Performance Measurements within Asynchronous Task-based Runtime Systems: A Double White Dwarf Merger as an Application release_xphmf3ntjfc77dqxwsnovlehhe

by Patrick Diehl and Dominic Marcello and Parsa Armini and Hartmut Kaiser and Sagiv Shiber and Geoffrey C. Clayton and Juhan Frank and Gregor Daiß and Dirk Pflüger and David Eder and Alice Koniges and Kevin Huck

Released as a article .

2021  

Abstract

Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and APEX to collect performance data and energy consumption. We added HPX application-specific performance counters to the Octo-Tiger full 3D AMR astrophysics application. This enables the combined visualization of physical and performance data to highlight bottlenecks with respect to different solvers. We examine the overhead introduced by these measurements, which is around 1%, with respect to the overall application runtime. We perform a convergence study for four different levels of refinement and analyze the application's performance with respect to adaptive grid refinement. The measurements' overheads are small, enabling the combined use of performance data and physical properties with the goal of improving the code's performance. All of these measurements were obtained on NERSC's Cori, Louisiana Optical Network Infrastructure's QueenBee2, and Indiana University's Big Red 3.
In text/plain format

Archived Files and Locations

application/pdf  737.4 kB
file_2vfohaexjneslgsg6jr3b57odi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-01-30
Version   v1
Language   en ?
arXiv  2102.00223v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 899252e7-929d-4a7d-a294-3bd7cefd9a2f
API URL: JSON