I’m trying to install clang/llvm with openmp gpu offloading capabilities. I’ve tried installing it on servers with GeForce 2080, Titan Xp2, and the Tesla V100 GPUs. However, when i try to compile the programs with GPU offloading, I keep getting the following error on all three servers mentioned above. Any help is appreciated.
clang-10: error: cannot find libdevice for sm_75. Provide path to different CUDA installation via --cuda-path, or pass -nocudalib to build without linking with libdevice.
clang-10: error: GPU arch sm_75 is supported by CUDA versions between 10.0 and 10.1 (inclusive), but installation at /usr/local/cuda is 7.0. Use --cuda-path to specify a different CUDA install, pass a different GPU arch with --cuda-gpu-arch, or pass --no-cuda-version-check.