<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=GB2312" http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
The question of OpenMP vs MPI has been around for a long time,<br>
for example:<br>
<br>
<a class="moz-txt-link-freetext" href="http://www.beowulf.org/archive/2001-March/002718.html">http://www.beowulf.org/archive/2001-March/002718.html</a><br>
<br>
My general impression is that it is a waste of time to convert from
pure MPI to<br>
a hybrid approach. For example:<br>
<br>
<a class="moz-txt-link-abbreviated" href="http://www.sc2000.org/techpapr/papers/pap.pap214.pdf">www.sc2000.org/techpapr/papers/pap.pap214.pdf</a><br>
<br>
On the other hand, here's a fellow who got a 4X speedup by going to
hybrid:<br>
<br>
<a class="moz-txt-link-abbreviated" href="http://www.nersc.gov/nusers/services/training/">www.nersc.gov/nusers/services/training/</a><wbr>classes/NUG/Jun04/NUG2004_yhe_hybrid.ppt<br>
<br>
<font size="-1"><span class="a">My own view is that with a modern
cluster with fast processors and with inter-node communications not<br>
that much slower than a cache miss to main memory, the unified MPI
model makes more sense, but<br>
there are many many papers arguing about this topic.<br>
<br>
-L<br>
<br>
</span></font>
</body>
</html>