Files
blender/intern
Thomas Dinges ad0a3de3ce Cycles / OpenCL: Let the OpenCL runtime determine its optimal work-group size automatically, by passing a NULL pointer here.
This is recommended in the Intel OpenCL optimization docs (http://software.intel.com/en-us/vcsource/samples/optimizing-opencl) and I can confirm a small performance increase here (1-2% on nVidia OpenCL, up to 8% on Intel OpenCL).
2013-12-24 20:20:57 +01:00
..
2013-11-29 15:13:12 -05:00
2013-11-29 15:13:12 -05:00
2013-11-05 04:32:51 +00:00