05.08.2012 Views

Par4all: Auto-Parallelizing C and Fortran for the CUDA Architecture

Par4all: Auto-Parallelizing C and Fortran for the CUDA Architecture

Par4all: Auto-Parallelizing C and Fortran for the CUDA Architecture

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

•Par4All ◮<br />

Hardware is moving quite (too) fast but...<br />

What has survived <strong>for</strong> 50+ years?<br />

<strong>Fortran</strong> programs...<br />

What has survived <strong>for</strong> 30+ years?<br />

C programs...<br />

• A lot of legacy code could be pushed onto parallel hardware<br />

(accelerators) with automatic tools...<br />

• Not as efficient as h<strong>and</strong>-tuned programs, but quick production<br />

phase<br />

• Need automatic tools <strong>for</strong> source-to-source trans<strong>for</strong>mation to<br />

leverage existing software tools <strong>for</strong> a given hardware<br />

�Par4All in <strong>CUDA</strong> — GPU conference 10/1/2009<br />

HPC Project, Mines ParisTech, TÉLÉCOM Bretagne, RPI Ronan KERYELL et al. 6 / 46

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!