Hi, I just installed PyCUDA, but test_driver.py crashes with the
CompileError: nvcc compilation of /tmp/tmpNht4bp/kernel.cu failed
[command: nvcc --cubin -arch sm_35
[stderr: error in open:
/usr/bin/../nvvm/libdevice/libdevice.compute_35.10.bc No such
file or directory ]
Note the last line- it seems to think my CUDA_ROOT is "/usr/bin/..",
which is clearly incorrect!
All of my CUDA environment variables are set properly (e.g. I'm able
to compile+run the CUDA samples and my own CUDA code without
problems), so my guess is that PyCUDA ignored one or more of these
variables during installation.
I've tried forcing PyCUDA to use the correct CUDA environment
variables during installation, as follows:
sudo ./configure.py --cuda-root=/usr/local/cuda
However, I still encounter the same error as above.
I would be grateful for any tips for how to address this problem.
Happy to provide more information if that would help.
Show replies by date