Hello all,
I am getting LogicError from gpuarray.to_gpu_async() for some reason. Code:
import pycuda.autoinit
import pycuda.driver as drv
import pycuda.gpuarray as gpuarray
import numpy
a = numpy.random.randn(400).astype(numpy.float32)
stream = drv.Stream()
a_gpu = gpuarray.to_gpu_async(a, stream=stream)
Gives:
Traceback (most recent call last):
File "t.py", line 10, in <module>
a_gpu = gpuarray.to_gpu_async(a, stream=stream)
File
"/Library/Python/2.6/site-packages/pycuda-0.94-py2.6-macosx-10.6-i386.egg/pycuda/gpuarray.py",
line 628, in to_gpu_async
result.set_async(ary, stream)
File
"/Library/Python/2.6/site-packages/pycuda-0.94-py2.6-macosx-10.6-i386.egg/pycuda/gpuarray.py",
line 103, in set_async
drv.memcpy_htod_async(self.gpudata, ary, stream)
pycuda._driver.LogicError: cuMemcpyHtoDAsync failed: invalid value
System: OSX 10.6.4, Cuda 3.1, Python 2.6, PyCuda 0.94
Synchronous to_gpu() works fine. Does anyone know what's wrong?
Best regards,
Bogdan
_______________________________________________
PyCUDA mailing list
[email protected]
http://lists.tiker.net/listinfo/pycuda
