Characterizing Application Performance Sensitivity to R esource Contention in Multicore Architectures
Characterizing Application Performance Sensitivity to R esource Contention in Multicore Architectures
复制标题
表征多核架构中应用程序性能对资源争用的敏感性
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
P. Mehrotra
中科院分区：
文献类型：
--
作者：
Haoqiang Jin;R. Hood;Johnny Chang;J. Djomehri;D. Jespersen;K. Taylor;R. Biswas;P. Mehrotra
内存层次结构中共享资源的争用可能会对基于商用多核微处理器的高端计算机上运行的应用程序的性能产生深远的影响。在本文中，我们描述了一种基于差异性能分析的方法，用于量化这种争用对并行应用程序的影响。特别是，我们通过比较使用不同模式将进程分配给多核节点上的核心的运行来描述对特定共享资源的争用。我们通过在使用四种不同四核微处理器（英特尔 Clovertown、英特尔 Harpertown、AMD 巴塞罗那和英特尔 Nehalem-EP）的高端计算平台上运行的 HPCC 基准测试和 NAS 并行基准测试的子集来演示我们的方法。结果有助于我们进一步了解这些代码对其执行环境的要求以及每台计算机提供性能的能力。
Contention for shared resources in the memory hierarchy can have a profound effect on the performance of applications running on high-end computers based on commodity multicore microprocessors. In this paper we describe a methodology, based on differential performance analysis, to quantify the effect of this contention on parallel applications. In particular, we characterize the contention for a specific shared resource by comparing runs that use different patterns of assigning processes to cores on multicore nodes. We demonstrate our approach with a subset of the HPCC benchmarks and the NAS Parallel Benchmarks running on high-end computing platforms that use four different quad-core microprocessors—Intel Clovertown, Intel Harpertown, AMD Barcelona, and Intel Nehalem-EP. The results help further our understanding of the requirements these codes place on their execution environments and also of each computer’s ability to deliver performance.