A good starting spot would be the tests in CMake itself for CUDA support:
https://gitlab.kitware.com/cmake/cmake/tree/master/Tests/Cuda
https://gitlab.kitware.com/cmake/cmake/tree/master/Tests/CudaOnly
On Thu, Mar 16, 2017 at 1:58 PM, Nick Henderson
wrote:
> Thank you!
Thank you!
Setting:
set(CMAKE_CUDA_FLAGS "-arch compute_30 ${CMAKE_CUDA_FLAGS}")
did the trick.
Is there any documentation or example projects related to the new CUDA
support?
CUDA support is great to have and will simplify my build system! Thank you.
--
View this message in context:
Hi,
The purpose of the cmake_device_link.o is to resolve device side
symbols when doing separable compilation. We do this device linking
step for all CUDA enabled targets as it makes the internal CMake to
logic significantly easier ( no need to propagate another property
through the graph, etc ).
Hello!
I am testing out the CUDA support in CMake 3.8.0-rc2.
When running `make VERBOSE=1` in the build directory, I get a warning
generated related to the GPU architecture flags for nvcc:
```
[ 80%] Linking CUDA device code