Skip to main navigation Skip to search Skip to main content

Communication-aware parallelization strategies for high performance applications

  • Delft University of Technology
  • LAB-STICC

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

With the advent of multicore processor architectures and the existence of a huge legacy code base, the need for efficient and scalable parallel zing compilers is growing. Where multi-core processors were seen as the way forward to address the known challenges such as the memory, power and ILP wall, efficient parallelization to make use of the multiple cores, is still an open issue. In this paper, we present two complementary tools, MCROF and XPU which provide an alternative development path to parallelise applications and that address the challenges of identifying potential parallelism and exploiting it in a different way. The MCROF tool provides a detailed profile of the data flowing inside an application and the XPU programming paradigm provides an intuitive and simple interface to express parallelism as well as the necessary runtime support. We demonstrate through two different use cases that better performance up to 4× can be achieved than available commercial compilers.

Original languageEnglish
Title of host publicationProceedings - IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2015
PublisherIEEE Computer Society
Pages539-544
Number of pages6
ISBN (Electronic)9781479987184
DOIs
Publication statusPublished - 27 Oct 2015
EventIEEE Computer Society Annual Symposium on VLSI, ISVLSI 2015 - Montpellier, France
Duration: 8 Jul 2015 → 10 Jul 2015

Publication series

NameProceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
Volume07-10-July-2015
ISSN (Print)2159-3469
ISSN (Electronic)2159-3477

Conference

ConferenceIEEE Computer Society Annual Symposium on VLSI, ISVLSI 2015
Country/TerritoryFrance
CityMontpellier
Period8/07/15 → 10/07/15

Keywords

  • Data-communication profiling
  • Multicore
  • Parallel Programming
  • Program Parallelization

Fingerprint

Dive into the research topics of 'Communication-aware parallelization strategies for high performance applications'. Together they form a unique fingerprint.

Cite this