Efficient selective multicore prefetching under limited memory bandwidth

Abstract

Current multicore systems implement multiple hardware prefetchers to tolerate long main memory latencies. However, memory bandwidth is a scarce shared resource which becomes critical with the increasing core count. To deal with this fact, recent works have focused on adaptive prefetchers, which control the prefetcher aggressiveness to regulate the main memory bandwidth consumption. Nevertheless, in limited bandwidth machines or under memory-hungry workloads, keeping active the prefetcher can damage the system performance and increase energy consumption. This paper introduces selective prefetching, where individual prefetchers are activated or deactivated to improve both main memory energy and performance, and proposes ADP, a prefetcher that deactivates local prefetchers in some cores when they present low performance and co-runners need additional bandwidth. Based on heuristics, an individual prefetcher is reactivated when performance enhancements are foreseen. Compared to a state-of-the-art adaptive prefetcher, ADP provides both performance and energy enhancements in limited memory bandwidth.

Bandwidth-Aware Dynamic Prefetch Configuration for IBM POWER8

“…Previous or contemporary with research on commercial machines, many research work has been carried out on simulation frameworks focusing on regulating the prefetcher aggressiveness. A representative subset of these works is [18], [19], [8], [20], [21], [22], [23], and [24]. In a similar way, sandbox prefetching [6], propose to implement a set of prefetchers and, at run-time, compare the prefetch patterns generated by each prefetcher with the memory accesses of the application to select the prefetcher that better fits the application memory access pattern.…”