High-productivity software development with pMatlab

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

Research output: Contribution to journalArticle

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 languageEnglish (US)
Article number4720227
Pages (from-to)75-79
Number of pages5
JournalComputing in Science and Engineering
Volume11
Issue number1
DOIs
StatePublished - Jan 1 2009

    Fingerprint

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Mullen, J., Bliss, N., Bond, R., Kepner, J., Kim, H., & Reuther, A. (2009). High-productivity software development with pMatlab. Computing in Science and Engineering, 11(1), 75-79. [4720227]. https://doi.org/10.1109/MCSE.2009.9