Characterizing the Performance of Executing Many-tasks on Summit
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 18-25
Abstract
Many scientific workloads are comprised of many tasks, where each task is an independent simulation or analysis of data. The execution of millions of tasks on heterogeneous HPC platforms requires scalable dynamic resource management and multi-level scheduling. RADICAL-Pilot (RP) -- an implementation of the Pilot abstraction, addresses these challenges and serves as an effective runtime system to execute workloads comprised of many tasks. In this paper, we characterize the performance of executing many tasks using RP when interfaced with JSM and PRRTE on Summit: RP is responsible for resource management and task scheduling on acquired resource; JSM or PRRTE enact the placement of launching of scheduled tasks. Our experiments provide lower bounds on the performance of RP when integrated with JSM and PRRTE. Specifically, for workloads comprised of homogeneous single-core, 15 minutes-long tasks we find that: PRRTE scales better than JSM for > O(1000) tasks; PRRTE overheads are negligible; and PRRTE supports optimizations that lower the impact of overheads and enable resource utilization of 63% when executing O(16K), 1-core tasks over 404 compute nodes.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- High-Throughput Computing on High-Performance Platforms: A Case Study2017
- CMS use of allocation based HPC resourcesJournal of Physics: Conference Series, 2017
- SAGA: A standardized access layer to heterogeneous Distributed Computing InfrastructureSoftwareX, 2015
- The Impact of Heterogeneous Computing on Workflows for Biomolecular Simulation and AnalysisComputing in Science & Engineering, 2015
- Flux: A Next-Generation Resource Management Framework for Large HPC Centers2014
- Evolution of the ATLAS PanDA workload management system for exascale computational scienceJournal of Physics: Conference Series, 2014
- Integration of cloud, grid and local cluster resources with DIRACJournal of Physics: Conference Series, 2011
- glideinWMS—a generic pilot-based workload management systemJournal of Physics: Conference Series, 2008
- DIRAC: A Scalable Lightweight Architecture for High Throughput Computing2004
- Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation2004