<div dir="ltr"><div>BTW, you can always use the libsmm generated with a previous version of cp2k for cp2k-2.6. The interface is the same and I don't expect any large improvement in performance.</div><div><br></div><div>Alfio</div><div><br></div><br><br>Il giorno mercoledì 29 ottobre 2014 03:48:46 UTC+1, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin: 0;margin-left: 0.8ex;border-left: 1px #ccc solid;padding-left: 1ex;"><div dir="ltr">Hi Alfio,<br><br>I am trying to build the libsmm in cp2k-2.6 and it looks like there has been some recent commits on that. I am trying to build the libsmm and when I run the tiny1, the pbs jobs run but there are no output files (*.out) generated in the /run_tiny_dnn/output_linux.<wbr>intel/. It looks something is wrong with my setup. I haven't changed any file. Do you have any pointers that comes to the rescue. <br><br>Thanks for your time,<br><br>Abhishek<br><br>On Thursday, October 23, 2014 4:23:20 AM UTC-4, Alfio Lazzaro wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Probably I was too optimistic when I asked you to replace the gfortran with ifort...</div><div>Let me explain the problem. The errors are due to the construct:</div><div><br></div><div>ERROR STOP</div><div><br></div><div>which is inside the file multrec_gen.f90 (lines 288 and 366). This is a 2008 Fortran construct and it appears that neither your ifort nor gfortran versions are supporting it.</div><div>Then there is no way to compile it unless we change the code. I would ask you to restore gfortran as host compiler in the config/linux.intel, and then open the file multrec_gen.f90 and remove the keyword "ERROR" (keep STOP) in the two lines. Try this and see if it fixes the problem.</div><div><br></div><div>I see also that "ERROR STOP" is used once in the file generate.bash file. You can remove from there too.</div><div><br></div><div>Alfio</div><div><br></div><br><br>Il giorno giovedì 23 ottobre 2014 06:54:24 UTC+2, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Thanks for figuring out the issue. I have used ifort instead of gfortran and I still get a different set of errors. <div><br></div><div>During the 3rd step <span style="line-height:18px">./generate -c config/linux.intel -j 20 -t 16 -w pbs small1</span></div><div><span style="line-height:18px"><br></span></div><span style="line-height:18px">These are the set of errors which looks different to the earlier ones :</span><div><span style="line-height:18px"><br>multrec_gen.f90(267): error #5144: Invalid character_kind_parameter. No underscore</span><br><span style="line-height:18px"> </span><span style="line-height:18px">IF (ANY(best_square<1)) ERROR STOP "tiny opts file needs sufficiently many square sizes"</span><br><span style="line-height:18px">------------------------------<wbr>------------------------------<wbr>------------------------------<wbr>---^</span><br><span style="line-height:18px">multrec_gen.f90(267): error #5082: Syntax error, found IDENTIFIER 'STOP' when expecting one of: ( % : . = =></span><br><span style="line-height:18px"> </span><span style="line-height:18px">IF (ANY(best_square<1)) ERROR STOP "tiny opts file needs sufficiently many square sizes"</span><br><span style="line-height:18px">------------------------------<wbr>-----^</span><br><span style="line-height:18px">multrec_gen.f90(331): error #5144: Invalid character_kind_parameter. No underscore</span><br><span style="line-height:18px"> </span><span style="line-height:18px">ERROR STOP "MISSING CASE mult_versions"</span><br><span style="line-height:18px">------------------------------<wbr>----------------^</span><br><span style="line-height:18px">multrec_gen.f90(331): error #5082: Syntax error, found IDENTIFIER 'STOP' when expecting one of: ( % : . = =></span><br><span style="line-height:18px"> </span><span style="line-height:18px">ERROR STOP "MISSING CASE mult_versions"</span><br><span style="line-height:18px">-------------^</span><br><span style="line-height:18px">multrec_gen.f90(267): error #6404: This name does not have a type, and must have an explicit type. </span><span style="line-height:18px"> </span><span style="line-height:18px">[ERROR]</span><br><span style="line-height:18px"> </span><span style="line-height:18px">IF (ANY(best_square<1)) ERROR STOP "tiny opts file needs sufficiently many square sizes"</span><br><span style="line-height:18px">-----------------------------^</span><br><div><p style="text-align:left"><span>compilation aborted for multrec_gen.f90 (code 1)</span></p></div><div><span style="line-height:18px">More info : </span></div><div><span style="line-height:18px">ifort 11.1 </span></div><div><span style="line-height:18px">./generate cleanall is done before building with ifort.</span></div><div><span style="line-height:18px"><br></span></div><div><span style="line-height:18px">Thanks for your help.</span></div><div><br></div><div><span style="line-height:18px">Abhishek <br></span><div><br>On Wednesday, October 22, 2014 4:31:48 AM UTC-4, Alfio Lazzaro wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Ok, thanks. I can reproduce your error and I think I understood its source. </div><div>It turns out that the compiler used for the compilation of the libsmm fortran files (gfortran 4.3 in my case) is the source of the problem.</div><div>I think the easiest solution would be to change inside the file:</div><div><br></div><div>build_libsmm/config/linux.<wbr>intel</div><div><br></div><div>the last line from:</div><div><br></div><div>host_compile="gfortran -O2"</div><div><br></div><div>to</div><div><br></div><div>host_compile="ifort -O2"</div><div><br></div><div>BTW, the error doesn't happen if I use gfortran 4.6.</div><div><br></div><div>I hope this solves your problem.</div><div><br></div><div>Alfio</div><br><br>Il giorno mercoledì 22 ottobre 2014 01:44:25 UTC+2, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Please find the attachment for the tiny summary file. <br><br>Abhishek<br><br>On Tuesday, October 21, 2014 11:10:04 AM UTC-4, Alfio Lazzaro wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Interesting... Then it seems that the problem is in the small1 phase...<div>Could you send me in attachment your tiny summary file? I will check what is wrong...</div><div><br></div><div>Alfio</div><div><div><br></div><div><br><br>Il giorno martedì 21 ottobre 2014 15:24:06 UTC+2, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">I have checked the summary file tiny_gen_optimal_dnn_linux.<wbr>intel.out and it has 9 columns with 13824 lines with no sign of corrupted entries. On the same lines, there are 13824 *.out files in build_libsmm/run_tiny_dnn/<wbr>output_linux.intel.<br><br>It looks like we can rule out that there could be something wrong with the summary file. I guess it would be worth informing that while collecting results using tiny2 some of the *.out files were missing so I had to run the tiny1 again to get the completion and tiny2 went smoothly. I am not sure if this could have triggered this issue. <br><br>let me know what you think on this.<br><br>Thanks,<br>Abhishek<br><br>On Tuesday, October 21, 2014 3:20:03 AM UTC-4, Alfio Lazzaro wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>OK, the files from tiny1 are generated correctly (6 columns is OK for the tiny1 files). The 9 columns are for the summary file generated during the tiny2 phase in the the main directory. Look inside the main directory (build_libsmm) for the file tiny_gen_optimal_dnn_linux.<wbr>intel.out. I suspect that this file has 3 columns (the first 3) in some lines (all lines must have 9 columns). BTW, if you hare using the default configuration for tiny1 matrix dimensions, then you should have 13824 *out files inside build_libsmm/run_tiny_dnn/<wbr>output_linux.intel. You can check it by using</div><div><br></div><div>> ls *.out | wc -l</div><div><br></div><div>The same for the summary file:</div><div><br></div><div>> wc -l tiny_gen_optimal_dnn_linux.<wbr>intel.out</div><div>13824 tiny_gen_optimal_dnn_linux.<wbr>intel.out</div><div><br></div><div>We can have several possible errors:</div><div>1) some of the *.out files are missing or corrupted</div><div>2) the summary file is corrupted</div><div><br></div><div>Let me know what you get from this investigation. Likely the problem is in the summary file...</div><div><br></div><div>Alfio</div><div><br></div><br><br>Il giorno lunedì 20 ottobre 2014 22:54:39 UTC+2, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi Alfio,<br><br>I have looked into the *.out files generated by the tiny1. I didn't see 9 columns in the *.out but instead 6 columns.<br><br> 1 1 1 1 0.441932 2.263<br> 1 1 1 7 0.242963 4.116<br> 1 1 17 1 0.370944 2.696<br> 1 3 1 1 0.249962 4.001<br> 1 3 1 7 0.544917 1.835<br> 1 5 1 1 0.267959 3.732<br> 1 15 1 1 0.498925 2.004<br> 2 1 1 1 0.441932 2.263<br><br>This is the output from a file (tiny_find_xx_xx_xx.out) in /build_libsmm/run_tiny_dnn/<wbr>output_linux.intel/<br>I have modified the pbs.wlm file by getting rid of few options like -lmppwidth and -lmppnppn which were not defined in the PBS for our cluster. <br>I am not sure how to investigate further. Do you have any pointers on how to approach this ?<br><br>Thank for your time. <br><br>Abhishek <br><br>On Monday, October 20, 2014 12:41:23 AM UTC-4, Alfio Lazzaro wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Hello <span style="color:rgb(0,0,0);font-family:georgia,serif;font-size:small;line-height:18px">Abhishek,</span></div><div><span style="color:rgb(0,0,0);font-family:georgia,serif;font-size:small;line-height:18px">could you check if the tiny2 phase is properly producing the tiny file? I mean, the error you are seeing is that the system is not able to read the tiny results during the small1 phase.</span></div><div><font color="#000000" face="georgia, serif" size="2"><span style="line-height:18px">The file should be something similar to:</span></font></div><div><font color="#000000" face="georgia, serif" size="2"><span style="line-height:18px"><br></span></font></div><div><font color="#000000" face="georgia, serif" size="2"><div><span style="line-height:18px">1 1 1 1 1 1 1 0.447362 0.447</span></div><div><span style="line-height:18px">1 1 2 4 1 1 1 0.451188 0.887</span></div><div><span style="line-height:18px">1 1 3 3 1 1 1 0.484057 1.240</span></div><div><span style="line-height:18px">1 1 4 5 1 1 4 0.500210 1.599</span></div><div><span style="line-height:18px">1 1 5 6 1 1 5 0.548113 1.824</span></div><div><span style="line-height:18px">1 1 6 1 1 1 6 0.456724 2.190</span></div><div style="line-height:18px"><br></div><div style="line-height:18px">As you can see there are 9 columns. If you see only 3 (the first three ones) then there is something wrong during tiny1.</div><div style="line-height:18px">The next step would be to investigate if the files *.out inside the tiny1 directory and then output directory are correct (you can post an example of .out file).</div><div style="line-height:18px"><br></div><div style="line-height:18px">Best regards,</div><div style="line-height:18px"><br></div><div style="line-height:18px">Alfio</div><div style="line-height:18px"><br></div></font></div><div><br></div><br><br>Il giorno domenica 19 ottobre 2014 22:03:42 UTC+2, Abhishek Bagusetty ha scritto:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div style="font-family:arial,sans-serif"><div><div><div><div><div><span style="font-family:georgia,serif"><font color="#000000" size="2">Hi Users & Developers,</font></span></div><div><span style="font-family:georgia,serif"><font color="#000000" size="2"><br></font></span></div><div><span style="font-family:georgia,serif"><font color="#000000" size="2">I am trying to build libsmm small matrix multiplication library and got an error while doing the 3rd step.</font></span></div><div><span style="font-family:georgia,serif"><font color="#000000" size="2"><br></font></span></div><div><span style="font-family:georgia,serif"><font color="#000000" size="2">Steps : </font></span></div><div><span style="font-family:georgia,serif"><font color="#000000" size="2">1. </font></span><span style="line-height:18px">./generate -c config/linux.intel -j 100 -t 16 -w pbs tiny1</span></div><div><span style="line-height:18px">2. ./generate -c config/linux.intel tiny2</span></div><div><span style="line-height:18px">3. .</span><span style="line-height:18px">/generate -c config/linux.intel -j 20 -t 16 -w pbs small1</span></div>
<div><font size="1"><span style="font-family:georgia,serif"><font color="#000000"><br></font></span></font></div><div><font size="1"><span style="font-family:georgia,serif"><font color="#000000"><br></font></span></font></div></div></div></div></div></div><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px">multrec_gen.f90:267.29:</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px"> IF (ANY(best_square<1)) ERROR STOP "tiny opts file needs sufficiently many</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px"> 1</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px">Error: Cannot assign to a named constant at (1)</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px">multrec_gen.f90:331.7:</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px"> ERROR STOP "MISSING CASE mult_versions"</span><br><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><span style="font-family:arial,sans-serif;line-height:18px"> 1</span><br><span style="line-height:18px;font-family:arial,sans-serif">Error: Unclassifiable statement at (1)</span><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><blockquote style="margin:0 0 0 40px;border:none;padding:0px"></blockquote><div style="font-family:arial,sans-serif"><p style="text-align:left"><br></p><p style="text-align:left">It would be great, if anyone has any pointers to get a fix on this issue. </p></div><span style="font-size:small;color:rgb(0,0,0);font-family:georgia,serif;line-height:18px">Thanks,</span><br><div style="font-family:arial,sans-serif"><p style="text-align:left"><span style="color:rgb(0,0,0);font-size:small;font-family:georgia,serif">Abhishek</span></p></div><div style="font-family:arial,sans-serif"><div><div><div><div><div><font style="font-family:georgia,serif;font-size:x-small" color="#0000ff">------------------------------</font><font style="font-family:georgia,serif;font-size:x-small" color="#0000ff"><wbr>------------------------------</font><font style="font-family:georgia,serif;font-size:x-small" color="#0000ff"><wbr>------------------------------</font><font style="font-family:georgia,serif;font-size:x-small" color="#0000ff"><wbr>-----------------</font><br></div><div><font size="1"><span style="font-family:georgia,serif"><font color="#0000ff">Abhishek Bagusetty</font><br></span></font></div><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">PhD Student, Computational Modeling & Simulation<br></span></span></font></div><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">Center for Simulation and Modeling<br></span></span></font></div><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">Department of Chemical & Petroleum Engineering<br></span></span></font></div><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">University of Pittsburgh</span><br><span style="color:rgb(0,0,255)">Pittsburgh, PA - 15261</span></span></font></div><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">Office : 920 Benedum Hall<br></span></span></font></div><div style="font-family:arial,sans-serif"><font size="1"><span style="font-family:georgia,serif"><span style="color:rgb(0,0,255)">------------------------------<wbr>------------------------------<wbr>------------------------------<wbr>-----------------</span></span></font></div></div></blockquote></div></blockquote></div></blockquote></div></blockquote></div></blockquote></div></div></div></blockquote></div></blockquote></div></blockquote></div></div></div></div></blockquote></div></blockquote></div></blockquote></div>