An orchestration language for parallel objects

Laxmikant V. Kalé; Mark Hills; Chao Huang

doi:10.1145/1066650.1066658

An orchestration language for parallel objects

Laxmikant V. Kalé, Mark Hills, Chao Huang

Siebel School of Computing and Data Science

Research output: Contribution to conference › Paper › peer-review

Abstract

Charm++, a parallel object language based on the idea of virtual processors, has attained significant success in efficient parallelization of applications. Requiring the user to only decompose the computation into a large number of objects ("virtual processors"), Charm++ empowers its intelligent adaptive runtime system to assign and reassign the objects to processors at runtime. This facility is used to optimize execution, including dynamic load balancing. However, in complex applications, Charm++ programs obscure the overall flow of control: one must look at the code of multiple objects to discern how the sets of objects are orchestrated in a given application. In this paper, we present an orchestration notation that allows expression of Charm++ functionality without its fragmented flow of control.

Original language	English (US)
DOIs	https://doi.org/10.1145/1066650.1066658
State	Published - 2004
Event	7th Workshop on Languages, Compilers, and Run-Time Support for Scalable Systems, LCR '04 - Houston, TX, United States Duration: Oct 22 2004 → Oct 23 2004

Other

Other	7th Workshop on Languages, Compilers, and Run-Time Support for Scalable Systems, LCR '04
Country/Territory	United States
City	Houston, TX
Period	10/22/04 → 10/23/04

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Online availability

10.1145/1066650.1066658

Library availability

Discover UIUC Full Text

Cite this

@conference{073b313b07be40baba1e6d02362b9b17,

title = "An orchestration language for parallel objects",

abstract = "Charm++, a parallel object language based on the idea of virtual processors, has attained significant success in efficient parallelization of applications. Requiring the user to only decompose the computation into a large number of objects ({"}virtual processors{"}), Charm++ empowers its intelligent adaptive runtime system to assign and reassign the objects to processors at runtime. This facility is used to optimize execution, including dynamic load balancing. However, in complex applications, Charm++ programs obscure the overall flow of control: one must look at the code of multiple objects to discern how the sets of objects are orchestrated in a given application. In this paper, we present an orchestration notation that allows expression of Charm++ functionality without its fragmented flow of control.",

author = "Kal{\'e}, {Laxmikant V.} and Mark Hills and Chao Huang",

year = "2004",

doi = "10.1145/1066650.1066658",

language = "English (US)",

note = "7th Workshop on Languages, Compilers, and Run-Time Support for Scalable Systems, LCR '04 ; Conference date: 22-10-2004 Through 23-10-2004",

}

TY - CONF

T1 - An orchestration language for parallel objects

AU - Kalé, Laxmikant V.

AU - Hills, Mark

AU - Huang, Chao

PY - 2004

Y1 - 2004

N2 - Charm++, a parallel object language based on the idea of virtual processors, has attained significant success in efficient parallelization of applications. Requiring the user to only decompose the computation into a large number of objects ("virtual processors"), Charm++ empowers its intelligent adaptive runtime system to assign and reassign the objects to processors at runtime. This facility is used to optimize execution, including dynamic load balancing. However, in complex applications, Charm++ programs obscure the overall flow of control: one must look at the code of multiple objects to discern how the sets of objects are orchestrated in a given application. In this paper, we present an orchestration notation that allows expression of Charm++ functionality without its fragmented flow of control.

AB - Charm++, a parallel object language based on the idea of virtual processors, has attained significant success in efficient parallelization of applications. Requiring the user to only decompose the computation into a large number of objects ("virtual processors"), Charm++ empowers its intelligent adaptive runtime system to assign and reassign the objects to processors at runtime. This facility is used to optimize execution, including dynamic load balancing. However, in complex applications, Charm++ programs obscure the overall flow of control: one must look at the code of multiple objects to discern how the sets of objects are orchestrated in a given application. In this paper, we present an orchestration notation that allows expression of Charm++ functionality without its fragmented flow of control.

UR - http://www.scopus.com/inward/record.url?scp=77953950162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953950162&partnerID=8YFLogxK

U2 - 10.1145/1066650.1066658

DO - 10.1145/1066650.1066658

M3 - Paper

AN - SCOPUS:77953950162

T2 - 7th Workshop on Languages, Compilers, and Run-Time Support for Scalable Systems, LCR '04

Y2 - 22 October 2004 through 23 October 2004

ER -

An orchestration language for parallel objects

Abstract

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this