Hi Jack, <br> If you are considering only a single node with multiple processor then multi-threading is the best way, also the performance is better. And for clusters i.e running a program to span across multiple nodes then MPI is the probably the best way. Also you can embed multi-threading within each MPI processes on these nodes which are running given MPI program.<br>
<br>Regards,<br>--Mahesh Doijade,<br><a href="http://hpc.wce.org.in/site">http://hpc.wce.org.in/site</a><br><br><div class="gmail_quote">On Thu, Dec 1, 2011 at 1:15 AM, Jack Jacky <span dir="ltr"><<a href="mailto:shajarian_e@yahoo.com">shajarian_e@yahoo.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div><div style="color: rgb(0, 0, 0); background-color: rgb(255, 255, 255); font-family: times new roman,new york,times,serif; font-size: 12pt;">
<div>which is the best way for writing parallel codes mpi or multi threading and for what systems?</div></div></div><br>_______________________________________________<br>
mpich-discuss mailing list <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
To manage subscription options or unsubscribe:<br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss</a><br>
<br></blockquote></div><br><br clear="all"><br>
<br><br>