libEnsemble: A Library to Coordinate the Concurrent Evaluation of Dynamic Ensembles of Calculations

Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on anything but aspirational/unicorn resources. Recognizing these tradeoffs as well as greater user functionality in a near-term exascale computing era, we present libEns...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on parallel and distributed systems Vol. 33; no. 4; pp. 977 - 988
Main Authors: Hudson, Stephen, Larson, Jeffrey, Navarro, John-Luke, Wild, Stefan M.
Format: Journal Article
Language:English
Published: New York IEEE 01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Arrays
Concurrent computing
Dynamic ensembles
Generators
History
HPC Python
Libraries
Optimization
Resource management
simulation support systems
workflow management
ISSN:1045-9219, 1558-2183
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on anything but aspirational/unicorn resources. Recognizing these tradeoffs as well as greater user functionality in a near-term exascale computing era, we present libEnsemble, a library aimed at particular scalability- and capability-stretching uses. libEnsemble enables running concurrent instances of an application in dynamically allocated ensembles through an extensible Python library. We highlight the structure, execution, and capabilities of the library on leading pre-exascale environments as well as advanced capabilities for exascale environments and beyond.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
None
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR). Scientific Discovery through Advanced Computing (SciDAC)
AC02-06CH11357; AC05-00OR22725
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2021.3082815