<div dir="ltr"><div dir="ltr">On Thu, Sep 28, 2023 at 4:09 PM Jaysaval, Piyoosh via petsc-dev <<a href="mailto:petsc-dev@mcs.anl.gov">petsc-dev@mcs.anl.gov</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="msg-8811726290652265571">





<div lang="EN-US" style="overflow-wrap: break-word;">
<div class="m_-4118899637568871307WordSection1">
<p class="MsoNormal">Hello PETSc developers,<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal">I am having some issues with using MUMPS solver after the solution phase from PETSc. I am solving a matrix equation with about 2.17 million DOFs and for 1764 RHSs. MUMPS successfully solves the system for all RHS; however, after the solve
 phase the distributed solution from MUMPS vector/matrix is scattered back to PETSc mpi vector (done within PETSc) and this is where I am getting the error.
<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal">FYI, when I use 1323 RHSs, there is no issue. Moreover, I had to use v3.18.6 (or lower) because of some compiling issue with v3.19+ and SuperLU_DIST on our cluster with older intel mpi.
<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal">Any help is greatly appreciated. Thanks.</p></div></div></div></blockquote><div><br></div><div>Have you configured with 64-bit indices?</div><div><br></div><div>  Thanks,</div><div><br></div><div>     Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="msg-8811726290652265571"><div lang="EN-US" style="overflow-wrap: break-word;"><div class="m_-4118899637568871307WordSection1"><p class="MsoNormal"></p>
<p class="MsoNormal">Piyoosh<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal">Here’s is the error message I am getting:<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">Entering ZMUMPS 5.5.1 from C interface with JOB, N =
</span><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">3 </span><span class="m_-4118899637568871307apple-converted-space">   
</span><span class="m_-4118899637568871307s1">2165687</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">      </span><span class="m_-4118899637568871307s1">executing #MPI =
</span><span class="m_-4118899637568871307apple-converted-space">    </span><span class="m_-4118899637568871307s1">63 and #OMP =</span><span class="m_-4118899637568871307apple-converted-space">     
</span><span class="m_-4118899637568871307s1">1</span><u></u><u></u></p>
<p class="m_-4118899637568871307p2"><u></u> <u></u></p>
<p class="m_-4118899637568871307p2"><u></u> <u></u></p>
<p class="m_-4118899637568871307p2"><u></u> <u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">****** SOLVE & CHECK STEP ********</span><u></u><u></u></p>
<p class="m_-4118899637568871307p2"><u></u> <u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">GLOBAL STATISTICS PRIOR SOLVE PHASE ...........</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Number of right-hand-sides</span><span class="m_-4118899637568871307apple-converted-space">                   
</span><span class="m_-4118899637568871307s1">=</span><span class="m_-4118899637568871307apple-converted-space">        </span>
<span class="m_-4118899637568871307s1">1764</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Blocking factor for multiple rhs</span><span class="m_-4118899637568871307apple-converted-space">             
</span><span class="m_-4118899637568871307s1">=</span><span class="m_-4118899637568871307apple-converted-space">          </span>
<span class="m_-4118899637568871307s1">32</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">ICNTL (9)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">1</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (10)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">0</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (11)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">0</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (20)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">1</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (21)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">1</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (30)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">0</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">--- (35)
</span><span class="m_-4118899637568871307apple-converted-space">                                    </span>
<span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">          </span><span class="m_-4118899637568871307s1">0</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">** Rank of processor needing largest memory in solve
</span><span class="m_-4118899637568871307apple-converted-space">    </span><span class="m_-4118899637568871307s1">: </span><span class="m_-4118899637568871307apple-converted-space">       
</span><span class="m_-4118899637568871307s1">5</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">** Space in MBYTES used by this processor for solve</span><span class="m_-4118899637568871307apple-converted-space">     
</span><span class="m_-4118899637568871307s1">:</span><span class="m_-4118899637568871307apple-converted-space">      </span>
<span class="m_-4118899637568871307s1">1173</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">** Avg. Space in MBYTES per working proc during solve</span><span class="m_-4118899637568871307apple-converted-space">   
</span><span class="m_-4118899637568871307s1">: </span><span class="m_-4118899637568871307apple-converted-space">      </span>
<span class="m_-4118899637568871307s1">820</span><u></u><u></u></p>
<p class="m_-4118899637568871307p2"><span class="m_-4118899637568871307apple-converted-space"> </span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Leaving solve with ...</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Time to build/scatter RHS</span><span class="m_-4118899637568871307apple-converted-space">       
</span><span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">      </span>
<span class="m_-4118899637568871307s1">0.130768</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Time in solution step (fwd/bwd)</span><span class="m_-4118899637568871307apple-converted-space"> 
</span><span class="m_-4118899637568871307s1">=</span><span class="m_-4118899637568871307apple-converted-space">      </span>
<span class="m_-4118899637568871307s1">41.264175</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">.. Time in forward (fwd) step
</span><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">       
</span><span class="m_-4118899637568871307s1">11.261921</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">.. Time in ScaLAPACK root
</span><span class="m_-4118899637568871307apple-converted-space">      </span><span class="m_-4118899637568871307s1">=</span><span class="m_-4118899637568871307apple-converted-space">         
</span><span class="m_-4118899637568871307s1">3.584752</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space">  </span><span class="m_-4118899637568871307s1">.. Time in backward (bwd) step</span><span class="m_-4118899637568871307apple-converted-space"> 
</span><span class="m_-4118899637568871307s1">= </span><span class="m_-4118899637568871307apple-converted-space">        </span>
<span class="m_-4118899637568871307s1">26.515026</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Time to gather solution(cent.sol)=
</span><span class="m_-4118899637568871307apple-converted-space">      </span><span class="m_-4118899637568871307s1">0.000000</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Time to copy/scale dist. solution=
</span><span class="m_-4118899637568871307apple-converted-space">      </span><span class="m_-4118899637568871307s1">0.724149</span><u></u><u></u></p>
<p class="m_-4118899637568871307p2"><u></u> <u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307apple-converted-space"> </span><span class="m_-4118899637568871307s1">Elapsed time in solve driver=</span><span class="m_-4118899637568871307apple-converted-space">     
</span><span class="m_-4118899637568871307s1">42.3461<u></u><u></u></span></p>
<p class="m_-4118899637568871307p1"><u></u> <u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: --------------------- Error Message --------------------------------------------------------------</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: Argument out of range</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: Scatter indices in iy are out of range</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: See <a href="https://petsc.org/release/faq/" target="_blank">
https://petsc.org/release/faq/</a> for trouble shooting.</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: Petsc Release Version 3.18.6, unknown</span><span class="m_-4118899637568871307apple-converted-space"> </span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: /people/jays242/softwares/pgemini-em/pgemini/src/pgemini on a arch-linux-intel-opt-v3.18.6 named dc230.local by jays242 Thu Sep 28 10:44:51 2023</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: Configure options PETSC_ARCH=arch-linux-intel-opt-v3.18.6 --with-debugging=0 COPTFLAGS=-O3 CXXOPTFLAGS=-O3 FOPTFLAGS=-O3 --with-cc=mpiicc --with-cxx=mpiicpc --with-fc=mpiifort --with-blaslapack-dir=/share/apps/intel/2020u4/compilers_and_libraries_2020.4.304/linux/mkl/lib/intel64
 -with-scalar-type=complex --download-mumps --download-metis --with-openmp --download-parmetis --download-superlu_dist --with-scalapack-lib="-L/share/apps/intel/2020u4/compilers_and_libraries_2020.4.304/linux/mkl/lib/intel64 -lmkl_scalapack_lp64 -lmkl_blacs_intelmpi_lp64"</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: #1 VecScatterCreate() at /qfs/people/jays242/softwares/pgemini-em/petsc-intel/src/vec/is/sf/interface/vscat.c:736</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: #2 MatMatSolve_MUMPS() at /qfs/people/jays242/softwares/pgemini-em/petsc-intel/src/mat/impls/aij/mpi/mumps/mumps.c:1449</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: #3 MatMatTransposeSolve_MUMPS() at /qfs/people/jays242/softwares/pgemini-em/petsc-intel/src/mat/impls/aij/mpi/mumps/mumps.c:1506</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[23]PETSC ERROR: #4 MatMatTransposeSolve() at /qfs/people/jays242/softwares/pgemini-em/petsc-intel/src/mat/interface/matrix.c:3789</span><u></u><u></u></p>
<p class="m_-4118899637568871307p1"><span class="m_-4118899637568871307s1">[24]PETSC ERROR: --------------------- Error Message ---------------</span><u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
</div>

</div></blockquote></div><br clear="all"><div><br></div><span class="gmail_signature_prefix">-- </span><br><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener</div><div><br></div><div><a href="http://www.cse.buffalo.edu/~knepley/" target="_blank">https://www.cse.buffalo.edu/~knepley/</a><br></div></div></div></div></div></div></div></div>