Skip to main navigation Skip to search Skip to main content

PUMA-V: An interactive visual tool for code optimization and parallelization based on the polyhedral model

  • Eric Papenhausen
  • , Klaus Mueller
  • , Harper Langston
  • , Benoit Meister
  • , Richard Lethin
  • Stony Brook University
  • Reservoir Labs

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

1 Scopus citations

Abstract

Taking advantage of multi-core processing has become crucial in realizing significant performance gains for most applications. When it comes to performance optimization, this has led to a delicate balancing act between parallelism and locality. Furthermore, exposing parallelism can require some non-trivial transformations. Although tools exist to automatically identify good transformations, a user guided exploration can often yield substantially better performance. We have developed a visualization interface, called PUMA-V, which combines user and machine efforts to optimize parallel code performance. By conveying information related to the structure of the code and performance characteristics, the user can focus on a subset of transformations to alleviate performance bottlenecks. Combining automatic optimization techniques with interactive visualizations helps the user perform this exploration rapidly.

Original languageEnglish
Title of host publication2016 New York Scientific Data Summit, NYSDS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467390514
DOIs
StatePublished - Nov 17 2016
Event2016 New York Scientific Data Summit, NYSDS 2016 - New York, United States
Duration: Aug 14 2016Aug 17 2016

Publication series

Name2016 New York Scientific Data Summit, NYSDS 2016 - Proceedings

Conference

Conference2016 New York Scientific Data Summit, NYSDS 2016
Country/TerritoryUnited States
CityNew York
Period08/14/1608/17/16

Keywords

  • optimization
  • polyhedral model
  • visualization

Fingerprint

Dive into the research topics of 'PUMA-V: An interactive visual tool for code optimization and parallelization based on the polyhedral model'. Together they form a unique fingerprint.

Cite this