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
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