-
Hi,
When running mpirun -np 2 (or higher) mosfit {json_file} -m {model} it crashes. I have mentioned it to Matt in private communication but since the issue still exists I thought to open an issue …
-
When using the `fullydistributed::Triangulation` in combination with a `TransfiniteInterpolationManifold`, an error occurs during the triangulation creation from a description generated by `Triangulat…
-
I followed your guiudance and installed the totally same environments. But I got random results when I run parallel_thresholds.py in32 CPUs many times (about 2/10 are abnormal results). Is it normal o…
-
Title basically says it, I have trained a model using HorovodAllToAllEmbeddings and saved by doingg:
```
de.keras.models.de_save_model(
model,
export_dir,
overwrit…
-
At some point my local preferences got reset from
```toml
[DFTK]
DFTK_threads = 1
[HDF5]
libhdf5 = "/usr/lib/x86_64-linux-gnu/hdf5/openmpi/libhdf5.so"
libhdf5_hl = "/usr/lib/x86_64-linux-gnu/h…
-
It would be good to use community standards rather than home-brew things.
-
The MPI launcher (dmlc-core/tracker/dmlc_tracker/mpi.py) in dmlc-core can not recognize Intel MPI.
It reports ''Unknown MPI Version''
-
MPICH defines the macro `MPI_VERSION` so the plugin should not:
```
In file included from /zhome/academic/HLRS/hlrs/hpcjschu/src/readex/scorep_plugin_x86_energy/src/x86_energy_sync_plugin.cpp:40:…
-
Hi Team,
I am doing noise cross-correlation simulations for a coupled acoustic-elastic media. When I have large no of external source files (60k files, each with 60k time steps), the step where sol…
-
# Problem
If my MPI ranks have a lot of threads, then I have to do:
1. local reduce
2. global allreduce
3. local broadcast
# Proposal
`MPI_Allreduce_init_mt`
then n threads can invoke …