Energy-aware mappings of series-parallel workflows onto chip multiprocessors

Abstract : This paper studies the problem of mapping streaming appli- cations that can be modeled by a series-parallel graph, onto a 2-dimensional tiled CMP architecture. The objective of the mapping is to minimize the energy consumption, using dynamic and voltage scaling techniques, while maintaining a given level of performance, reflected by the rate of process- ing the data streams. This mapping problem turns out to be NP-hard, but we identify simpler instances, whose optimal solution can be computed by a dynamic programming algo- rithm in polynomial time. Several heuristics are proposed to tackle the general problem, building upon the theoretical results. Finally, we assess the performance of the heuris- tics through comprehensive simulations using the StreamIt workflow suite and various CMP grid sizes.
Complete list of metadatas

Cited literature [49 references]  Display  Hide  Download

https://hal.inria.fr/inria-00560707
Contributor : Anne Benoit <>
Submitted on : Monday, April 4, 2011 - 2:10:28 PM
Last modification on : Monday, February 18, 2019 - 2:12:32 PM

File

RR-7521.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00560707, version 2

Collections

Citation

Anne Benoit, Rami Melhem, Paul Renaud-Goud, Yves Robert. Energy-aware mappings of series-parallel workflows onto chip multiprocessors. [Research Report] RR-7521, INRIA. 2011, pp.40. ⟨inria-00560707v2⟩

Share

Metrics

Record views

384

Files downloads

233