pnorbert
pnorbert
Or setting explicitly the DataTransport to WAN works as well. So it's the default policy that is causing problems when a "normal" C++ code is connecting to a Python/mpi4py code.
https://github.com/ornladios/ADIOS2-Examples/pull/67 now initializes MPI with threads in gray-scott. So the default transport will be MPI on both sides. Nevertheless this is still an issue for any app that uses MPI_Init(),...
agree, making it default on the state of the individual application is not the best idea. It will not work when two apps have different MPI init levels and one...
I came to similar conclusions. Either we could just dump metadata for the timestep being constructed somewhere and use an external tool to merge the metadata pieces and construct a...
Does it work now?
@caitlinross This is not the correct repo. Created a new PR for this in https://github.com/ornladios/ADIOS2-Examples/pull/60
Anyone has any update on this? Is this still an issue with the master branch?
It was the simplest way to "determine" if a dataset is BP5 or BP4 if `mmd.0` existed or not. This bug shows that it is not correct though. The correct...
The tests run fine with current master of MGARD, so I don't think we need to fix anything in adios.
I can't look at this right now but note that the two level aggregation did not help with the attributes, only with meta-meta data. That is if an attribute is...