Am 17.09.2013 20:20, schrieb Andreas Kloeckner:
Sven Schreiber <[email protected]> writes:
As I said, the same code runs (albeit slowly) on the CPU, if I choose
[0] at the prompt.
AMD implementation bug, I think. (The HD 4000s are on the way to not
being supported by most AMD's CL stuff anyhow.) Just comment out that
check.
Hm, thanks for the quick reply, but I did that and now it's taking
"forever" (in a right-censored sense, it's still running apparently).
But nothing that pyopencl could do here, I guess.
thanks,
sven
_______________________________________________
PyOpenCL mailing list
[email protected]
http://lists.tiker.net/listinfo/pyopencl
