PUL: Pre-load in Software for Caches Wouldn't Always Play Along

Abstract

Memory latencies and bandwidth are major factors, limiting system performance and scalability. Modern CPUs aim at hiding latencies by employing large caches, out-of-order execution, or complex hardware prefetchers. However, software-based prefetching exhibits higher efficiency, improving with newer CPU generations. In this paper we investigate software-based, post-Moore systems that offload operations to intelligent memories. We show that software-based prefetching has even higher potential in near-data processing settings by maximizing compute utilization through compute/IO interleaving.