Parallel Processing White Papers

Parallel Processing of Matrix Multiplication in a CPU and GPU Heterogeneous Environment

Overview GPUs for numerical computations are becoming an attractive alternative in research. This paper proposes a new parallel processing environment for matrix multiplications by using both CPUs and GPUs. The execution time of matrix multiplications can be decreased to 40.1% by the method, compared with using the fastest of either CPU only case or GPU only case. The method performs well when matrix sizes are large.

Further White Paper Details
PublisherUniversity of Electro-Communications File FormatPDF
Date PublishedApril 2006 Downloads5
FormatWhite Papers   
Topics
Thin clients switch on digitally excluded

Thin clients switch on digitally excluded

Case study: Digital inclusion project tackles social exclusion in Liverpool more

Renault goes multilingual

Renault goes multilingual

Case study: Translation tech turns docs into 23 languages… more


Quick Sitemap Links: