paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Bootstrapping

Bootstrapping(自举)
ASPLOS Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems2019匹配度 0/10 · 论文聚焦处理器微架构中的解耦前瞻(DLA)与 SMT 核优化,属于体系结构方向,与静态分析、LLM/Agent、浮点程序分析或贝叶斯程序分析没有可识别的交集。引用 5 inbox
Sushant Kondguli, Michael Huang
crossref: 2026-09-12

AI 速览

一句话:提出 Bootstrapping,让解耦前瞻在单个 SMT 核上达到双核效果,显著提升单线程性能。

单线程性能提升仍是通用处理器的重要目标,但核心微架构设计近年趋于停滞,程序中蕴含的并行性尚未被充分利用。解耦前瞻(DLA)通过独立线程上下文改善主流水线的数据与指令供给,是提升单线程性能的有效途径,但其默认实现需要额外核心;SMT 上的朴素实现又效率低下。本文提出优化的 Bootstrapping 实现,使 DLA 在单个 SMT 核上也能像使用两个核心一样有效。在多个基准套件上,融合双核可带来 1.22 倍提升,而 Bootstrapping 取得 1.48 倍加速,表明其可作为通用微架构中颇具吸引力的特性。

问题
单线程性能提升面临微架构设计停滞,而解耦前瞻(DLA)虽有效却依赖额外核心,SMT 朴素实现效率低。
方法
提出 Bootstrapping,优化 DLA 在单个 SMT 核上的执行,使辅助线程上下文高效服务主流水线。
评估
在广泛基准套件上评估,Bootstrapping 相比基线取得 1.48 倍加速,优于双核融合的 1.22 倍。
原文摘要(Abstract)

Single-thread performance improvement remains a central design goal for general purpose processors. Microarchitectural designs for the core have reached a plateau over the past years. However, we are still far from exhausting the implicit parallelism available in today's programs. One approach is to use a separate thread context to improve data and instruction supply to the main pipeline. Such decoupled look-ahead (DLA) architectures have been shown to be an effective way to improve single-thread performance. However, a default implementation requires an additional core. While an SMT flavor is possible, a naive implementation is inefficient and thus slow. In this paper, we propose an optimized implementation called Bootstrapping that makes DLA just as effective on a single (SMT) core as using two cores. While fusing two cores can improve single-thread performance by 1.22x, Bootstrapping provides a speedup of 1.48 over a broad range of benchmark suites, making it a compelling microarchitectural feature for general-purpose microarchitectures.

链接与引用

DOI 原文 · PDF(开放获取) ·

BibTeX
@inproceedings{paperbot4921,
  title = {Bootstrapping},
  author = {Sushant Kondguli and Michael Huang},
  booktitle = {ASPLOS},
  year = {2019},
  doi = {10.1145/3297858.3304052}
}