MueLu_UnitTestsTpetra_MPI_4 failing (timeout) in ATDM cuda builds on waterman
Created by: fryeguy52
CC: @trilinos/muelu , @srajama1 (Trilinos Linear Solvers Product Lead), @bartlettroscoe
Next Action Status
Duplicate of #3491 (closed) which was closed on 9/27/2018.
Description
As shown in this query the test:
- MueLu_UnitTestsTpetra_MPI_4
is failing in the builds:
- Trilinos-atdm-waterman-cuda-9.2-opt
- Trilinos-atdm-waterman-cuda-9.2-debug
In the cdash results for yesterday we can see that this test on cuda builds is taking 6+ minutes to complete and on non-cuda builds completes in less than 90 sec. Waterman is the only platform where it hit the timeout but others are very close. for example, one build on ride
took 9:49 yesterday.
Steps to Reproduce
One should be able to reproduce this failure on the machine waterman as described in:
More specifically, the commands given for the system waterman are provided at:
The exact commands to reproduce this issue should be:
$ cd <some_build_dir>/
$ source $TRILINOS_DIR/cmake/std/atdm/load-env.sh cuda-debug
$ cmake \
-GNinja \
-DTrilinos_CONFIGURE_OPTIONS_FILE:STRING=cmake/std/atdm/ATDMDevEnv.cmake \
-DTrilinos_ENABLE_TESTS=ON -DTrilinos_ENABLE_MueLu=ON \
$TRILINOS_DIR
$ make NP=20
$ bsub -x -Is -n 20 ctest -j20