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 operating system (and requires a specific C++ IDE, see #4).
Would it be possible for you to break this dependency?
I realize that is a rather tall order for C#, which is rather Windows-centric, so this might be a disguised request to port this to another language, but it would be what I would need to use CudaPAD.
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).
Your source seems to run well against the 9.1 nvcc toolkit. I see that you had mentioned in your readme that you'd like, one day, to be able run the code against a card to get timing results. That would be helpful but I can imagine would take a bit of work.
I was thinking that it also might be useful to display the clock cycles required for each operation in the PTX or SASS. I was wondering if you are aware of any reference or source for this type of information?