On Montag 02 Februar 2009, Dan Goodman wrote: > So my question is basically, how can I allocate space on the global > memory using PyCuda, and then copy from this space. I couldn't decide > how to do this from the docs (or even if its possible).
From the Python side: not a problem, just use pycuda.driver.mem_alloc(). From the GPU code side (in a CUDA C function): you can't--allocating memory would require global locking, and that would be pretty awfully slow. > Of course if anyone has another idea for a parallel way to do my > thresholding operation that would also be great! :-) For the given sizes, I think that Ian's idea involving atomics is a really nice one. Andreas
signature.asc
Description: This is a digitally signed message part.
_______________________________________________ PyCuda mailing list [email protected] http://tiker.net/mailman/listinfo/pycuda_tiker.net
