On Fri, Nov 12, 2010 at 9:52 AM, Barry Smith <span dir="ltr"><<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<br>
What should we use a for programming model for PETSc on multi-core systems? Currently for conventional multicore we have only have one MPI process per core and for GPU we have subclasses of Vec and Mat with custom CUDA code.<br>
<br>
Should we introduce subclasses of Vec and Mat built on pthreads (this is what Bill G recommends, and not to use OpenMP)?<br></blockquote><div><br></div><div>pthreads are a nightmare and do not do vectorization right, which is necessary here. I am for OpenCL/CUDA. Eventually</div>
<div>I think OpenCL will take its head out of its ass and be as nice as CUDA.</div><div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Is there a way to have some kind of consistent model between conventional multicore and GPU multi-core? If not the same code. What about this MCUDA stuff?<br>
<font color="#888888"><br>
Barry<br></font></blockquote></div>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener<br>