unable to build cuda samples (cuda 7.0) on linux with clang

Hi all,

Im trying to build cuda samples version 7.0 on linux using clang. Cuda 5.5, 6.0, 6.5 can be successfully built with clang, but when im trying to build 7.0 samples - the following error appears:
HOST_COMPILER=/usr/local/bin/clang++
TARGET_OS=linux
TARGET_ARCH=x86_64
HOST_ARCH=x86_64
“/usr/local/cuda-7.0”/bin/nvcc -ccbin /usr/local/bin/clang++ -I…/…/common/inc -m64 -Xcompiler -arch -Xcompiler x86_64 -gencode arch=compute_20,code=sm_20 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_52,code=compute_52 -o simplePrintf.o -c simplePrintf.cu
nvcc fatal : Host compiler targets unsupported OS.
make: *** [simplePrintf.o] Error 1

Any help would be appreciated.
Thanks.

clang isn’t a supported compiler on linux for CUDA.

You can discover the supported configurations here:

https://docs.nvidia.com/cuda/cuda-getting-started-guide-for-linux/index.html#system-requirements