[PyCUDA] Invalid Context with DeviceMemoryPool & GPUArray

[Bryan Catanzaro]

Hi All -
I recently upgraded to CUDA 3.2 RC, and pulled PyCUDA from git, on my Mac OS X installation (running a 32 bit Python 2.6).
For some reason, trying to create a GPUArray, using pycuda.tools.DeviceMemoryPool.allocate as the allocator, causes an error.
Creating the same GPUArray, using the default allocator, seems to work fine.  Before upgrading CUDA and PyCUDA, creating GPUArrays with the memory pool worked for me.

I've attached a minimal program with this problem.  Has anyone else seen this error?

- bryan

Traceback (most recent call last):
  File "invalid_context.py", line 10, in <module>
    failure = pycuda.gpuarray.GPUArray((10,), numpy.int32, allocator.allocate)
  File "/Users/catanzar/work/pycuda/build/lib.macosx-10.6-i386-2.6/pycuda/gpuarray.py", line 81, in __init__
    self.gpudata = self.allocator(self.size * self.dtype.itemsize)
pycuda._driver.LogicError: cuMemAlloc failed: invalid context





-------------- next part --------------
A non-text attachment was scrubbed...
Name: invalid_context.py
Type: text/x-python-script
Size: 269 bytes
Desc: not available
URL: <http://lists.tiker.net/pipermail/pycuda/attachments/20100929/c1cb7eda/attachment.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 3690 bytes
Desc: not available
URL: <http://lists.tiker.net/pipermail/pycuda/attachments/20100929/c1cb7eda/attachment-0001.bin>