- 14 Mar, 2017 40 commits
-
-
Martin Khannouz authored
export tarball. Add check for time in python script. Small change in the timer in the tests (not that much).
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
database from stdout and trace.rec.
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
That way no need of using a file to exchange them. Split the mpi job in two. Change a little bit informations printed in the job.
-
Martin Khannouz authored
-
Martin Khannouz authored
by cerr.
-
Martin Khannouz authored
-
Martin Khannouz authored
Still have to fix memory leak, but it works.
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
So we get average time of executing and test to check if the result is good.
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
When SCALFMM_SIMGRID_TASKNAMEPARAMS was enable, in the m2m mpi, a variable was incremented too soon.
-
Martin Khannouz authored
I know, it's kind of useless, but now it's on the repo.
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
-
Martin Khannouz authored
mapping.
-
Martin Khannouz authored
-
Martin Khannouz authored
Note that some error could appear if there is not enough group in input.
-
Martin Khannouz authored
-
Martin Khannouz authored
Also add the sbatch script that run tests.
-
Martin Khannouz authored
The implicit part reproducing explicit mapping works well. But on the explicit side, it turn out that if all morton indexes ain't used, it segfault. Gotta investigate it.
-
Martin Khannouz authored
File that will be load after by testBlockedImplicitAlgorithm.
-
Martin Khannouz authored
testBlockedImplicitAlgorithm and doesn't require a mapping file anymore. To do it properly, MPI_Init is done in the main and MPI_Finalize in the algorithm destructor.
-
Martin Khannouz authored
-
Martin Khannouz authored
of explicit mpi.
-
Martin Khannouz authored
each level. Note : The constructor is not implemented yet. Just declared.
-
Martin Khannouz authored
It works well when the number of leaves is dividable by the number of mpi process. Else there is some offset.
-