Probabilistic Directed Writebacks for Exclusive Caches

Author:

Olson Lena E.1,Hill Mark D.1

Affiliation:

1. University of Wisconsin-Madison, Madison, WI

Abstract

Energy is an increasingly important consideration in memory system design. Caches improve energy efficiency by decreasing execution time and reducing the number of main memory accesses, but they suffer from known inefficiencies: the last-level cache (LLC) tends to have a high miss ratio while simultaneously storing many blocks that are never referenced. Because these blocks are not referenced before eviction, we can write them directly to memory rather than to the LLC. To do so, we must predict which blocks will not be referenced. Previous approaches rely on additional state at the LLC and/or extra communication. We show that by predicting working set size per program counter (PC), we can decide which blocks have low probability of being referenced. Our approach relies on the insight that it is possible to makes this prediction based solely on the address stream as seen by the level-one data cache (L1D), eliminating the need to store or communicate PC values between levels of the cache hierarchy. We require no modifications to the LLC. Our approach uses Flajolet andMartin's probabilistic counting to keep the state small: two additional bits per L1D block, with an additional 6KB prediction table. This approach yields a large reduction in number of LLC writebacks: 25% fewer for SPEC on average, 80% fewer for graph500, and 67% fewer for an in-memory hash table.

Publisher

Association for Computing Machinery (ACM)

Reference31 articles.

1. graph500 -- the graph500 list. http://www.graph500.org/. graph500 -- the graph500 list. http://www.graph500.org/.

2. The reuse cache

3. FreshCache: Statically and dynamically exploiting dataless ways

4. Universal classes of hash functions (Extended Abstract)

5. Improving cache performance by selective cache bypass

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3