“C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v4.0\bin\nvcc.exe” -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin” -I"C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v4.0\include" -m64 -ptx -arch sm_20 “[path to my kernel]\my_kernel.cu”
“cudafe++.exe” crashes and the command line tells me:
"C:/Program Files (x86)/Microsoft Visual Studio 10.0/VC/include\stddef.h(38) (col. 25): internal error: assertion failed
at: “D:/Bld/rel/gpgpu/toolkit/r4.0/compiler/edg/EDG_4.2/src/il_to_str.c”, line 1364
1 catastrophic error detected in the compilation of “C:/Users/[user]/AppData/Local/Temp/tmpxft_000013a4_00000000-6_my_kernel.cpp4.ii”.
Compilation aborted.
This application has requested the Runtime to terminate it in an unusual way.
Please contact the application’s support team for more information.
When I use the Visual Studio 2008 paths, it works fine.
Is Visual Studio 2010 still not yet supported (opposed to as stated in the webinar), or is this a bug?
Thanks a lot for your answer, but actually this didn’t answer the question.
As I already said, in the webinar mentioned above it was said that Visual Studio 2010 should be fully supported with CUDA 4.0 RC so that one can compile CUDA WITHOUT an VS 2008-compiler!
Anyone knows if this is true and if yes, why the command above does not compile?
The error message indicates an internal compiler error. It would be helpful if you would file a bug for this, attaching a self-contained repro case. Thank you for your help.