<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=""><br class=""></div> Are you sure you have the correct PETSc branch? From configure.log it has<div class=""><br class=""></div><div class=""><div class=""> Defined "VERSION_GIT" to ""v3.16.2-466-g959e1fce86""</div><div class=""> Defined "VERSION_DATE_GIT" to ""2021-12-18 11:17:24 -0600""</div><div class=""> Defined "VERSION_BRANCH_GIT" to ""master""</div><div class=""><br class=""></div><div class="">It should have balay/slu-without-omp-3 for the branch.</div><div class=""><br class=""></div><div class=""><br class=""></div><div><br class=""><blockquote type="cite" class=""><div class="">On Dec 20, 2021, at 10:50 AM, Roland Richter <<a href="mailto:roland.richter@ntnu.no" class="">roland.richter@ntnu.no</a>> wrote:</div><br class="Apple-interchange-newline"><div class="">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" class="">
<div class=""><p class="">In that case it fails with</p><p class=""><i class="">~/Downloads/git-files/petsc/mpich-complex-linux-gcc-demo/externalpackages/git.superlu_dist/SRC/cublas_utils.h:22:10:
fatal error: cublas_v2.h: No such file or directory</i></p><p class="">even though this header is available. I assume some header paths
are not set correctly?</p><p class="">Thanks,</p><p class="">regards,</p><p class="">Roland<br class="">
</p>
<div class="moz-cite-prefix">Am 20.12.21 um 16:29 schrieb Barry
Smith:<br class="">
</div>
<blockquote type="cite" cite="mid:2B3C240D-CEBB-4B45-A60E-ECD1F092B058@petsc.dev" class="">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" class="">
<div class=""><br class="">
</div>
Please try the branch balay/slu-without-omp-3 It is in MR <a href="https://gitlab.com/petsc/petsc/-/merge_requests/4635" class="moz-txt-link-freetext" moz-do-not-send="true">https://gitlab.com/petsc/petsc/-/merge_requests/4635</a>
<div class=""><br class="">
</div>
<div class=""><br class="">
<div class=""><br class="">
<blockquote type="cite" class="">
<div class="">On Dec 20, 2021, at 8:14 AM, Roland Richter
<<a href="mailto:roland.richter@ntnu.no" class="moz-txt-link-freetext" moz-do-not-send="true">roland.richter@ntnu.no</a>>
wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div class=""><p class="">Hei,</p><p class="">I tried to combine CUDA with superlu_dist in
petsc using the following configure-line:</p><p class=""><i class="">./configure
PETSC_ARCH=mpich-complex-linux-gcc-demo
--CC=/opt/intel/oneapi/mpi/2021.5.0/bin/mpicc
--CXX=/opt/intel/oneapi/mpi/2021.5.0/bin/mpicxx
--FC=/opt/intel/oneapi/mpi/2021.5.0/bin/mpifc
--CFLAGS="-mavx2 -march=native -O3"
--CXXFLAGS="-mavx2 -march=native -O3"
--FFLAGS="-mavx2 -march=native -O3"
--CUDAFLAGS=-allow-unsupported-compiler
--CUDA-CXX=g++ --prefix=/opt/petsc
--with-blaslapack=1 --with-mpi=1
--with-scalar-type=complex --download-suitesparse=1
--with-cuda --with-debugging=0 --with-openmp
--download-superlu_dist --force</i></p><p class="">but the configure-step fails with several
errors correlated with CUDA and superlu_dist, the
first one being</p><p class=""><i class="">cublas_utils.c:21:37: error:
‘CUDART_VERSION’ undeclared (first use in this
function); did you mean ‘CUDA_VERSION’?</i><i class=""><br class="">
</i><i class=""> 21 | printf("CUDA version: v
%d\n",CUDART_VERSION);</i><i class=""><br class="">
</i><i class="">
| ^~~~~~~~~~~~~~</i><i class=""><br class="">
</i><i class="">
| CUDA_VERSION</i></p><p class="">Compiling superlu_dist separately works,
though (including CUDA).</p><p class="">Is there a bug somewhere in the
configure-routine? I attached the full configure-log.<br class="">
</p><p class="">Thanks!</p><p class="">Regards,</p><p class="">Roland<br class="">
</p>
</div>
<span id="cid:F1E9B5DB-A92E-4C95-83FD-3F462C695FE9" class=""><configure.log></span></div>
</blockquote>
</div>
<br class="">
</div>
</blockquote>
</div>
<span id="cid:4A36F88D-58F8-40D3-A642-41C361B045C8"><configure.log></span></div></blockquote></div><br class=""></div></body></html>