Hi.<br><br>I'm another one waiting for the OpenCL version here.<br><br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
4.6 will support only CUDA.<br>
<br>
OpenCL GPU implementations have yet match CUDA; on CPU it would hardly<br>
match the performance of the hand-tuned SSE kernels, moreover, CPU &<br>
GPU algorithms are not the same.<br></blockquote><div><br>If you allow me, the (second and third!) argument is not strong enough, since also cuda for cpu would not match the performance of all tricks from gromacs. Also, I think that the cpu and cuda algorithms are not the same. From my point of view, the only really strong argument would be the first one: "OpenCL GPU implementations have yet match CUDA!", despite the fact that I would like to see it better explained if possible (even a link would be suffice).<br>
<br>More important: does this mean that openMM and gromacs gpu development are "breaking apart"? What can we really expect from that, other than easier installation and usage?<br><br>Thanks a lot!<br><br>Sincerely yours,<br>
<br>Jones<br><br> </div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<span class="HOEnZb"><font color="#888888"><br>
--<br>
Szilárd<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
<br>
<br>
On Sun, Nov 27, 2011 at 11:25 PM, Alexey Shvetsov<br>
<<a href="mailto:alexxy@omrb.pnpi.spb.ru">alexxy@omrb.pnpi.spb.ru</a>> wrote:<br>
> Hi!<br>
><br>
> Will it use CUDA or OpenCL? Second one will be more common since it will<br>
> work with wider range of platfroms (cpu, gpu, fcpga)<br>
><br>
> Szilárd Páll писал 27.11.2011 23:50:<br>
>><br>
>> Native acceleration = not relying on external libraries. ;)<br>
>><br>
>> --<br>
>> Szilárd<br>
>><br>
>><br>
>><br>
>> On Sun, Nov 27, 2011 at 9:33 PM, Peter C. Lai <<a href="mailto:pcl@uab.edu">pcl@uab.edu</a>> wrote:<br>
>>><br>
>>> Random hijack:<br>
>>><br>
>>> Will the CUDA acceleration support CMAP or will it still be limited to<br>
>>> the limitations of OpenMM that it currently has?<br>
>>><br>
>>> On 2011-11-27 12:10:47PM -0600, Szilárd Páll wrote:<br>
>>>><br>
>>>> Hi Andrzej,<br>
>>>><br>
>>>> GROMACS 4.6 is work in progress, it will have native CUDA acceleration<br>
>>>> with multi-GPU support along a few other improvements. You can expect<br>
>>>> a speedup in the ballpark of 3x. We will soon have the code available<br>
>>>> for testing.<br>
>>>><br>
>>>> I'm a little skeptical about the 5x of ACEMD. What setting did you<br>
>>>> use? AFAIR they were using large time-steps without contraints in<br>
>>>> their benchmarks.<br>
>>>><br>
>>>> Cheers,<br>
>>>> --<br>
>>>> Szilárd<br>
>>>><br>
>>>><br>
>>>><br>
>>>> On Thu, Nov 24, 2011 at 9:53 AM, Andrzej Rzepiela<br>
>>>> <<a href="mailto:Andrzej.Rzepiela@physik.uni-freiburg.de">Andrzej.Rzepiela@physik.uni-freiburg.de</a>> wrote:<br>
>>>> > Dears,<br>
>>>> ><br>
>>>> > I would like to ask what performance improvement is expected for<br>
>>>> > future<br>
>>>> > releases (e.g. 4.6) for PME calculations on gpu cards. Last week I<br>
>>>> > sent<br>
>>>> > benchmark results for dhfr to the list, which show no performance gain<br>
>>>> > when<br>
>>>> > the newest versions of tesla cards vs intel xeon R are used (more or<br>
>>>> > less in<br>
>>>> > agreement of what is presented on the gromacs website). However, for<br>
>>>> > the<br>
>>>> > same system simulations with different gpu code, acemd, on a very<br>
>>>> > similar<br>
>>>> > machine can be about 5 times faster, as benchmarked recently by my<br>
>>>> > colleagues, suggesting that performance of gromacs may soon improve.<br>
>>>> > is that<br>
>>>> > correct ?<br>
>>>> ><br>
>>>> ><br>
>>>> > Andrzej<br>
>>>> > --<br>
>>>> > gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br>
>>>> > <a href="http://lists.gromacs.org/mailman/listinfo/gmx-users" target="_blank">http://lists.gromacs.org/mailman/listinfo/gmx-users</a><br>
>>>> > Please search the archive at<br>
>>>> > <a href="http://www.gromacs.org/Support/Mailing_Lists/Search" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/Search</a> before posting!<br>
>>>> > Please don't post (un)subscribe requests to the list. Use thewww<br>
>>>> > interface<br>
>>>> > or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>
>>>> > Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
>>>> ><br>
>>>> --<br>
>>>> gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br>
>>>> <a href="http://lists.gromacs.org/mailman/listinfo/gmx-users" target="_blank">http://lists.gromacs.org/mailman/listinfo/gmx-users</a><br>
>>>> Please search the archive at<br>
>>>> <a href="http://www.gromacs.org/Support/Mailing_Lists/Search" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/Search</a> before posting!<br>
>>>> Please don't post (un)subscribe requests to the list. Use the<br>
>>>> www interface or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>
>>>> Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
>>><br>
>>> --<br>
>>> ==================================================================<br>
>>> Peter C. Lai | University of Alabama-Birmingham<br>
>>> Programmer/Analyst | KAUL 752A<br>
>>> Genetics, Div. of Research | 705 South 20th Street<br>
>>> <a href="mailto:pcl@uab.edu">pcl@uab.edu</a> | Birmingham AL 35294-4461<br>
>>> <a href="tel:%28205%29%20690-0808" value="+12056900808">(205) 690-0808</a> |<br>
>>> ==================================================================<br>
>>><br>
>>> --<br>
>>> gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br>
>>> <a href="http://lists.gromacs.org/mailman/listinfo/gmx-users" target="_blank">http://lists.gromacs.org/mailman/listinfo/gmx-users</a><br>
>>> Please search the archive at<br>
>>> <a href="http://www.gromacs.org/Support/Mailing_Lists/Search" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/Search</a> before posting!<br>
>>> Please don't post (un)subscribe requests to the list. Use the<br>
>>> www interface or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>
>>> Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
>>><br>
><br>
> --<br>
> Best Regards,<br>
> Alexey 'Alexxy' Shvetsov<br>
> Petersburg Nuclear Physics Institute, Russia<br>
> Department of Molecular and Radiation Biophysics<br>
> Gentoo Team Ru<br>
> Gentoo Linux Dev<br>
> mailto:<a href="mailto:alexxyum@gmail.com">alexxyum@gmail.com</a><br>
> mailto:<a href="mailto:alexxy@gentoo.org">alexxy@gentoo.org</a><br>
> mailto:<a href="mailto:alexxy@omrb.pnpi.spb.ru">alexxy@omrb.pnpi.spb.ru</a><br>
> --<br>
> gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br>
> <a href="http://lists.gromacs.org/mailman/listinfo/gmx-users" target="_blank">http://lists.gromacs.org/mailman/listinfo/gmx-users</a><br>
> Please search the archive at<br>
> <a href="http://www.gromacs.org/Support/Mailing_Lists/Search" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/Search</a> before posting!<br>
> Please don't post (un)subscribe requests to the list. Use the www interface<br>
> or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>
> Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
><br>
--<br>
gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br>
<a href="http://lists.gromacs.org/mailman/listinfo/gmx-users" target="_blank">http://lists.gromacs.org/mailman/listinfo/gmx-users</a><br>
Please search the archive at <a href="http://www.gromacs.org/Support/Mailing_Lists/Search" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/Search</a> before posting!<br>
Please don't post (un)subscribe requests to the list. Use the<br>
www interface or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>
Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
</div></div></blockquote></div><br>