Recently, multicore technology has been introduced to embedded systems in order to improve performance and reduce power consumption.
In the present study, three SMP multicore processors for embedded systems and a multicore processor for a desktop PC are evaluatedby the parallel benchmark using OpenMP. The results indicate that, even if the memory performance is low, applications thatare not memory-intensive exhibit large speedups by parallelization. The results also indicate a large performance improvementdue to parallelization using OpenMP, despite its low cost.
%0 Journal Article
%1 toshihiro2009evaluation
%A Hanawa, Toshihiro
%A Sato, Mitsuhisa
%A Lee, Jinpil
%A Imada, Takayuki
%A Kimura, Hideaki
%A Boku, Taisuke
%D 2009
%J Evolving OpenMP in an Age of Extreme Parallelism
%K Benchmarks Embedded Evaluation MicroBenchmarks MultiCore OpenMP Parallel
%P 15--27
%T Evaluation of Multicore Processors for Embedded Systems by Parallel Benchmark Program Using OpenMP
%U http://dx.doi.org/10.1007/978-3-642-02303-3_2
%X Recently, multicore technology has been introduced to embedded systems in order to improve performance and reduce power consumption.
In the present study, three SMP multicore processors for embedded systems and a multicore processor for a desktop PC are evaluatedby the parallel benchmark using OpenMP. The results indicate that, even if the memory performance is low, applications thatare not memory-intensive exhibit large speedups by parallelization. The results also indicate a large performance improvementdue to parallelization using OpenMP, despite its low cost.
@article{toshihiro2009evaluation,
abstract = {Recently, multicore technology has been introduced to embedded systems in order to improve performance and reduce power consumption.
In the present study, three SMP multicore processors for embedded systems and a multicore processor for a desktop PC are evaluatedby the parallel benchmark using OpenMP. The results indicate that, even if the memory performance is low, applications thatare not memory-intensive exhibit large speedups by parallelization. The results also indicate a large performance improvementdue to parallelization using OpenMP, despite its low cost.},
added-at = {2009-11-12T17:10:02.000+0100},
author = {Hanawa, Toshihiro and Sato, Mitsuhisa and Lee, Jinpil and Imada, Takayuki and Kimura, Hideaki and Boku, Taisuke},
biburl = {https://www.bibsonomy.org/bibtex/27a5bf57bc50d637806190baa65a1ad29/gron},
interhash = {ceb35b2c1527ff836806be0ce9f9ca99},
intrahash = {7a5bf57bc50d637806190baa65a1ad29},
journal = {Evolving OpenMP in an Age of Extreme Parallelism},
keywords = {Benchmarks Embedded Evaluation MicroBenchmarks MultiCore OpenMP Parallel},
pages = {15--27},
timestamp = {2009-11-12T17:10:02.000+0100},
title = {Evaluation of Multicore Processors for Embedded Systems by Parallel Benchmark Program Using OpenMP},
url = {http://dx.doi.org/10.1007/978-3-642-02303-3_2},
year = 2009
}