<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> Please try the branch balay/slu-without-omp-3 It is in MR <a href="https://gitlab.com/petsc/petsc/-/merge_requests/4635" class="">https://gitlab.com/petsc/petsc/-/merge_requests/4635</a><div class=""><br class=""></div><div class=""><br class=""><div><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="">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="">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"><configure.log></span></div></blockquote></div><br class=""></div></body></html>