Discussion:
[PyCUDA] Error running PyCUDA Tests
David A. Markowitz
2015-01-16 17:30:10 UTC
Permalink
Hi, I just installed PyCUDA, but test_driver.py crashes with the
following error:

CompileError: nvcc compilation of /tmp/tmpNht4bp/kernel.cu failed
[command: nvcc --cubin -arch sm_35
-I/usr/local/lib/python2.7/dist-packages/pycuda-2014.1-py2.7-linux-x86_64.egg/pycuda/cuda
kernel.cu]
[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
--cudadrv-lib-dir=/usr/local/cuda/lib64

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.

Thanks,

-David
Andreas Kloeckner
2015-01-17 19:41:42 UTC
Permalink
Post by David A. Markowitz
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
-I/usr/local/lib/python2.7/dist-packages/pycuda-2014.1-py2.7-linux-x86_64.egg/pycuda/cuda
kernel.cu]
/usr/bin/../nvvm/libdevice/libdevice.compute_35.10.bc No such
file or directory ]
This looks like nvcc is unable to find its own parts. Does nvcc work
when called from the command line on a simple CUDA sample? (My guess is
no.)

Andreas

Loading...