<div dir="ltr"><div class="gmail_extra"><div><div class="gmail_signature">On Thu, Nov 26, 2015 at 8:21 PM, Vedran Miletić <span dir="ltr"><<a href="mailto:rivanvx@gmail.com" target="_blank">rivanvx@gmail.com</a>></span> wrote:<br></div></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><span class="">2015-11-26 20:07 GMT+01:00 Szilárd Páll <<a href="mailto:pall.szilard@gmail.com">pall.szilard@gmail.com</a>>:<br>
> Hi,<br>
><br>
> Besides FPGA folks, what about Apple, embedded and mobile platforms<br>
> (Qualcomm, ARM, Samsung, etc.)?<br>
><br>
> I'm not sure Intel is totally uninterested. They've just moved out again<br>
> their OpenCL SDK form the silly bundle they had before in the latest release<br>
> AFAIK because people complained.<br>
><br>
<br>
</span>On a non-HPC side, there is also Beignet which, from what I hear,<br>
should be pretty stable.<br>
<br>
> NVIDIA: no comment.<br>
><br>
<br>
Actually, they have improved in this regard. They now support OpenCL<br>
1.2 [1] </blockquote><div><br></div><div>Yeah. I'm still not buying that they don't have enough request for OpenCL support to put a guy or two on it and</div><div>i) implement standards in a timely fashion</div><div>ii) fix bugs that render their runtime useless for most intents and purposes (e.g. the blocking clEnqueueNDRangeKernel, a ~6 years old bug that we have observed recently too [1] is just insane).</div><div><br></div><div>And let me quote someone else with controversial claims:</div><div><a href="https://twitter.com/jrprice89/status/667466444355993600">https://twitter.com/jrprice89/status/667466444355993600</a></div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">and they are willing to fund OpenCL-based teaching and<br>
research programs; they have rebranded their academic programs from<br>
CUDA Teaching Center to GPU Education Center etc.<br></blockquote><div><br></div><div>I did not know about it, kudos for that. </div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<span class=""><br>
> HIP and CUDA support seems like a desperate move from AMD to lower the<br>
> barrier of entry and make things (seem) easier. Attracting dev/user interest<br>
> to stay afloat is crucial for them. It would however be a major mistake for<br>
> AMD to move away from OpenCL, I think - unless they want to shoot themselves<br>
> in the foot by encouraging people to only write CUDA kernels for AMD. Still<br>
> need to look into this closer to understand what the direction is.<br>
><br>
<br>
</span>I agree completely. I hope they are aware that being completely open<br>
source is their (only?) big advantage, because stability, performance,<br>
and performance per watt are lacking.<br></blockquote><div><br></div><div>I mostly agree. Open source could be a way to gain traction and advantage. </div><div><br></div><div>However, there was a window for AMD to gain some traction - sadly past tense as now it's becoming too late unless Pascal slips and miracles happen. Their raw DP (and in some cases SP) flop rate is better on the latest FirePro GPUs and the new Maxwell surprise Teslas can't compete with that. COmbine that with 32 GB/board, is something that NVIDIA does not have.</div><div><br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<span class=""><br>
> Overall, I feel like this is the time to not take the back seat. Rather than<br>
> letting others decide whether it's going to be open standards or vendor<br>
> lock-in that defines the low-level accelerator programming for the coming<br>
> years I feel like we, though GROMACS, can show that we care and perhaps can<br>
> make a difference. That's why I wrote the previous mail. Don't get me wrong,<br>
> I do not have the illusion that tomorrow we can just drop CUDA support just<br>
> to make a point. However, providing an a decent alternative based on OpenCL<br>
> and pointing out that we want the open alternative to work as well as the<br>
> closed one does require effort, but it is realistic.<br>
><br>
<br>
</span>Thanks for saying that. GROMACS is an widely used code and we might<br>
have a chance here.<br>
<br></blockquote><div><br></div><div>[1.] <a href="https://forums.khronos.org/showthread.php/5822-non-blocking-call-to-clEnqueueNDRangeKernel">https://forums.khronos.org/showthread.php/5822-non-blocking-call-to-clEnqueueNDRangeKernel</a><br></div><div><br></div><div>Cheers,</div><div>--</div><div>Szilárd<br></div><div><br></div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
Regards,<br>
Vedran Miletic<br>
<br>
[1] <a href="http://www.geeks3d.com/20150326/nvidia-r349-12-graphics-driver-for-linux/" rel="noreferrer" target="_blank">http://www.geeks3d.com/20150326/nvidia-r349-12-graphics-driver-for-linux/</a><br>
<br>
<br>
> Cheers,<br>
<span class=""><font color="#888888">><br>
> --<br>
> Szilárd<br>
</font></span><div class=""><div class="h5"><br>
<br>
--<br>
Vedran Miletić<br>
<a href="http://vedranmileti.ch/" rel="noreferrer" target="_blank">http://vedranmileti.ch/</a><br>
--<br>
Gromacs Developers mailing list<br>
<br>
* Please search the archive at <a href="http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List" rel="noreferrer" target="_blank">http://www.gromacs.org/Support/Mailing_Lists/GMX-developers_List</a> before posting!<br>
<br>
* Can't post? Read <a href="http://www.gromacs.org/Support/Mailing_Lists" rel="noreferrer" target="_blank">http://www.gromacs.org/Support/Mailing_Lists</a><br>
<br>
* For (un)subscribe requests visit<br>
<a href="https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers" rel="noreferrer" target="_blank">https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-developers</a> or send a mail to <a href="mailto:gmx-developers-request@gromacs.org">gmx-developers-request@gromacs.org</a>.</div></div></blockquote></div><br></div></div>