Andreas Kloeckner <[email protected]> writes: > I haven't yet figured out what's behind these "out of resources" errors, > but I'll keep poking. I'd be glad to receive clues. On the whole, I find > these results pretty encouraging, and I'd like to get 2013.1 out as soon > as I can (before I get a chance to go back and break stuff again).
I know now what they mean by "out of resources"--they mean "mem object allocation failure" (i.e. deferred failure to allocate global memory): http://devgurus.amd.com/thread/160271 I've fixed a few more issues that I ran into as I was testing today. Cypress appears happy with test_algorithms.py now, while Devastator is still encountering some odd issue in the segmented scan. I'd very much like to hear more test results from other GPUs for the current code in git. (I'd be especially curious about Apple and Intel Ivy Bridge because I can't test those myself.) Andreas _______________________________________________ PyOpenCL mailing list [email protected] http://lists.tiker.net/listinfo/pyopencl
