<div dir="ltr">Hi,<br><br>sorry for writing it confusing. One BlueGene core is 5.7x slower than one Barcelona core.<br><br>
<meta http-equiv="CONTENT-TYPE" content="text/html; charset=utf-8">
<title></title>
<meta name="GENERATOR" content="OpenOffice.org 2.4 (Unix)">
<style>
<!--
BODY,DIV,TABLE,THEAD,TBODY,TFOOT,TR,TH,TD,P { font-family:"DejaVu Sans"; font-size:x-small }
-->
</style>
<table rules="none" border="0" cellspacing="0" cols="3" frame="void">
<colgroup><col width="111"><col width="111"><col width="111"></colgroup>
<tbody>
<tr>
<td width="111" align="left" height="24"><br></td>
<td width="111" align="left">Barcelona</td>
<td width="111" align="left">PPC450</td>
</tr>
<tr>
<td align="left" height="24">Perfomance</td>
<td align="right">3.3</td>
<td align="right">0.6</td>
</tr>
<tr>
<td align="left" height="23">Peak</td>
<td align="right">16.8</td>
<td align="right">3.4</td>
</tr>
</tbody>
</table>
<br>The Performance is measured in both cases by taking the counted force Gflop divided by the measured time in the Force part. So it is the force only Gflop/s rate. <br><br><br>Roland<br><br><div class="gmail_quote">On Thu, Jul 31, 2008 at 2:15 AM, David van der Spoel <span dir="ltr"><<a href="mailto:spoel@xray.bmc.uu.se">spoel@xray.bmc.uu.se</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div class="Ih2E3d">Roland Schulz wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi,<br>
<br>
it was mostly wrong names in the #include statements.<br>
<br>
It works on BlueGene/P and is much faster than the C non-bonded kernel (about 2x). With this intrinsic C kernel one gets 18% of peak. Because BlueGene doesn't have SIMD commands specific for single precision (thus it does only 2 at a time instead of 4) the performance difference to Opteron is greater than for double precision code. The performance difference to a Barcelona 2.1Ghz core is 5.7x (at 20% peak).<br>
</blockquote>
<br></div>
I'm not sure I follow you.<br>
Are you saying the BlueGene/P core is 5.7 times faster than an Opteron core?<br>
Or the other way around? And in single or in double?<br>
<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>
Roland<div class="Ih2E3d"><br>
<br>
On Wed, Jul 30, 2008 at 12:29 PM, Roland Schulz <<a href="mailto:roland@utk.edu" target="_blank">roland@utk.edu</a> <mailto:<a href="mailto:roland@utk.edu" target="_blank">roland@utk.edu</a>>> wrote:<br>
<br>
Hi,<br>
<br>
it seems that the blugene non-bonded kernel in the CVS version is<br>
incomplete. E.g. the nb_kernel_bluegene_test_asm.h is missing as far<br>
as I can see. The gromacs wiki for bluegene explains how to get the<br>
kernel generated by mknb to work. Also on the mailinglist all the<br>
messages I found about BlueGene were about mknb and not abou the<br>
bluegene specifik kernel.<br>
<br>
Could it be that it is incomplete do one has to do somethng to<br>
generate these files?<br>
<br>
Roland<br>
<br>
<br>
On Wed, Jul 30, 2008 at 11:45 AM, Berk Hess <<a href="mailto:hessb@mpip-mainz.mpg.de" target="_blank">hessb@mpip-mainz.mpg.de</a><br></div><div class="Ih2E3d">
<mailto:<a href="mailto:hessb@mpip-mainz.mpg.de" target="_blank">hessb@mpip-mainz.mpg.de</a>>> wrote:<br>
<br>
Hi,<br>
<br>
Mathias Puetz from IBM wrote non-bonded kernels for BlueGene/L.<br>
I don't know if these are also used for BlueGene/P.<br>
If there are problems, he would be the person to contact.<br>
<br>
Berk.<br>
<br>
<br>
Roland Schulz wrote:<br>
<br>
Hi,<br>
<br>
has someone looked at the non-bonded kernels for BlueGene/P?<br>
Based on the assembler produced by the compiler, it does no<br>
SIMD, runs out of registers and does unnecessary rounding.<br>
<br>
Are there plans for a PPC450 assembler kernel?<br>
<br>
Roland<br>
This email was Anti Virus checked by Astaro Security<br>
Gateway. <a href="http://www.astaro.com" target="_blank">http://www.astaro.com</a><br>
------------------------------------------------------------------------<br>
<br>
_______________________________________________<br>
gmx-developers mailing list<br></div>
<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a> <mailto:<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a>><div class="Ih2E3d">
<br>
<a href="http://www.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://www.gromacs.org/mailman/listinfo/gmx-developers</a><br>
Please don't post (un)subscribe requests to the list. Use<br>
the www interface or send it to<br>
<a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a><br></div>
<mailto:<a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a>>.<br>
<br>
<br>
_______________________________________________<br>
gmx-developers mailing list<br>
<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a> <mailto:<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a>><div class="Ih2E3d">
<br>
<a href="http://www.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://www.gromacs.org/mailman/listinfo/gmx-developers</a><br>
Please don't post (un)subscribe requests to the list. Use the<br>
www interface or send it to <a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a><br></div>
<mailto:<a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a>>.<div class="Ih2E3d"><br>
<br>
<br>
<br>
<br>
------------------------------------------------------------------------<br>
<br>
_______________________________________________<br>
gmx-developers mailing list<br>
<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a><br>
<a href="http://www.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://www.gromacs.org/mailman/listinfo/gmx-developers</a><br>
Please don't post (un)subscribe requests to the list. Use the www interface or send it to <a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a>.<br>
</div></blockquote>
<br>
<br>
-- <br>
David.<br>
________________________________________________________________________<br><font color="#888888">
David van der Spoel, PhD, Assoc. Prof., Molecular Biophysics group,<br>
Dept. of Cell and Molecular Biology, Uppsala University.<br>
Husargatan 3, Box 596, 75124 Uppsala, Sweden<br>
phone: 46 18 471 4205 fax: 46 18 511 755<br>
<a href="mailto:spoel@xray.bmc.uu.se" target="_blank">spoel@xray.bmc.uu.se</a> <a href="mailto:spoel@gromacs.org" target="_blank">spoel@gromacs.org</a> <a href="http://folding.bmc.uu.se" target="_blank">http://folding.bmc.uu.se</a><br>
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++</font><div><div></div><div class="Wj3C7c"><br>
_______________________________________________<br>
gmx-developers mailing list<br>
<a href="mailto:gmx-developers@gromacs.org" target="_blank">gmx-developers@gromacs.org</a><br>
<a href="http://www.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://www.gromacs.org/mailman/listinfo/gmx-developers</a><br>
Please don't post (un)subscribe requests to the list. Use the www interface or send it to <a href="mailto:gmx-developers-request@gromacs.org" target="_blank">gmx-developers-request@gromacs.org</a>.<br>
</div></div></blockquote></div><br></div>