AROSJul 31

Themis: Software-Defined Hardware Prefetching

UW
arXiv:2608.002597.5h-index: 28
Predicted impact top 47% in AR · last 90 daysOriginality Incremental advance
AI Analysis

For datacenter workloads where memory bandwidth is limited, Themis improves prefetching efficiency by reducing useless prefetches, providing a practical solution that can be applied to any hardware prefetcher.

Themis is a profile-guided hardware prefetching solution that uses page-level hints in page-table entries to disable prefetchers for certain data pages, reducing useless prefetch requests by about 40% and achieving speedups of 4.1% for BOP, 3.1% for SPP+PPF, and 1.4% for Pythia on datacenter workloads.

Data cache misses represent a significant portion of stall cycles in datacenter workloads. Hardware prefetchers that reduce such stalls by fetching data ahead of time have become increasingly sophisticated. However, to achieve high coverage, they have to prefetch aggressively, generating many inaccurate accesses that waste memory bandwidth. This is problematic in datacenter environments where memory bandwidth is a limited resource due to high multi-tenancy. We observe that for datacenter workloads, inaccurate prefetches can be effectively filtered on a data page granularity, without sacrificing prefetch coverage. However, storing per-page metadata about prefetch usefulness in hardware is costly, so we propose a novel hardware-software interface for data prefetching: The software directs the hardware on where to prefetch, and the hardware identifies and issues prefetches in the regions of interest. We propose Themis, a profile-guided hardware prefetching solution that implements this new interface. Themis utilizes page-level hints stored in page-table entries to disable the prefetcher for certain data pages at runtime. Themis requires no binary or ISA changes and can be used to optimize processes without disrupting their execution. Themis is also orthogonal to existing works on prefetching and can be applied to optimize any hardware prefetcher. Our results show that Themis is able to achieve around 40% reduction in useless prefetch requests, resulting in speedup for all the evaluated prefetchers for datacenter workloads, including 4.1% for BOP, 3.1% for SPP+PPF, and 1.4% for Pythia.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes