetcher that selects the best local deltas, i.e., those that consider only demand accesses issued by the same instruction. Thanks to a high-confidence mechanism that precisely detects the timely local deltas with high coverage, Berti generates accurate prefetch requests. Then, it orchestrates the prefetch requests to the memory hierarchy, using the selected deltas. Our empirical results using ChampSim and SPEC CPU2017 and GAP workloads show that, with a storage overhead of just 2.55 KB, Berti improves performance by 8.5% compared to a baseline IP-stride and 3.5% compared to IPCP, a state-of-the-art prefetcher. Our evaluation also shows that Berti reduces dynamic energy at the memory hierarchy by 33.6% compared to IPCP, thanks to its high prefetch accuracy.Downloads
Bibtex
@InProceedings{anavarrotorres-micro22,
author = {Agust{\'i}n Navarro-Torres and Biswabandan Panda and Jes{\'u}s Alastruey-Bened{\'e} and Pablo Ib{\'a}{\~n}ez and V{\'i}ctor Vi{\~n}als-Y{\'u}fera and Alberto Ros},
title = {Berti: An Accurate Local-Delta Data Prefetcher},
booktitle = {55th International Symposium on Microarchitecture (MICRO)},
doi = {10.1109/MICRO56248.2022.00072},
pages = {975--991},
year = {2022},
editor = {ACM/IEEE},
address = {Chicago, IL (USA)},
month = oct,
publisher = {IEEE Computer Society},
ratio-acep = {22.49\% (83/369)},
isbn = {978-1-6654-6272-3},
}