>On Mittwoch 21 Oktober 2009, Peter Schmidtke wrote:
>> The kernel has correct access to the data in x,y and writes correctly to
>> out. But dim1 is not 0, why? Normally the code like this should only
fill
>> up dest[0] and nothing else.

>Leave out the drv.In(). "In" means "allocate space on the device and pass
a 
>pointer".

>> Another question a bit disconnected from the first one is, if I allocate
a
>> numpy array with zeros (numpy.zeros(4,dtype="float32")) and I run the
>> kernel without writing actually to all fields in the array dest, why I
have
>> a resulting array that has no 0 element, but some memory crap?

>I'm not sure I understand--a numpy array and a kernel aren't connected in
any 
>way. Is there a copy operation in between?

>Andreas

Thanks, indeed...you answered the second question with your first answer
already ;) Just forgot that the very convenient drv.In & out do all the GPU
allocation...that must be the Python effect ;)

++

Peter


_______________________________________________
PyCUDA mailing list
[email protected]
http://tiker.net/mailman/listinfo/pycuda_tiker.net

Reply via email to