[PyCuda] threading with permanent context

[Nicholas Tung]

Do you need to recompile the kernel because of application requirements or
because there's some weird caching bug? It should be fast to load cached
kernels. Also, there's a JIT compiler if you can make the necessary
modifications in PTX. I haven't used it though.

Native support for multi-threaded garbage collection (it is calling the free
function) would be cool, though perhaps not a high priority.

regards,
Nicholas
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.tiker.net/pipermail/pycuda/attachments/20090513/f17905ab/attachment-0001.htm>