Classification-Based Unified Cache Replacement via Partitioned Victim Address History

Classification-Based Unified Cache Replacement via Partitioned Victim Address History
复制标题

通过分区受害者地址历史记录进行基于分类的统一缓存替换

DOI:
10.1109/dsd51259.2020.00027
复制
发表时间:
2020
期刊:
2020 23rd Euromicro Conference on Digital System Design (DSD)
影响因子:
--
通讯作者:
Eishi Arima
Eishi Arima
中科院分区:
--
文献类型:
--
作者:
Eishi Arima

文献摘要

参考文献

被引文献

相似文献

在现代微处理器中,较低级别的高速缓存存储器通常被实现为统一的高速缓存,其中不同类别的高速缓存行(诸如数据、指令和页表缓存(PTE))共存。特别是在现代系统中,随着应用程序对更大工作集的需求,TLB攻击后频繁的PTE访问会发生,这一趋势自然会导致不同类型的缓存行之间的冲突,本文针对这种冲突问题,提出了一种基于分区的受害者地址历史的系统机制。先前的研究表明,基于历史的缓存管理的有效性,以预测重用,从而提高命中率。这项工作增加了以下功能:(1)将历史划分为多个区域,以分别跟踪所有不同缓存行类别的重用性;以及(2)在缓存替换时为不同的缓存行类别设置不同的分配优先级。此外,本文提出了一种控制系统,通过使用历史结构的统计信息,同时动态优化历史分区和该高速缓存分配优先级。实验结果表明,所提出的技术提高了性能显着相比,传统的LRU为基础的方法和其他。
In modern microprocessors, lower level cache memories are usually implemented as unified caches where different classes of cachelines such as data, instructions, and Page Table Entries (PTEs) coexist. Particularly, frequent PTE accesses following after TLB missies can happen on modern systems, which is driven by the increasing demands of applications for larger working set size, and this trend naturally leads to significant conflicts among these different kinds of cachelines.This paper targets the emerging conflict problem and provides a systematic mechanism using a partitioned victim address history. Prior studies have shown the effectiveness of history-based cache managements to predict the reuseness and thus to improve the hit rate. This work augments the following functionalities: (1) partitioning the history into multiple areas to separately keep track of the reuseness for all the different cacheline categories; and (2) setting different allocation priorities to the different cacheline categories when cache replacement. Furthermore, this paper proposes a control system to dynamically optimize the history partitions and the cache allocation priorities at the same time by using the statistics of the history structure. The experimental result indicates that the proposed technique improves performance considerably compared with the conventional LRU-based approach and others.
DOI: --
发表时间: --
期刊:
影响因子: --
作者:
Juan E. Navarro;Sitaram Iyer;P. Druschel;Alan L. Cox
通讯作者: Juan E. Navarro;Sitaram Iyer;P. Druschel;Alan L. Cox
DOI: --
发表时间: 2013
期刊: --
影响因子: --
作者:
A. Bhattacharjee
通讯作者: A. Bhattacharjee
页面覆盖:增强的虚拟内存框架,可实现细粒度的内存管理
DOI: 10.1145/2749469.2750379
发表时间: 2015
期刊: 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA)
影响因子: --
作者:
Vivek Seshadri;Gennady Pekhimenko;Olatunji Ruwase;O. Mutlu;Phillip B. Gibbons;M. Kozuch;T. Mowry;Trishul M. Chilimbi
通讯作者: Trishul M. Chilimbi
D-MRAM 缓存:利用 3T-1MTJ DRAM / MRAM 混合内存提高能源效率
DOI: 10.7873/date.2013.363
发表时间: 2013
期刊: 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)
影响因子: --
作者:
H. Noguchi;K. Nomura;K. Abe;S. Fujita;Eishi Arima;Kyundong Kim;Takashi Nakada;Shinobu Miwa;Hiroshi Nakamura
通讯作者: Hiroshi Nakamura
在缓存分区的 CMP 平台上协同调度 HPC 工作负载
DOI: --
发表时间: 2018
期刊: IEEE International Conference on Cluster Computing
影响因子: --
作者:
G. Aupy;A. Benoit;Brice Goglin;L. Pottier;Y. Robert
通讯作者: Y. Robert