POSTER: The Liberation Day of Nondeterministic Programs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The demand for thread-level parallelism (TLP) is endless, especially on commodity processors, as TLP is essential for gaining performance. However, the TLP of today's programs is limited by dependences that must be satisfied at run time. We have found that for nondeterministic programs, some of these actual dependences can be satisfied with alternative data that can be generated in parallel, therefore boosting the program's TLP. We show how these dependences (which we call 'state dependences' because they are related to the program's state) can be exploited using algorithm-specific knowledge. To demonstrate the practicality of our technique, we implemented a system called April25th that incorporates the concept of 'state dependences'. This system boosts the performance of five nondeterministic, multi-threaded PARSEC benchmarks by 100.5%.

Original languageEnglish (US)
Title of host publicationProceedings - 26th International Conference on Parallel Architectures and Compilation Techniques, PACT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages136-137
Number of pages2
ISBN (Electronic)9781467395243
DOIs
StatePublished - Oct 31 2017
Event26th International Conference on Parallel Architectures and Compilation Techniques, PACT 2017 - Portland, United States
Duration: Sep 9 2017Sep 13 2017

Publication series

NameParallel Architectures and Compilation Techniques - Conference Proceedings, PACT
Volume2017-September
ISSN (Print)1089-795X

Other

Other26th International Conference on Parallel Architectures and Compilation Techniques, PACT 2017
Country/TerritoryUnited States
CityPortland
Period9/9/179/13/17

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'POSTER: The Liberation Day of Nondeterministic Programs'. Together they form a unique fingerprint.

Cite this