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

Stephen Hudson; Jeffrey Larson; John-Luke Navarro; Stefan M. Wild

doi:10.1109/TPDS.2021.3082815

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

Distributed, Parallel, and Cluster Computing 2021-06-28 v1

Authors: Stephen Hudson , Jeffrey Larson , John-Luke Navarro , Stefan M. Wild

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

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.

Keywords

libensemble concurrent evaluation dynamic ensembles exascale computing python library workflow management

Cite

@article{arxiv.2104.08322,
  title  = {libEnsemble: A Library to Coordinate the Concurrent Evaluation of Dynamic Ensembles of Calculations},
  author = {Stephen Hudson and Jeffrey Larson and John-Luke Navarro and Stefan M. Wild},
  journal= {arXiv preprint arXiv:2104.08322},
  year   = {2021}
}

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

Abstract

Keywords

Cite

Related papers