Mainstream parallel array programming on cell

Paul Keir, Paul Cockshott, Andrew Richards

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)
14 Downloads (Pure)

Abstract

We present the E# compiler and runtime library for the `F' subset of the Fortran 95 programming language. `F' provides first-class support for arrays, allowing E#
to implicitly evaluate array expressions in parallel using the SPU co-processors of the Cell Broadband Engine. We present performance results from four benchmarks that all demonstrate absolute speedups over equivalent `C' or Fortran
versions running on the PPU host processor. A significant benefit of this straightforward approach is that a serial implementation of any code is always available, providing code longevity, and a familiar development paradigm.
Original languageEnglish
Title of host publicationEuro-Par 2011: Parallel Processing Workshops
Subtitle of host publicationCCPI, CGWS, HeteroPar, HiBB, HPCVirt, HPPC, HPSS, MDGS, ProPer, Resilience, UCHPC, VHPC, Bordeaux, France, August 29 – September 2, 2011, Revised Selected Papers, Part I
EditorsMichael Alexander, Pasqua D’Ambra, Adam Belloum, George Bosilca, Mario Cannataro, Marco Danelutto, Beniamino Di Martino, Michael Gerndt, Emmanuel Jeannot, Raymond Namyst, Jean Roman, Stephen L. Scott, Jesper Larsson Traff, Geoffroy Vallée, Josef Weidendorfe
PublisherSpringer-Verlag
Pages260-269
Number of pages10
Volume 7155
ISBN (Electronic) 978-3-642-29737-3
ISBN (Print)978-3-642-29736-6
DOIs
Publication statusPublished - 2012
Externally publishedYes

Publication series

NameLecture Notes in Computer Science
PublisherSpringer-Verlag
ISSN (Print)0302-9743

Keywords

  • multicore
  • parallelism
  • heterogeneous
  • array
  • collection
  • cell
  • fortran

Fingerprint

Dive into the research topics of 'Mainstream parallel array programming on cell'. Together they form a unique fingerprint.

Cite this