Andreas, Thanks for the help. I was using the lastest version of the cuda toolkit but I had an older version of the nvidia driver (195.xxx) which came with Ubuntu but I got the latest version of the nvidia driver and now that function is there!
nm -D /usr/lib/nvidia-current/libcuda.so.1 | grep cuMemAllocPitch_v2 000000000015bc80 T cuMemAllocPitch_v2 ____________ Bryan Absher On Sat, Oct 2, 2010 at 12:01 PM, Andreas Kloeckner <li...@informa.tiker.net> wrote: > Hi Bryan, > > On Fri, 1 Oct 2010 21:10:27 -0700, Bryan Absher <bryan.abs...@gmail.com> > wrote: >> I have heard great things about the pycuda, if only it would run. Here >> is the output to the test_driver.py >> >> $ python ./test_driver.py >> Traceback (most recent call last): >> File "./test_driver.py", line 4, in <module> >> from pycuda.tools import mark_cuda_test >> File >> "/usr/local/lib/python2.6/dist-packages/pycuda-0.94.1-py2.6-linux-x86_64.egg/pycuda/tools.py", >> line 30, in <module> >> import pycuda.driver as cuda >> File >> "/usr/local/lib/python2.6/dist-packages/pycuda-0.94.1-py2.6-linux-x86_64.egg/pycuda/driver.py", >> line 1, in <module> >> from pycuda._driver import * >> ImportError: >> /usr/local/lib/python2.6/dist-packages/pycuda-0.94.1-py2.6-linux-x86_64.egg/pycuda/_driver.so: >> undefined symbol: cuMemAllocPitch_v2 >> >> $ ldd ./_driver.so >> linux-vdso.so.1 => (0x00007fff80f56000) >> libcuda.so.1 => /usr/lib/nvidia-current/libcuda.so.1 >> (0x00007fc378457000) >> libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00007fc378143000) >> libm.so.6 => /lib/libm.so.6 (0x00007fc377ebf000) >> libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00007fc377ca8000) >> libpthread.so.0 => /lib/libpthread.so.0 (0x00007fc377a8b000) >> libc.so.6 => /lib/libc.so.6 (0x00007fc377707000) >> libz.so.1 => /lib/libz.so.1 (0x00007fc3774f0000) >> libdl.so.2 => /lib/libdl.so.2 (0x00007fc3772ec000) >> /lib64/ld-linux-x86-64.so.2 (0x00007fc379030000) > > My suspicion would be that /usr/lib/nvidia-current/libcuda.so.1 is not > the current (3.2) version of libcuda.so. (But it seems you're compiling > against 3.2 headers, which gives you unavailable symbol errors. You can > easily check for a 3.2 libcuda yourself: > > I get: > nm -D /usr/lib/libcuda.so | grep cuMemAllocPitch_v2 > 000000000015c0e0 T cuMemAllocPitch_v2 > > Try > > nm -D /usr/lib/nvidia-current/libcuda.so.1 | grep cuMemAllocPitch_v2 > > If you get empty output, you have an old version. > > HTH, > Andreas > > _______________________________________________ PyCUDA mailing list PyCUDA@tiker.net http://lists.tiker.net/listinfo/pycuda