Parallelism Reduction Based on Pattern Substitution in Dataflow Oriented Programming Languages

Loïc Cudennec 1, * Renaud Sirdey 1
* Corresponding author
1 Laboratoire des fondements des systèmes temps-réels embarqués
LIST - Laboratoire d'Intégration des Systèmes et des Technologies
Abstract : In this paper, we present a compiler extension for applications targeting high performance embedded systems. It analyzes the graph of a dataflow application in order to adapt its parallelism degree. Our approach consists in the detection and the substitution of built-in patterns in the dataflow. Modifications applied on the graph do not alter the semantic of the application. A parallelism reduction engine is also described to perform an exhaustive search of the best reduction. Our proposition has been implemented within an industry-grade compiler for the Sigma-C dataflow language. It shows that for dataflow applications, the parallelism reduction extension helps the user focus on the algorithm by hiding all parallelism tuning considerations. Experimentations demonstrate the accuracy and the performance of the reduction engine for both synthetic and real applications.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download
https://hal.inria.fr/hal-00706943
Contributor : Loïc Cudennec <>
Submitted on : Wednesday, June 13, 2012 - 2:01:37 PM
Last modification on : Friday, September 6, 2019 - 2:22:06 PM
Long-term archiving on : Friday, September 14, 2012 - 2:20:29 AM

File

cudsir_iccs2012.pdf
Files produced by the author(s)

Identifiers

Collections

CEA | DRT | LIST

Citation

Loïc Cudennec, Renaud Sirdey. Parallelism Reduction Based on Pattern Substitution in Dataflow Oriented Programming Languages. International Conference on Computational Science, ICCS 2012, University of Nebraska, Omaha, Jun 2012, Omaha, Nebraska, United States. pp.146-155, ⟨10.1016/j.procs.2012.04.016⟩. ⟨hal-00706943⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

316

Files downloads

536

Contact


archive-ouverte@inria.fr