<div dir="ltr"><div class="gmail_extra"><br><br><div class="gmail_quote">On Tue, Jul 1, 2014 at 12:47 AM, Alexey Shvetsov <span dir="ltr"><<a href="mailto:alexxy@omrb.pnpi.spb.ru" target="_blank">alexxy@omrb.pnpi.spb.ru</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Roland Schulz писал 01-07-2014 03:59:<br>
<div class="">> HI Alexey ,<br>
><br>
> On Fri, May 30, 2014 at 6:52 AM, Alexey Shvetsov<br>
> <<a href="mailto:alexxy@omrb.pnpi.spb.ru">alexxy@omrb.pnpi.spb.ru</a>> wrote:<br>
><br>
>> Hi!<br>
>><br>
>> I tryed to build 5.0 branch on ARM board (dual core cortex-a7). It<br>
>> builds (if<br>
>> i define arm as allowed arch in features/gccfeatures.h) but some<br>
>> regression<br>
>> tests fails.<br>
><br>
> What compiler did you use? Which tests fail?<br>
<br>
</div>Hi!<br>
<br>
I tryed with gcc-4.8.2. Spc and methanol test failed with SIGBUS<br>
<br>
There were 2 notes<br>
Reading file<br>
/home/alexxy/Develop/gromacs_build/none/src/programs/mdrun/tests/Testing/Temporary/CanWrite_Trajectories_ThatDifferInNstxout_0.tpr,<br>
VERSION 5.0-beta2-dev-20140211-9a31310 (single precision)<br>
Changing nstlist from 10 to 25, rlist from 1.022 to 1.076<br>
<br>
Using 1 MPI thread<br>
starting mdrun 'spc-and-methanol'<br>
6 steps, 0.0 ps.<br>
Bus error<br></blockquote><div><br></div><div>Could you post a backtrace to redmine?</div><div><br></div><div>BTW: Has anyone tried to compile & run Gromacs on Android? That way I would have test hardware ;-). </div>
<div><br></div><div>Roland</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br>
<br>
I'll rebuild current master with gcc-4.9 to check if there are same<br>
issue.<br>
<div class=""><br>
><br>
> Roland<br>
><br>
>> В письме от 30 мая 2014 12:43:29<br>
>> пользователь Szilárd Páll написал:<br>
>><br>
>>> Hi,<br>
>>><br>
>>> A few days ago I did some sanity checks by compiling and<br>
>>> regressiontesting the 5.0 branch on ARM. This exercise made me<br>
>> realize<br>
>>> that the recently included Random123 library is now the single<br>
>> most<br>
>>> limiting factor when it comes to portability. In fact, as it is<br>
>> not<br>
>>> optional, v5.0 is ATM practically limited to x86* and Powerpc64<br>
>> (BGQ)<br>
</div>>>> architectures -- based on the docs (see <a href="http://goo.gl/YdKofG" target="_blank">http://goo.gl/YdKofG</a> [1])<br>
<div><div class="h5">>>> Random123 has not been tested (let alone optimized) on anything<br>
>> else.<br>
>>> Additionally, note that the code won't even compile on<br>
>> non-supported<br>
>>> architectures, so in its current state GROMACS 5.0 won't compile<br>
>> on<br>
>>> anything else but x86* and PPC64, e.g. with gcc compilation will<br>
>> be<br>
>>> aborted by the "#error" in features/gccfeatures.h:38. Removing<br>
>> these<br>
>>> sanity checks does let the code compile on ARM and<br>
>> regressiontests do<br>
>>> pass, though.<br>
>>><br>
>>> I've exchanged a couple of emails with the developers and they<br>
>> suggest<br>
>>> that in practice Threefry should work on ARM (and perhaps other<br>
>>> architectures too), but testing/validation is definitely<br>
>> necessary.<br>
>>> Performance is not optimized on unsupported architectures, I<br>
>> assume,<br>
>>> so some optimization may not hurt too - especially if there are<br>
>> cases<br>
>>> where we generate many PRNGs per step (BTW has the potential<br>
>> overhead<br>
>>> been assessed?).<br>
>>><br>
>>> Cheers,<br>
>>> --<br>
>>> Szilárd<br>
>><br>
>> --<br>
>> Best Regards,<br>
>> Alexey 'Alexxy' Shvetsov, PhD<br>
>> Department of Molecular and Radiation Biophysics<br>
>> FSBI Petersburg Nuclear Physics Institute, NRC Kurchatov Institute,<br>
>> Leningrad region, Gatchina, Russia<br>
>> mailto:<a href="mailto:alexxyum@gmail.com">alexxyum@gmail.com</a><br>
>> mailto:<a href="mailto:alexxy@omrb.pnpi.spb.ru">alexxy@omrb.pnpi.spb.ru</a><br>
>><br>
>> --<br>
>> Gromacs Developers mailing list<br>
>><br>
>> * Please search the archive at<br>
</div></div>>> <a href="http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List</a> [2]<br>
>> before posting!<br>
>><br>
>> * Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a> [3]<br>
<div class="">>><br>
>> * For (un)subscribe requests visit<br>
>><br>
> <a href="https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers" target="_blank">https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers</a><br>
</div>>> [4] or send a mail to <a href="mailto:gmx-developers-request@gromacs.org">gmx-developers-request@gromacs.org</a>.<br>
><br>
> --<br>
> ORNL/UT Center for Molecular Biophysics <a href="http://cmb.ornl.gov" target="_blank">cmb.ornl.gov</a> [5]<br>
<div class="">> <a href="tel:865-241-1537" value="+18652411537">865-241-1537</a>, ORNL PO BOX 2008 MS6309<br>
><br>
</div>> Links:<br>
> ------<br>
> [1] <a href="http://goo.gl/YdKofG" target="_blank">http://goo.gl/YdKofG</a><br>
> [2] <a href="http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List</a><br>
> [3] <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
> [4]<br>
> <a href="https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers" target="_blank">https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers</a><br>
> [5] <a href="http://cmb.ornl.gov" target="_blank">http://cmb.ornl.gov</a><br>
<div class="HOEnZb"><div class="h5"><br>
--<br>
Best Regards,<br>
Alexey 'Alexxy' Shvetsov, PhD<br>
Department of Molecular and Radiation Biophysics<br>
FSBI Petersburg Nuclear Physics Institute, NRC Kurchatov Institute,<br>
Leningrad region, Gatchina, Russia<br>
mailto:<a href="mailto:alexxyum@gmail.com">alexxyum@gmail.com</a><br>
mailto:<a href="mailto:alexxy@omrb.pnpi.spb.ru">alexxy@omrb.pnpi.spb.ru</a><br>
</div></div></blockquote></div><br><br clear="all"><div><br></div>-- <br>ORNL/UT Center for Molecular Biophysics <a href="http://cmb.ornl.gov">cmb.ornl.gov</a><br>865-241-1537, ORNL PO BOX 2008 MS6309
</div></div>