<body>
- <h1>Installing deal.II with CUDA</h1>
+ <h1>Installing deal.II with CUDA</h1>
<p>
To compile and run CUDA code, you need a CUDA-enabled GPU, appropriate
-DDEAL_II_CUDA_FLAGS="-arch=sm_60"
</pre>
- <code>-DDEAL_II_CUDA_FLAGS_DEBUG</code> and
+ <code>-DDEAL_II_CUDA_FLAGS_DEBUG</code> and
<code>-DDEAL_II_CUDA_FLAGS_RELEASE</code> are also available if you want
a finer control on the CUDA flags. The CUDA compiler and the
- CUDA toolkit root directory can be set using
- <code>-DDEAL_II_CUDA_COMPILER</code> and
+ CUDA toolkit root directory can be set using
+ <code>-DDEAL_II_CUDA_COMPILER</code> and
<code>-DDEAL_II_CUDA_TOOLKIT_ROOT_DIR</code>.
Finally, the CUDA host compiler is the same as the C++ compiler
by default, but can be changed using CUDA flags as well.
</p>
+ <p>
+ In order to enable MPI Cuda support (provided that your MPI library
+ supports it) configure with:
+ <pre>
+
+ -DDEAL_II_WITH_CUDA=ON
+ -DDEAL_II_WITH_MPI=ON
+ -DDEAL_II_MPI_WITH_CUDA_SUPPORT=ON
+ </pre>
+ This configuration option is currently not autodetected.
+ </p>
+
</body>
-
</html>
projects / dealii.git / commitdiff