一句话：提出层次化预取，用软件分析划分粗粒度功能块（Bundle）并由轻量硬件记录重放预取，较 FDIP 平均提速 6.6%。
服务器端应用庞大的指令工作集使前端取指成为瓶颈，即便配备取指导向预取（FDIP）也难以缓解；而面向服务器场景的预取器多依赖记录—重放机制来利用指令序列的重复性，却因实际控制流与预测控制流不一致而损失覆盖率与及时性。本文提出层次化预取（Hierarchical Prefetching）：先在服务器代码中识别常见的粗粒度功能块（称为 Bundle，涵盖数十至数百 KB 代码），再将其作为一个整体进行预取。该方法结合对代码的简单软件分析来形成 Bundle，以及轻量级硬件完成记录—重放式预取；由于大部分元数据保存在主存，片上存储需求不足 2KB。在 11 个流行服务器负载上的实验表明，该方法在缺失覆盖率和及时性上均显著优于先前技术，相对 FDIP 取得平均 6.6% 的性能提升。
The large working set of instructions in server-side applications causes a significant bottleneck in the front-end, even for high-performance processors equipped with fetch-directed instruction prefetching (FDIP). Prefetchers specifically designed for server scenarios typically rely on a record-and-replay mechanism that exploits the repetitiveness of instruction sequences. However, the efficacy of these techniques is compromised by discrepancies between actual and predicted control flows, resulting in loss of coverage and timeliness. This paper proposes Hierarchical Prefetching, a novel approach that tackles the limitations of existing prefetchers. It identifies common coarse-grained functionality blocks (called Bundles) within the server code and prefetches them as a whole. Bundles are significantly larger than typical prefetch targets, encompassing tens to hundreds of kilobytes of code. The approach combines simple software analysis of code for bundle formation and light-weight hardware for record-and-replay prefetching. The prefetcher requires under 2KB of on-chip storage by keeping most of the metadata in main memory. Experiments with 11 popular server workloads reveal that Hierarchical Prefetching significantly improves miss coverage and timeliness over prior techniques, achieving a 6.6% average performance gain over FDIP.
@inproceedings{ZhangGHLQSWZZZ25,
title = {Hierarchical Prefetching: A Software-Hardware Instruction Prefetcher for Server Applications},
author = {Tingji Zhang and Boris Grot and Wenjian He and Yashuai Lv and Peng Qu and Fang Su and Wenxin Wang and Guowei Zhang and Xuefeng Zhang and Youhui Zhang},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3676641.3716260}
}