Best-Offset Hardware Prefetching

被引:0
作者
Michaud, Pierre [1 ]
机构
[1] Inria, Campus Beaulieu, Rennes, France
来源
PROCEEDINGS OF THE 2016 IEEE INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE COMPUTER ARCHITECTURE (HPCA-22) | 2016年
关键词
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Hardware prefetching is an important feature of modern highperformance processors. When the application working set is too large to fit in on-chip caches, disabling hardware prefetchers may result in severe performance reduction. A new prefetcher was recently introduced, the Sandbox prefetcher, that tries to find dynamically the best prefetch offset using the sandbox method. The Sandbox prefetcher uses simple hardware and was shown to be quite effective. However, the sandbox method does not take into account prefetch timeliness. We propose an offset prefetcher with a new method for selecting the prefetch offset that takes into account prefetch timeliness. We show that our Best-Offset prefetcher outperforms the Sandbox prefetcher on the SPEC CPU2006 benchmarks, with equally simple hardware.
引用
收藏
页码:469 / 480
页数:12
相关论文
共 39 条
  • [1] [Anonymous], HPCA
  • [2] [Anonymous], 2011, MICRO
  • [3] [Anonymous], 2007, HPCA
  • [4] [Anonymous], MICRO
  • [5] [Anonymous], 2007, ISCA
  • [6] [Anonymous], 2014, INT 64 IA 32 ARCH OP
  • [7] [Anonymous], MICRO
  • [8] [Anonymous], 2006, ISCA
  • [9] [Anonymous], 2005, PLDI
  • [10] [Anonymous], 1997, ISCA