A Quantitative Analysis of Node Sharing on HPC Clusters Using XDMoD Application Kernels
Open Access
- 17 July 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Abstract
In this investigation, we study how application performance is affected when jobs are permitted to share compute nodes. A series of application kernels consisting of a diverse set of benchmark calculations were run in both exclusive and node-sharing modes on the Center for Computational Research's high-performance computing (HPC) cluster. Very little increase in runtime was observed due to job contention among application kernel jobs run on shared nodes. The small differences in runtime were quantitatively modeled in order to characterize the resource contention and attempt to determine the circumstances under which it would or would not be important. A machine learning regression model applied to the runtime data successfully fitted the small differences between the exclusive and shared node runtime data; it also provided insight into the contention for node resources that occurs when jobs are allowed to share nodes. Analysis of a representative job mix shows that runtime of shared jobs is affected primarily by the memory subsystem, in particular by the reduction in the effective cache size due to sharing; this leads to higher utilization of DRAM. Insights such as these are crucial when formulating policies proposing node sharing as a mechanism for improving HPC utilization.Keywords
This publication has 14 references indexed in Scilit:
- Application kernels: HPC resources performance monitoring and variance analysisConcurrency and Computation: Practice and Experience, 2015
- Analysis of XDMoD/SUPReMM Data Using Machine Learning Techniques2015
- Open XDMoD: A Tool for the Comprehensive Management of High-Performance Computing ResourcesComputing in Science & Engineering, 2015
- An Analysis of Node Sharing on HPC Clusters using XDMoD/TACC_Stats2014
- The case for colocation of high performance computing workloadsConcurrency and Computation: Practice and Experience, 2013
- Enabling fair pricing on HPC systems with node sharing2013
- Cache Pirating: Measuring the Curse of the Shared Cache2011
- NWChem: A comprehensive and scalable open-source solution for large scale molecular simulationsComputer Physics Communications, 2010
- Scalable molecular dynamics with NAMDJournal of Computational Chemistry, 2005
- General atomic and molecular electronic structure systemJournal of Computational Chemistry, 1993