<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class=""><div class=""></div><div class=""><br class=""></div><div class=""><br class=""><div class=""> <div style="color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-east-asian: normal; font-variant-position: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">---<br class="">Ron Cohen<br class=""><a href="mailto:reco...@gmail.com" class="">reco...@gmail.com</a><br class="">skypename: ronaldcohen</div><div style="color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-east-asian: normal; font-variant-position: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">twitter: @recohen3<br class=""><div class=""><br class=""></div></div><br class="Apple-interchange-newline"><br class="Apple-interchange-newline"> </div> <div><br class=""><blockquote type="cite" class=""><div class="">On Jan 7, 2019, at 5:39 PM, Robert Schade <<a href="mailto:robert...@uni-paderborn.de" class="">robert...@uni-paderborn.de</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div class=""><div class="protected-part"><div class="protected-title">Signed PGP part</div><div class="protected-content">r is automatically private because it is the first iteration variable.<br class="">Every drho(s, i) is only read and written in exactly one loop<br class="">iteration. The statement "COLLAPSE(3)" collapses the three perfectly<br class="">nested loops into one loop. So, IMHO, this code looks ok.<br class="">Best Wishes<br class="">Robert<br class=""><br class=""><br class="">On 07.01.19 14:52, Ronald Cohen wrote:<br class="">> Yes, I agree. I have tried the 2018.05 and the 2019.1 intel<br class="">> compilers. The POPT version runs fine, but the PSMP version fails<br class="">> in the vDW routines. I find things like: in qs_dispersion_nonloc.F<br class="">><br class="">> !$OMP PARALLEL DO DEFAULT(NONE)<span class="Apple-converted-space"> </span> & !$OMP<br class="">> SHARED(ispin,i,n,lo,drho,drho_r)<span class="Apple-converted-space"> </span> & !$OMP<span class="Apple-converted-space"> </span> PRIVATE(s)<br class="">> & !$OMP<span class="Apple-converted-space"> </span> COLLAPSE(3) DO r = 0, n(3)-1 DO q = 0, n(2)-1<br class="">> DO p = 0, n(1)-1 s = r*n(2)*n(1)+q*n(1)+p+1 drho(s, i) = drho(s,<br class="">> i)+drho_r(i, ispin)%pw%cr3d(p+lo(1), q +lo(2), r+lo(3)) END DO END<br class="">> DO END DO !$OMP END PARALLEL DO END DO END DO<br class="">><br class="">> Doesn’t this have to be marked as a reduction? And shouldn’t r, q,<br class="">> p be labeled private? Perhaps this is automatic, but I do not see<br class="">> that said anywhere. Does gnu treat such differently than intel?<br class="">> Just ideas.<br class="">><br class="">> I am currently trying the toolchain, but it is building everything<br class="">> from scratch, including blas, lapack, scalapack etc etc, so will<br class="">> take days.<br class="">><br class="">> Thank you for your help,<br class="">><br class="">> Sincerely,<br class="">><br class="">> Ron<br class="">><br class="">> --- Ron Cohen <a href="mailto:reco...@gmail.com" class="">reco...@gmail.com</a> <<a href="mailto:reco...@gmail.com" class="">mailto:reco...@gmail.com</a>><br class="">> skypename: ronaldcohen twitter: @recohen3<br class="">><br class="">><br class="">><br class="">><br class="">>> On Jan 7, 2019, at 2:16 PM, Robert Schade<br class="">>> <<a href="mailto:robert...@uni-paderborn.de" class="">robert...@uni-paderborn.de</a><br class="">>> <<a href="mailto:robert...@uni-paderborn.de" class="">mailto:robert...@uni-paderborn.de</a>>> wrote:<br class="">>><br class="">>> Building cp2k on Intel Xeon Phi Knights Landing (KNL, not to be<br class="">>> confused with KNC!) is not different from building it on any<br class="">>> other Intel CPU. Hence, I think that the failing regtests point<br class="">>> to an underlying issue. Which exact version of the Intel Compiler<br class="">>> and MKL have you tried? Best Wishes Robert<br class="">>><br class="">>> On 06.01.19 01:59, Ronald Cohen wrote:<br class="">>>> OK—sorry for all the noise. I am trying:<br class="">>>> ./install_cp2k_toolchain.sh --with-elpa=install<br class="">>>> --with-libint=install --with-gcc=install I hate not being able<br class="">>>> to use my intel tools which work for me for everything else<br class="">>>> just fine.<br class="">>>><br class="">>>> Ron<br class="">>>><br class="">>><br class="">>> -- Robert Schade Paderborn Center for Parallel Computing (PC2)<br class="">>> University of Paderborn Warburger Str. 100 D-33098 Paderborn<br class="">>> Germany <a href="mailto:robert...@uni-paderborn.de" class="">robert...@uni-paderborn.de</a><br class="">>> <<a href="mailto:robert...@uni-paderborn.de" class="">mailto:robert...@uni-paderborn.de</a>> +49/(0)5251/60-5393<br class="">>><br class="">>> -- You received this message because you are subscribed to a<br class="">>> topic in the Google Groups "cp2k" group. To unsubscribe from this<br class="">>> topic, visit<br class="">>> <a href="https://groups.google.com/d/topic/cp2k/gzmRqKNt62U/unsubscribe" class="">https://groups.google.com/d/topic/cp2k/gzmRqKNt62U/unsubscribe</a>.<br class="">>> To unsubscribe from this group and all its topics, send an email<br class="">>> to <a href="mailto:cp2k+uns...@googlegroups.com" class="">cp2k+uns...@googlegroups.com</a>. To post to this group, send<br class="">>> email to <a href="mailto:cp...@googlegroups.com" class="">cp...@googlegroups.com</a>. Visit this group at<br class="">>> <a href="https://groups.google.com/group/cp2k" class="">https://groups.google.com/group/cp2k</a>. For more options, visit<br class="">>> <a href="https://groups.google.com/d/optout" class="">https://groups.google.com/d/optout</a>.<br class="">><br class="">> -- You received this message because you are subscribed to the<br class="">> Google Groups "cp2k" group. To unsubscribe from this group and stop<br class="">> receiving emails from it, send an email to<br class="">> <a href="mailto:cp2k+uns...@googlegroups.com" class="">cp2k+uns...@googlegroups.com</a><br class="">> <<a href="mailto:cp2k+uns...@googlegroups.com" class="">mailto:cp2k+uns...@googlegroups.com</a>>. To post to this group,<br class="">> send email to <a href="mailto:cp...@googlegroups.com" class="">cp...@googlegroups.com</a><br class="">> <<a href="mailto:cp...@googlegroups.com" class="">mailto:cp...@googlegroups.com</a>>. Visit this group at<br class="">> <a href="https://groups.google.com/group/cp2k" class="">https://groups.google.com/group/cp2k</a>. For more options, visit<br class="">> <a href="https://groups.google.com/d/optout" class="">https://groups.google.com/d/optout</a>.<br class=""><br class="">--<br class="">Robert Schade<br class="">Paderborn Center for Parallel Computing (PC2)<br class="">University of Paderborn<br class="">Warburger Str. 100<br class="">D-33098 Paderborn<br class="">Germany<br class=""><a href="mailto:robert...@uni-paderborn.de" class="">robert...@uni-paderborn.de</a><br class="">+49/(0)5251/60-5393</div></div><br class=""><iframe class="untrusted-content-test" scrolling="auto" width="200" height="20" style="border:none;display:block;overflow:auto;" data-src="data:text/html;charset=UTF-8;base64,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" sandbox="allow-scripts"></iframe></div></div></blockquote></div><br class=""></div></div></body></html>