Open eyalroz opened 3 years ago
I don't see a beautiful way to break the windows dependancy on this. I just checked and Cuda's compiler nvcc.exe can use either gcc(with g++) on Linux or cl.exe (part of visual studio) - so basically the large toolkit setups are needed that I can tell. I think the only way to get this to work would be to have the code compiled on a online api or some kind of portable Linux or windows container.
This seems like a great app (which BTW NVIDIA itself should have really released itself independently of the source view in NSight Compute). However - it is limited to a single, specific C++ IDE.
Would it be possible for you to break this dependency?
Specifrically, if you could write a valid
CMakeLists.txt
for CudaPAD, that would do the trick. (And CMake can generate SLN files, so it shouldn't really hamper the user of MSVS to build it).