<div class="gmail_quote">On Sat, Jul 28, 2012 at 3:00 AM, Roland Schulz <span dir="ltr"><<a href="mailto:roland@utk.edu" target="_blank">roland@utk.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im">On Thu, Jul 26, 2012 at 10:56 PM, Szilárd Páll <<a href="mailto:szilard.pall@cbr.su.se">szilard.pall@cbr.su.se</a>> wrote:<br>
<br>
> Note the *important* adjective above ;)<br>
><br>
> XML and GSL is irrelevant and I think we can be a bit smart and prune some<br>
> configs that we can be fairly confident that they're more or less<br>
> equivalent.<br>
><br>
> Not sure what you mean by "3 parallelization"; if it's MPI, tMPI, and OpenMP<br>
> than it's two or four (depending on weather we want to test both MPI/tMPI +<br>
> OpenMP on/off).<br>
</div>I meant no-mpi, libMPI, tMPI.<br>
<div class="im"><br>
> The number of (CPU) acceleration types can be slightly<br>
> reduced as I wouldn't consider anything but SSE/AVX that highly important.<br>
> Also, I'd consider only three OS-es and on some of them not all compilers<br>
> are available.<br>
><br>
> So we're left with ~ 10x2x3x2x4 = 480 configs per OS (and less on Win).<br>
</div>Sure but then you are already missing many possible configurations.<br></blockquote><div><br></div><div>Right, but there are some that are relevant for many users and some that are pretty much irrelevant for most (e.g. no tMPI & no MPI & no OpenMP).</div>
<div><br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I'm wondering whether it would make sense to pick randomly<br>
configurations from the all-vs-all configuration matrix. The most</blockquote><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
important configurations would already be tested by the Gerrit<br>
auto-trigger and with the random selection all odd combinations have a<br>
change to get picked over time.<br></blockquote><div><br></div><div>Randomly picking configurations could work, but unless the full coverage is achieved in just a few weeks, it's not very effective, I think.</div><div>
<br></div></div><div class="gmail_quote"><div>Additionally, the current gerrit auto-triggered configurations could use some extending.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im"><br>
> Assuming that each build takes ~3 min which is the case on 2-3 cores (note<br>
> that I mean build only!),<br>
</div>No the build time is currently much higher on all VMs. The IO<br>
performance is a significant factor.<br></blockquote><div><br></div><div>That's partly because of the tests. I/O is indeed an issue, we're planning to move the virtual disks with jenkins worspaces to SSDs, somebody just needs to find the time to do it.</div>
<div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">
> Even if we multiply the above 24h/4cores/OS with 3-4, it's still a rather<br>
> manageable number especially that AFAIK hardware resources are not the<br>
> biggest issue.<br>
</div>It should be easy to setup. I'm happy to help anyone who wants to add<br>
more Jenkins jobs.<br></blockquote><div><br></div><div>I know a few more that should be added, I'll try to add more when the NxN code is in.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br>
Roland<br>
<br>
><br>
> Cheers,<br>
> Sz.<br>
<div class="HOEnZb"><div class="h5">><br>
>><br>
>> Roland<br>
>><br>
>><br>
>><br>
>> ><br>
>> > --<br>
>> > Szilárd<br>
>> ><br>
>> >><br>
>> >> Mac. So it is somewhat surprising that you have 2 independent<br>
>> >> problems.<br>
>> >><br>
>> >> Roland<br>
>> >><br>
>> >> ><br>
>> >> > Many thanks,<br>
>> >> > Jochen<br>
>> >> ><br>
>> >> ><br>
>> >> > --<br>
>> >> > ---------------------------------------------------<br>
>> >> > Dr. Jochen Hub<br>
>> >> > Computational Molecular Biophysics Group<br>
>> >> > Institute for Microbiology and Genetics<br>
>> >> > Georg-August-University of Göttingen<br>
>> >> > Justus-von-Liebig-Weg 11, 37077 Göttingen, Germany.<br>
>> >> > Phone: <a href="tel:%2B49-551-39-14189" value="+495513914189">+49-551-39-14189</a><br>
>> >> > <a href="http://cmb.bio.uni-goettingen.de/" target="_blank">http://cmb.bio.uni-goettingen.de/</a><br>
>> >> > ---------------------------------------------------<br>
>> >> > --<br>
>> >> > gmx-developers mailing list<br>
>> >> > <a href="mailto:gmx-developers@gromacs.org">gmx-developers@gromacs.org</a><br>
>> >> > <a href="http://lists.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://lists.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">gmx-developers-request@gromacs.org</a>.<br>
>> >> ><br>
>> >> ><br>
>> >> ><br>
>> >> ><br>
>> >><br>
>> >><br>
>> >><br>
>> >> --<br>
>> >> ORNL/UT Center for Molecular Biophysics <a href="http://cmb.ornl.gov" target="_blank">cmb.ornl.gov</a><br>
>> >> 865-241-1537, ORNL PO BOX 2008 MS6309<br>
>> >> --<br>
>> >> gmx-developers mailing list<br>
>> >> <a href="mailto:gmx-developers@gromacs.org">gmx-developers@gromacs.org</a><br>
>> >> <a href="http://lists.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://lists.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">gmx-developers-request@gromacs.org</a>.<br>
>> ><br>
>> ><br>
>><br>
>><br>
>><br>
>> --<br>
>> ORNL/UT Center for Molecular Biophysics <a href="http://cmb.ornl.gov" target="_blank">cmb.ornl.gov</a><br>
>> 865-241-1537, ORNL PO BOX 2008 MS6309<br>
>> --<br>
>> gmx-developers mailing list<br>
>> <a href="mailto:gmx-developers@gromacs.org">gmx-developers@gromacs.org</a><br>
>> <a href="http://lists.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://lists.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">gmx-developers-request@gromacs.org</a>.<br>
><br>
><br>
<br>
<br>
<br>
--<br>
ORNL/UT Center for Molecular Biophysics <a href="http://cmb.ornl.gov" target="_blank">cmb.ornl.gov</a><br>
865-241-1537, ORNL PO BOX 2008 MS6309<br>
--<br>
gmx-developers mailing list<br>
<a href="mailto:gmx-developers@gromacs.org">gmx-developers@gromacs.org</a><br>
<a href="http://lists.gromacs.org/mailman/listinfo/gmx-developers" target="_blank">http://lists.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">gmx-developers-request@gromacs.org</a>.<br>
</div></div></blockquote></div><br>