High-productivity software development with pMatlab

Julie Mullen; Nadya Bliss; Robert Bond; Jeremy Kepner; Hahn Kim; Albert Reuther

doi:10.1109/MCSE.2009.9

High-productivity software development with pMatlab

Julie Mullen, Nadya Bliss, Robert Bond, Jeremy Kepner, Hahn Kim, Albert Reuther

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

5 Scopus citations

Abstract

The MIT Lincoln Laboratory, US, has created an interactive parallel development environment that includes the pMatlab and MatlabMPI, which is an open source Matlab-compatible library for interprocessor communication. pMatlab is a parallel Matlab library that provides an easy-to-use programming environment, lowering the problem of developing parallel and distributed application codes.The laboratory has also developed the gridMatlab, which is a proprietary library that connects the user's desktop computer Matlab session with N-1 remote Matlab session on a large distributed cluster. It is found that the core data structures in pMatlab are distributed arrays. It is observed pMatlab creates these distributed arrays through maps, which provide the ability of rapidly transforming a serial program into a parallel program, by specifying the way data is to be distributed across a number of processors.

Original language	English (US)
Article number	4720227
Pages (from-to)	75-79
Number of pages	5
Journal	Computing in Science and Engineering
Volume	11
Issue number	1
DOIs	https://doi.org/10.1109/MCSE.2009.9
State	Published - Jan 2009
Externally published	Yes

ASJC Scopus subject areas

Computer Science(all)
Engineering(all)

Access to Document

10.1109/MCSE.2009.9

Cite this

@article{f1e5dcb7104645e8a3395d7d1e258f02,

title = "High-productivity software development with pMatlab",

abstract = "The MIT Lincoln Laboratory, US, has created an interactive parallel development environment that includes the pMatlab and MatlabMPI, which is an open source Matlab-compatible library for interprocessor communication. pMatlab is a parallel Matlab library that provides an easy-to-use programming environment, lowering the problem of developing parallel and distributed application codes.The laboratory has also developed the gridMatlab, which is a proprietary library that connects the user's desktop computer Matlab session with N-1 remote Matlab session on a large distributed cluster. It is found that the core data structures in pMatlab are distributed arrays. It is observed pMatlab creates these distributed arrays through maps, which provide the ability of rapidly transforming a serial program into a parallel program, by specifying the way data is to be distributed across a number of processors.",

author = "Julie Mullen and Nadya Bliss and Robert Bond and Jeremy Kepner and Hahn Kim and Albert Reuther",

note = "Funding Information: This work is sponsored by the US Air Force under Air Force contract FA8721-05-C-0002. Opinions, interpretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the US government.",

year = "2009",

month = jan,

doi = "10.1109/MCSE.2009.9",

language = "English (US)",

volume = "11",

pages = "75--79",

journal = "Computing in Science and Engineering",

issn = "1521-9615",

publisher = "IEEE Computer Society",

number = "1",

}

TY - JOUR

T1 - High-productivity software development with pMatlab

AU - Mullen, Julie

AU - Bliss, Nadya

AU - Bond, Robert

AU - Kepner, Jeremy

AU - Kim, Hahn

AU - Reuther, Albert

N1 - Funding Information: This work is sponsored by the US Air Force under Air Force contract FA8721-05-C-0002. Opinions, interpretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the US government.

PY - 2009/1

Y1 - 2009/1

N2 - The MIT Lincoln Laboratory, US, has created an interactive parallel development environment that includes the pMatlab and MatlabMPI, which is an open source Matlab-compatible library for interprocessor communication. pMatlab is a parallel Matlab library that provides an easy-to-use programming environment, lowering the problem of developing parallel and distributed application codes.The laboratory has also developed the gridMatlab, which is a proprietary library that connects the user's desktop computer Matlab session with N-1 remote Matlab session on a large distributed cluster. It is found that the core data structures in pMatlab are distributed arrays. It is observed pMatlab creates these distributed arrays through maps, which provide the ability of rapidly transforming a serial program into a parallel program, by specifying the way data is to be distributed across a number of processors.

AB - The MIT Lincoln Laboratory, US, has created an interactive parallel development environment that includes the pMatlab and MatlabMPI, which is an open source Matlab-compatible library for interprocessor communication. pMatlab is a parallel Matlab library that provides an easy-to-use programming environment, lowering the problem of developing parallel and distributed application codes.The laboratory has also developed the gridMatlab, which is a proprietary library that connects the user's desktop computer Matlab session with N-1 remote Matlab session on a large distributed cluster. It is found that the core data structures in pMatlab are distributed arrays. It is observed pMatlab creates these distributed arrays through maps, which provide the ability of rapidly transforming a serial program into a parallel program, by specifying the way data is to be distributed across a number of processors.

UR - http://www.scopus.com/inward/record.url?scp=58149127204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149127204&partnerID=8YFLogxK

U2 - 10.1109/MCSE.2009.9

DO - 10.1109/MCSE.2009.9

M3 - Article

AN - SCOPUS:58149127204

SN - 1521-9615

VL - 11

SP - 75

EP - 79

JO - Computing in Science and Engineering

JF - Computing in Science and Engineering

IS - 1

M1 - 4720227

ER -

High-productivity software development with pMatlab

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this