<html><body>
<DIV><BR>-------------- Original message -------------- <BR>From: Jon Forrest <jlforrest@berkeley.edu> <BR><BR>> That said, I just don't see how Microsoft's HPC server <BR>> can succeed. </DIV>
<DIV class=signature> </DIV>
<DIV class=signature>Yes, it seems impossible, but then what is success here? In the most</DIV>
<DIV class=signature>limited sense this is a perimeter defending move by Microsoft. Now</DIV>
<DIV class=signature>that a much larger part of the IT world is parallel and the Linux/HPC universe </DIV>
<DIV class=signature>has a parallel cluster/savvy advantage along several dimensions. But also</DIV>
<DIV class=signature>considered those new entrants into clustered server computing arena in</DIV>
<DIV class=signature>proximity markets like finance where there is a lot of "application server"</DIV>
<DIV class=signature>type work that is initiated from a Windows desktops. Then there is the</DIV>
<DIV class=signature>improved workflow argument and the "high productivity computing" concept.</DIV>
<DIV class=signature>That's mind share grabber with folks making spending decisions in these</DIV>
<DIV class=signature>new arrival areas. Then there is raw staying power. </DIV>
<DIV class=signature> </DIV>
<DIV class=signature>If by success you mean total replacement and domination, not likely ... but</DIV>
<DIV class=signature>if you mean capturing a somewhat larger share of the new arrivals into the market</DIV>
<DIV class=signature>and protecting their flank from a end around stimulated by the parallel revolution</DIV>
<DIV class=signature>... then I would say, yes ... they can succeed.</DIV>
<DIV class=signature> </DIV>
<DIV class=signature>rbw</DIV>
!DSPAM:47f556a9131301523621093!
</body></html>