<div dir="ltr">If we do want to go with some big datasets, I can provide some 1024^3 and 1536^3 unigrids. I'm sure others have better AMR data than I do.<br></div><div class="gmail_extra"><br><br><div class="gmail_quote">
On Fri, Mar 1, 2013 at 3:41 PM, Matthew Turk <span dir="ltr"><<a href="mailto:matthewturk@gmail.com" target="_blank">matthewturk@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hey Sam,<br>
<div class="im"><br>
On Fri, Mar 1, 2013 at 2:38 PM, Sam Skillman <<a href="mailto:samskillman@gmail.com">samskillman@gmail.com</a>> wrote:<br>
> I think in terms of providing a test for the cluster, the benchmark should<br>
> not require the shipment of data. For the benchmarking of yt for yt's own<br>
> sake, then we do need to test the IO performance.<br>
<br>
</div>I'm not really sure that we want to avoid IO...<br>
<div class="im"><br>
><br>
> I think it'd be great to make an in-memory dataset that can then be used for<br>
> testing performance. For example, set up a bunch of refined spheres and<br>
> then project/slice/profile/render/halo find?<br>
<br>
</div>Perhaps, but will our current IC generators work at really, really big<br>
scale? I didn't think they would. Plus it's hard to get them to<br>
subdivide -- you end up with ltos of nested grids.<br>
<div class="HOEnZb"><div class="h5"><br>
><br>
> Sam<br>
><br>
><br>
> On Fri, Mar 1, 2013 at 12:31 PM, Matthew Turk <<a href="mailto:matthewturk@gmail.com">matthewturk@gmail.com</a>> wrote:<br>
>><br>
>> Hi Jeff,<br>
>><br>
>> Sure. I got asked for a standard yt performance benchmark to be run<br>
>> to figure out performance of an analysis cluster and evaluate its<br>
>> readiness. :) I think it's safe to sya that we should be pushing<br>
>> things like IO, memory capacity and communication performance.<br>
>><br>
>> Adding such a set of scripts (and their results!) would be very useful<br>
>> going forward, along with a little description of why we chose the<br>
>> routines we did.<br>
>><br>
>> -Matt<br>
>><br>
>> On Fri, Mar 1, 2013 at 2:17 PM, j s oishi <<a href="mailto:jsoishi@gmail.com">jsoishi@gmail.com</a>> wrote:<br>
>> > Matt,<br>
>> ><br>
>> > It might be helpful if you shared some more details of this particular<br>
>> > benchmarking exercise, if you can. It would be helpful for making sure<br>
>> > we present the most usefil information to the people asking for it as<br>
>> > well as info that is useful to us going forwards.<br>
>> ><br>
>> > j<br>
>> ><br>
>> > On Fri, Mar 1, 2013 at 2:05 PM, Matthew Turk <<a href="mailto:matthewturk@gmail.com">matthewturk@gmail.com</a>><br>
>> > wrote:<br>
>> >> Definitely, yes. For what it's worth, the specific use case I have in<br>
>> >> mind is for performance testing a system, so I think scalability will<br>
>> >> be important.<br>
>> >><br>
>> >> On Fri, Mar 1, 2013 at 2:01 PM, Cameron Hummels <<a href="mailto:chummels@gmail.com">chummels@gmail.com</a>><br>
>> >> wrote:<br>
>> >>> It might be worth showing how well this works on a single proc as well<br>
>> >>> as<br>
>> >>> how well it works using parallel mode on a few different numbers of<br>
>> >>> processors.<br>
>> >>><br>
>> >>><br>
>> >>> On Fri, Mar 1, 2013 at 1:57 PM, Christopher Moody<br>
>> >>> <<a href="mailto:chrisemoody@gmail.com">chrisemoody@gmail.com</a>><br>
>> >>> wrote:<br>
>> >>>><br>
>> >>>> Perhaps a benchmark for simply calculating a derived field? This<br>
>> >>>> would<br>
>> >>>> then profile a much smaller codebase.<br>
>> >>>><br>
>> >>>> Also benchmarking projections/fields for AMR/octree/particles of<br>
>> >>>> similar<br>
>> >>>> resolutions would be pretty cool.<br>
>> >>>><br>
>> >>>> chris<br>
>> >>>><br>
>> >>>><br>
>> >>>> On Fri, Mar 1, 2013 at 10:53 AM, Matthew Turk <<a href="mailto:matthewturk@gmail.com">matthewturk@gmail.com</a>><br>
>> >>>> wrote:<br>
>> >>>>><br>
>> >>>>> Okay, I like that idea. So a unified script with timing for in each<br>
>> >>>>> section might include:<br>
>> >>>>><br>
>> >>>>> * Halo profiling<br>
>> >>>>> * Global projection<br>
>> >>>>> * Global profiles<br>
>> >>>>> * Global VR (CTF and OffAxisProj)<br>
>> >>>>><br>
>> >>>>> I think we probably want a large unigrid and a large AMR dataset to<br>
>> >>>>> run these on, too.<br>
>> >>>>><br>
>> >>>>> On Fri, Mar 1, 2013 at 1:50 PM, Nathan Goldbaum<br>
>> >>>>> <<a href="mailto:goldbaum@ucolick.org">goldbaum@ucolick.org</a>><br>
>> >>>>> wrote:<br>
>> >>>>> > Probably a good idea to try some off axis projections or simple<br>
>> >>>>> > volume<br>
>> >>>>> > renderings to test the VR code.<br>
>> >>>>> ><br>
>> >>>>> ><br>
>> >>>>> > On Fri, Mar 1, 2013 at 10:48 AM, Matthew Turk<br>
>> >>>>> > <<a href="mailto:matthewturk@gmail.com">matthewturk@gmail.com</a>><br>
>> >>>>> > wrote:<br>
>> >>>>> >><br>
>> >>>>> >> Hi all,<br>
>> >>>>> >><br>
>> >>>>> >> I got an email asking for a benchmark of yt. I think this is<br>
>> >>>>> >> very,<br>
>> >>>>> >> very valuable to have going forward. I was wondering if anyone<br>
>> >>>>> >> had<br>
>> >>>>> >> any suggestions?<br>
>> >>>>> >><br>
>> >>>>> >> I'm thinking that we probably want to test things like the halo<br>
>> >>>>> >> finder, projections, and phase plots. Would a medium (1536^3)<br>
>> >>>>> >> halo<br>
>> >>>>> >> profiling run do that? Do we want to add on some global<br>
>> >>>>> >> projections<br>
>> >>>>> >> and phase plots as well?<br>
>> >>>>> >><br>
>> >>>>> >> -Matt<br>
>> >>>>> >> _______________________________________________<br>
>> >>>>> >> yt-dev mailing list<br>
>> >>>>> >> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >>>>> >> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> >>>>> ><br>
>> >>>>> ><br>
>> >>>>> ><br>
>> >>>>> > _______________________________________________<br>
>> >>>>> > yt-dev mailing list<br>
>> >>>>> > <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >>>>> > <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> >>>>> ><br>
>> >>>>> _______________________________________________<br>
>> >>>>> yt-dev mailing list<br>
>> >>>>> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >>>>> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> >>>><br>
>> >>>><br>
>> >>>><br>
>> >>>> _______________________________________________<br>
>> >>>> yt-dev mailing list<br>
>> >>>> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >>>> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> >>>><br>
>> >>><br>
>> >>><br>
>> >>><br>
>> >>> --<br>
>> >>> Cameron Hummels<br>
>> >>> Postdoctoral Researcher<br>
>> >>> Steward Observatory<br>
>> >>> University of Arizona<br>
>> >>> <a href="http://chummels.org" target="_blank">http://chummels.org</a><br>
>> >>><br>
>> >>> _______________________________________________<br>
>> >>> yt-dev mailing list<br>
>> >>> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >>> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> >>><br>
>> >> _______________________________________________<br>
>> >> yt-dev mailing list<br>
>> >> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> >> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> > _______________________________________________<br>
>> > yt-dev mailing list<br>
>> > <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> > <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
>> _______________________________________________<br>
>> yt-dev mailing list<br>
>> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
>> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
><br>
><br>
><br>
> _______________________________________________<br>
> yt-dev mailing list<br>
> <a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
> <a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
><br>
_______________________________________________<br>
yt-dev mailing list<br>
<a href="mailto:yt-dev@lists.spacepope.org">yt-dev@lists.spacepope.org</a><br>
<a href="http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org" target="_blank">http://lists.spacepope.org/listinfo.cgi/yt-dev-spacepope.org</a><br>
</div></div></blockquote></div><br></div>