Automatic parallelization of scripting languages

Toward transparent desktop parallel computing

Xiaosong Ma, Jiangtian Li, Nagiza F. Samatova

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Desktop computing remains indispensable in scientific exploration, largely because it provides people with devices for human interaction and environments for interactive job execution. However, with today's rapidly growing data volume and task complexity, it is increasingly hard for individual workstations to meet the demands of interactive scientific data processing. The increasing cost of such interactive processing is hindering the productivity of end-to-end scientific computing workflows. While existing distributed computing systems allow people to aggregate desktop workstation resources for parallel computing, the burden of explicit parallel programming and parallel job execution often prohibits scientists to take advantage of such platforms. In this paper, we discuss the need for transparent desktop parallel computing in scientific data processing. As an initial step toward this goal, we present our on-going work on the automatic parallelization of the scripting language R, a popular tool for statistical computing. Our preliminary results suggest that a reasonable speedup can be achieved on real-world sequential R programs without requiring any code modification.

Original languageEnglish
Title of host publicationProceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM
DOIs
Publication statusPublished - 24 Sep 2007
Externally publishedYes
Event21st International Parallel and Distributed Processing Symposium, IPDPS 2007 - Long Beach, CA, United States
Duration: 26 Mar 200730 Mar 2007

Other

Other21st International Parallel and Distributed Processing Symposium, IPDPS 2007
CountryUnited States
CityLong Beach, CA
Period26/3/0730/3/07

Fingerprint

Automatic Parallelization
Parallel processing systems
Parallel Computing
Natural sciences computing
Parallel programming
Computer workstations
Distributed computer systems
Statistical Computing
Computer systems
Scientific Computing
Productivity
Parallel Programming
Distributed Computing
Work Flow
Speedup
Processing
Costs
Resources
Computing
Interaction

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Mathematics(all)

Cite this

Ma, X., Li, J., & Samatova, N. F. (2007). Automatic parallelization of scripting languages: Toward transparent desktop parallel computing. In Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM [4228216] https://doi.org/10.1109/IPDPS.2007.370488

Automatic parallelization of scripting languages : Toward transparent desktop parallel computing. / Ma, Xiaosong; Li, Jiangtian; Samatova, Nagiza F.

Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM. 2007. 4228216.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ma, X, Li, J & Samatova, NF 2007, Automatic parallelization of scripting languages: Toward transparent desktop parallel computing. in Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM., 4228216, 21st International Parallel and Distributed Processing Symposium, IPDPS 2007, Long Beach, CA, United States, 26/3/07. https://doi.org/10.1109/IPDPS.2007.370488
Ma X, Li J, Samatova NF. Automatic parallelization of scripting languages: Toward transparent desktop parallel computing. In Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM. 2007. 4228216 https://doi.org/10.1109/IPDPS.2007.370488
Ma, Xiaosong ; Li, Jiangtian ; Samatova, Nagiza F. / Automatic parallelization of scripting languages : Toward transparent desktop parallel computing. Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM. 2007.
@inproceedings{94848c93950243ae9c325b9771147e0a,
title = "Automatic parallelization of scripting languages: Toward transparent desktop parallel computing",
abstract = "Desktop computing remains indispensable in scientific exploration, largely because it provides people with devices for human interaction and environments for interactive job execution. However, with today's rapidly growing data volume and task complexity, it is increasingly hard for individual workstations to meet the demands of interactive scientific data processing. The increasing cost of such interactive processing is hindering the productivity of end-to-end scientific computing workflows. While existing distributed computing systems allow people to aggregate desktop workstation resources for parallel computing, the burden of explicit parallel programming and parallel job execution often prohibits scientists to take advantage of such platforms. In this paper, we discuss the need for transparent desktop parallel computing in scientific data processing. As an initial step toward this goal, we present our on-going work on the automatic parallelization of the scripting language R, a popular tool for statistical computing. Our preliminary results suggest that a reasonable speedup can be achieved on real-world sequential R programs without requiring any code modification.",
author = "Xiaosong Ma and Jiangtian Li and Samatova, {Nagiza F.}",
year = "2007",
month = "9",
day = "24",
doi = "10.1109/IPDPS.2007.370488",
language = "English",
isbn = "1424409101",
booktitle = "Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM",

}

TY - GEN

T1 - Automatic parallelization of scripting languages

T2 - Toward transparent desktop parallel computing

AU - Ma, Xiaosong

AU - Li, Jiangtian

AU - Samatova, Nagiza F.

PY - 2007/9/24

Y1 - 2007/9/24

N2 - Desktop computing remains indispensable in scientific exploration, largely because it provides people with devices for human interaction and environments for interactive job execution. However, with today's rapidly growing data volume and task complexity, it is increasingly hard for individual workstations to meet the demands of interactive scientific data processing. The increasing cost of such interactive processing is hindering the productivity of end-to-end scientific computing workflows. While existing distributed computing systems allow people to aggregate desktop workstation resources for parallel computing, the burden of explicit parallel programming and parallel job execution often prohibits scientists to take advantage of such platforms. In this paper, we discuss the need for transparent desktop parallel computing in scientific data processing. As an initial step toward this goal, we present our on-going work on the automatic parallelization of the scripting language R, a popular tool for statistical computing. Our preliminary results suggest that a reasonable speedup can be achieved on real-world sequential R programs without requiring any code modification.

AB - Desktop computing remains indispensable in scientific exploration, largely because it provides people with devices for human interaction and environments for interactive job execution. However, with today's rapidly growing data volume and task complexity, it is increasingly hard for individual workstations to meet the demands of interactive scientific data processing. The increasing cost of such interactive processing is hindering the productivity of end-to-end scientific computing workflows. While existing distributed computing systems allow people to aggregate desktop workstation resources for parallel computing, the burden of explicit parallel programming and parallel job execution often prohibits scientists to take advantage of such platforms. In this paper, we discuss the need for transparent desktop parallel computing in scientific data processing. As an initial step toward this goal, we present our on-going work on the automatic parallelization of the scripting language R, a popular tool for statistical computing. Our preliminary results suggest that a reasonable speedup can be achieved on real-world sequential R programs without requiring any code modification.

UR - http://www.scopus.com/inward/record.url?scp=34548757823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548757823&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2007.370488

DO - 10.1109/IPDPS.2007.370488

M3 - Conference contribution

SN - 1424409101

SN - 9781424409105

BT - Proceedings - 21st International Parallel and Distributed Processing Symposium, IPDPS 2007; Abstracts and CD-ROM

ER -