everything seems to be OK (so segfault), but instead of solution I get: ERROR in MPI_ALLREDUCE, DATATYPE= 7 (see listing below)
Any idea what could be the reason?
Thanks in advance for any hint.
Best reagrds Artur Pozniak
address@hidden /usr/bin/mpirun -np 4 ./elastostatic elastostatic.param MESH_FILE=structured:GT="GT_PK(2,1)";SIZES=[1,1];NOISED=0 FEM_TYPE=FEM_PK(2,1)
INTEGRATION=IM_TRIANGLE(6) MESH_FILE=structured:GT="GT_PK(2,1)";SIZES=[1,1];NOISED=0 FEM_TYPE=FEM_PK(2,1) INTEGRATION=IM_TRIANGLE(6) Trace 1 in elastostatic.cc, line 479: Running parallelized Getfem level 2
MESH_FILE=structured:GT="GT_PK(2,1)";SIZES=[1,1];NOISED=0 FEM_TYPE=FEM_PK(2,1) INTEGRATION=IM_TRIANGLE(6) MESH_FILE=structured:GT="GT_PK(2,1)";SIZES=[1,1];NOISED=0 FEM_TYPE=FEM_PK(2,1) INTEGRATION=IM_TRIANGLE(6)
temps creation maillage 4.16833 temps creation maillage 4.22139 Selecting Neumann and Dirichlet boundaries Selecting Neumann and Dirichlet boundaries temps creation maillage 4.51347 temps creation maillage 4.56164
Selecting Neumann and Dirichlet boundaries Selecting Neumann and Dirichlet boundaries enumerate dof time 10.2421 temps init 15.4047 begining resol Number of dof for u: 502002 enumerate dof time 10.5826
temps init 15.7118 begining resol Number of dof for u: 502002 enumerate dof time 10.4441 temps init 15.8901 Total number of variables : 502002 Total number of variables : 502002 enumerate dof time 10.9423
temps init 16.422 begining resol Number of dof for u: 502002 Partition time 0.764749 Total number of variables : 502002 begining resol Number of dof for u: 502002 Partition time 0.854165 Total number of variables : 502002
Partition time 0.780813 Partition time 0.748922 Trace 2 in ../src/getfem/getfem_modeling.h, line 819: Assembling stiffness matrix for linear elasticity Trace 2 in ../src/getfem/getfem_modeling.h, line 1796: Assembling Dirichlet constraints, version 7
Trace 3 in ../src/getfem/getfem_assembling.h, line 1055: Simplification of the Dirichlet condition Trace 2 in ../src/getfem/getfem_modeling.h, line 1113: Assembling a source term Trace 2 in ../src/getfem/getfem_modeling.h, line 1227: Assembling a source term
ERROR in MPI_ALLREDUCE, DATATYPE= 7 ERROR in MPI_ALLREDUCE, DATATYPE= 7 ERROR in MPI_ALLREDUCE, DATATYPE= 7 ERROR in MPI_ALLREDUCE, DATATYPE= 7
[Prev in Thread]
Current Thread
[Next in Thread]
[Getfem-users] parallel version with latest openmpi,
Artur Poźniak<=