Co-scheduling HPC workloads on cache-partitioned CMP platforms
Co-scheduling HPC workloads on cache-partitioned CMP platforms
复制标题
在缓存分区的 CMP 平台上协同调度 HPC 工作负载
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Y. Robert
中科院分区：
文献类型：
--
作者：
G. Aupy;A. Benoit;Brice Goglin;L. Pottier;Y. Robert
随着诸如芯片多处理器（CMP）的众核架构的出现，访问全局共享存储器的处理单元的数量不断增加。协同调度技术用于提高此类架构上的应用吞吐量，但共享资源通常会产生严重的干扰。本文针对最后一级缓存（LLC）中的干扰问题，采用Intel最新推出的该高速缓存分配技术（CAT）对LLC进行分区，为每个协同调度的应用分配各自的缓存区域。我们认为m迭代HPC应用程序并发运行，并回答以下问题：（i）如何精确地建模这些应用程序的行为上的缓存分区的平台？以及（ii）应该为每个应用程序分配多少个内核和高速缓存部分，以最大限度地提高平台效率？在这里，平台效率被定义为全局性能最大化，或者保证每个应用程序每秒迭代的固定比率。通过广泛的实验，使用CAT，我们展示了多个HPC应用程序共同调度到CMP平台时，缓存分区的影响。
With the recent advent of many-core architectures such as chip multiprocessors (CMPs), the number of processing units accessing a global shared memory is constantly increasing. Co-scheduling techniques are used to improve application throughput on such architectures, but sharing resources often generates critical interferences. In this article, we focus on the interferences in the last level of cache (LLC) and use the Cache Allocation Technology (CAT) recently provided by Intel to partition the LLC and give each co-scheduled application their own cache area. We consider m iterative HPC applications running concurrently and answer to the following questions: (i) How to precisely model the behavior of these applications on the cache-partitioned platform? and (ii) how many cores and cache fractions should be assigned to each application to maximize the platform efficiency? Here, platform efficiency is defined as maximizing the performance either globally, or as guaranteeing a fixed ratio of iterations per second for each application. Through extensive experiments using CAT, we demonstrate the impact of cache partitioning when multiple HPC applications are co-scheduled onto CMP platforms.