https://github.com/pkestene/cuda_mpi_autotools_proj_template
A template project for CUDA+MPI with autotools build system
https://github.com/pkestene/cuda_mpi_autotools_proj_template
automake autotools cuda cuda-mpi mpi
Last synced: 8 months ago
JSON representation
A template project for CUDA+MPI with autotools build system
- Host: GitHub
- URL: https://github.com/pkestene/cuda_mpi_autotools_proj_template
- Owner: pkestene
- License: gpl-2.0
- Created: 2014-10-28T11:27:44.000Z (over 11 years ago)
- Default Branch: master
- Last Pushed: 2019-11-08T13:26:34.000Z (over 6 years ago)
- Last Synced: 2024-12-18T17:34:11.220Z (over 1 year ago)
- Topics: automake, autotools, cuda, cuda-mpi, mpi
- Language: M4
- Size: 16.6 KB
- Stars: 4
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# cuda_mpi_autotools_proj_template
A template project for CUDA+MPI with autotools build system
## Build for the first time
### Run autogen.sh script.
> ./autogen.sh
It will create all autotools related files.
### Run configure
> ./configure --with-cuda=$CUDA_ROOT --enable-mpi
where CUDA_ROOT is an environment variable set to the location of the CUDA toolkit (e.g. /usr/local/cuda-6.5)
### Run make
This will build an executable src/testHelloMpiCuda.
### Start application
You can run it on a multi-GPU cluster with
> mpirun -np N_PROC_MPI ./testHelloMpiCuda
## Reference
For a detailled discussion about coupling CUDA and MPI (initialize CUDA context before/after MPI_Init), see the following references:
- https://github.com/parallel-forall/code-samples/tree/master/posts/cuda-aware-mpi-example
- http://www.open-mpi.org/faq/?category=running#mpi-cuda-support