Extended Abstract: Productive Parallel Programming with Parsl

Kyle Chard; Yadu Babuji; Anna Woodard; Ben Clifford; Zhuozhao Li; Mihael Hategan; Ian Foster; Mike Wilde; Daniel S. Katz

doi:10.1145/3463478.3463486

Extended Abstract: Productive Parallel Programming with Parsl

Kyle Chard, Yadu Babuji, Anna Woodard, Ben Clifford, Zhuozhao Li, Mihael Hategan, Ian Foster, Mike Wilde, Daniel S. Katz

Research output: Contribution to journal › Article › peer-review

Abstract

Parsl is a parallel programming library for Python that aims to make it easy to specify parallelism in programs and to realize that parallelism on arbitrary parallel and distributed computing systems. Parsl relies on developers annotating Python functions—wrapping either Python or external applications—to indicate that these functions may be executed concurrently. Developers can then link together functions via the exchange of data. Parsl establishes a dynamic dependency graph and sends tasks for execution on connected resources when dependencies are resolved. Parsl’s runtime system enables different compute resources to be used, from laptops to supercomputers, without modification to the Parsl program.

Original language	English (US)
Pages (from-to)	51-54
Number of pages	4
Journal	Ada User Journal
Volume	42
Issue number	1
DOIs	https://doi.org/10.1145/3463478.3463486
State	Published - Mar 2021

ASJC Scopus subject areas

Software

Online availability

10.1145/3463478.3463486

Library availability

Discover UIUC Full Text

Cite this

@article{95cebcfcfbfe4d8b8716d92457e17d7e,

title = "Extended Abstract: Productive Parallel Programming with Parsl",

abstract = "Parsl is a parallel programming library for Python that aims to make it easy to specify parallelism in programs and to realize that parallelism on arbitrary parallel and distributed computing systems. Parsl relies on developers annotating Python functions—wrapping either Python or external applications—to indicate that these functions may be executed concurrently. Developers can then link together functions via the exchange of data. Parsl establishes a dynamic dependency graph and sends tasks for execution on connected resources when dependencies are resolved. Parsl{\textquoteright}s runtime system enables different compute resources to be used, from laptops to supercomputers, without modification to the Parsl program.",

author = "Kyle Chard and Yadu Babuji and Anna Woodard and Ben Clifford and Zhuozhao Li and Mihael Hategan and Ian Foster and Mike Wilde and Katz, {Daniel S.}",

year = "2021",

month = mar,

doi = "10.1145/3463478.3463486",

language = "English (US)",

volume = "42",

pages = "51--54",

journal = "Ada User Journal",

issn = "1381-6551",

publisher = "Ada-Europe",

number = "1",

}

TY - JOUR

T1 - Extended Abstract

T2 - Productive Parallel Programming with Parsl

AU - Chard, Kyle

AU - Babuji, Yadu

AU - Woodard, Anna

AU - Clifford, Ben

AU - Li, Zhuozhao

AU - Hategan, Mihael

AU - Foster, Ian

AU - Wilde, Mike

AU - Katz, Daniel S.

PY - 2021/3

Y1 - 2021/3

N2 - Parsl is a parallel programming library for Python that aims to make it easy to specify parallelism in programs and to realize that parallelism on arbitrary parallel and distributed computing systems. Parsl relies on developers annotating Python functions—wrapping either Python or external applications—to indicate that these functions may be executed concurrently. Developers can then link together functions via the exchange of data. Parsl establishes a dynamic dependency graph and sends tasks for execution on connected resources when dependencies are resolved. Parsl’s runtime system enables different compute resources to be used, from laptops to supercomputers, without modification to the Parsl program.

AB - Parsl is a parallel programming library for Python that aims to make it easy to specify parallelism in programs and to realize that parallelism on arbitrary parallel and distributed computing systems. Parsl relies on developers annotating Python functions—wrapping either Python or external applications—to indicate that these functions may be executed concurrently. Developers can then link together functions via the exchange of data. Parsl establishes a dynamic dependency graph and sends tasks for execution on connected resources when dependencies are resolved. Parsl’s runtime system enables different compute resources to be used, from laptops to supercomputers, without modification to the Parsl program.

UR - http://www.scopus.com/inward/record.url?scp=85132569864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132569864&partnerID=8YFLogxK

U2 - 10.1145/3463478.3463486

DO - 10.1145/3463478.3463486

M3 - Article

AN - SCOPUS:85132569864

SN - 1381-6551

VL - 42

SP - 51

EP - 54

JO - Ada User Journal

JF - Ada User Journal

IS - 1

ER -

Extended Abstract: Productive Parallel Programming with Parsl

Abstract

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this