<div dir="ltr"><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">Dear Filippo,</div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">
<br></div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">Thank you for your quick response.</div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">
I recompiled it without magma, that error disappeared and now it works. </div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">But I have another question. I tried to test the perfomance of QE-GPU compared with QE without GPU acceleration. If I understand correctly, my command for run should looks like the following</div>
<div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)"><br></div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">mpirun -np 2 /qe-dir/bin/pw-gpu.x -in input > output</div>
<div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)"><br></div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">And it will start with 2 MPI process and get 2 GPUs on my host. Is it correct?</div>
<div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)"><br></div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">Thanks!</div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)">
<br></div><div class="gmail_default" style="font-family:garamond,serif;font-size:large;color:rgb(0,0,0)"> <strong style="font-size:small;font-family:Verdana,Arial,Helvetica,sans-serif;color:rgb(34,34,34)"><span style="font-family:georgia,palatino">--</span></strong></div>
<p style="font-family:Verdana,Arial,Helvetica,sans-serif;font-size:13px;margin:0px"><span style="font-size:small"><strong><span style="font-family:georgia,palatino">Sincerely yours,</span></strong></span><br><span style="font-size:small"><strong><span style="font-family:georgia,palatino">Alexander G. Kvashnin </span></strong></span></p>
<table border="0" style="font-family:Verdana,Arial,Helvetica,sans-serif;font-size:13px"><tbody><tr><td><div><span style="font-size:small"><strong><span style="font-family:georgia,palatino">=====================================================<br>
PhD Student <br>Moscow Institute of Physics and Technology <a href="http://s.wisestamp.com/links?url=http%3A%2F%2Fmipt.ru%2F&sn=" target="_blank">http://mipt.ru/</a></span></strong></span></div><div><span style="font-size:small"><strong><span style="font-family:georgia,palatino">141700, Institutsky lane 9, Dolgoprudny, Moscow Region, Russia</span></strong></span></div>
</td><td><span style="font-family:georgia,palatino;font-size:x-small"><strong><br></strong></span></td></tr><tr><td><span style="font-size:small"><strong><span style="font-family:georgia,palatino">Junior research scientist<br>
Technological Institute for Superhard <br>and Novel Carbon Materials <a href="http://s.wisestamp.com/links?url=http%3A%2F%2Fwww.tisnum.ru%2F&sn=" target="_blank">http://www.tisnum.ru/</a><a href="http://s.wisestamp.com/links?url=http%3A%2F%2Fwww.ntcstm.troitsk.ru%2F&sn=" target="_blank"><br>
</a>142190, Central'naya St. 7a, Troitsk, Moscow Region, Russia<br>=====================================================</span></strong></span></td><td><span style="font-family:georgia,palatino;font-size:x-small"><strong><br>
</strong></span></td></tr></tbody></table></div><div class="gmail_extra"><br><br><div class="gmail_quote">On 26 March 2014 00:41, Filippo Spiga <span dir="ltr"><<a href="mailto:spiga.filippo@gmail.com" target="_blank">spiga.filippo@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Dear Alexander,<br>
<div class=""><br>
On Mar 25, 2014, at 5:29 AM, Alexander G. Kvashnin <<a href="mailto:agkvashnin@gmail.com">agkvashnin@gmail.com</a>> wrote:<br>
> Dear QE users and developers,<br>
><br>
> Recently I compiled QE-GPU on my system with GPU NVidia Tesla K20Xm.<br>
> I have CUDA ver. 5.5.<br>
> Intel MPI 4.1.3.048<br>
> Intel Compiler 14.0<br>
><br>
> I compiled GPU-QE using the instruction on the website. I downloaded espresso-5.0.2, than downloaded QE-GPU-14.01.0 with patch file. After the patching I type a configuration command:<br>
><br>
> ./configure LAPACK_LIBS=/opt/intel/composer_xe_2013_sp1.2.144/mkl/lib/intel64/libmkl_lapack95_lp64.a --enable-openmp --enable-parallel --enable-cuda --with-gpu-arch=30 --with-cuda-dir=/opt/cuda/5.5 --enable-phigemm --enable-magma<br>
<br>
</div>"--with-phigemm" and "--with-magma" are the correct. i will add a check that, if someone spell those wrong, the configure step will halt completely. I am going to check the website and the README too to verify there is consistency in the instructions.<br>
<br>
I do suggest to do _not_ specify any BLAS/LAPACK/SCALAPACK variable in the configure line but edit the make.sys after!<br>
<div class=""><br>
<br>
<br>
> After successful configuration I compile pw-gpu.x and everything was fine. Then I tried to test the performance of this system compared with common HPC.<br>
> But I have troubles. As I understand commonly 1 process goes to 1GPU, so I need to run 2 MPI processes on my host with 2 GPUs. If I am wrong, please, tell me where? After the start I have the error message:<br>
><br>
> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%<br>
> task # 0<br>
> from cdiaghg : error # 61<br>
> diagonalization (ZHEGV*) failed<br>
> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%<br>
<br>
</div>Probably because MAGMA is used (there should be a message on top of the output). Next version will print a lot of information on top of the file so it is possible to understand how the application has been compiled and what features are active.<br>
<br>
Can you try recompiling using "--without-magma"?<br>
<br>
Thanks<br>
F<br>
<br>
--<br>
Mr. Filippo SPIGA, M.Sc.<br>
<a href="http://www.linkedin.com/in/filippospiga" target="_blank">http://www.linkedin.com/in/filippospiga</a> ~ skype: filippo.spiga<br>
<br>
«Nobody will drive us out of Cantor's paradise.» ~ David Hilbert<br>
<br>
*****<br>
Disclaimer: "Please note this message and any attachments are CONFIDENTIAL and may be privileged or otherwise protected from disclosure. The contents are not to be disclosed to anyone other than the addressee. Unauthorized recipients are requested to preserve this confidentiality and to advise the sender immediately of any error in transmission."<br>
<br>
<br>
<br>
_______________________________________________<br>
Pw_forum mailing list<br>
<a href="mailto:Pw_forum@pwscf.org">Pw_forum@pwscf.org</a><br>
<a href="http://pwscf.org/mailman/listinfo/pw_forum" target="_blank">http://pwscf.org/mailman/listinfo/pw_forum</a><br>
</blockquote></div><br></div>