sandey/blender
1
0
Fork 0
forked from bartvdbraak/blender
Code Pull Requests Activity
cc95172667
blender/intern/cycles/kernel/bvh
History
Brecht Van Lommel a3abb020e3 Fix Cycles CUDA performance on CUDA 8.0. 
Mostly this is making inlining match CUDA 7.5 in a few performance critical
places. The end result is that performance is now better than before, possibly
due to less register spilling or other CUDA 8.0 compiler improvements.

On benchmarks scenes, there are 3% to 35% render time reductions. Stack memory
usage is reduced a little too.

Reviewed By: sergey

Differential Revision: https://developer.blender.org/D2269
2016-10-03 22:15:25 +02:00
..
bvh_nodes.h Fix Cycles CUDA performance on CUDA 8.0. 2016-10-03 22:15:25 +02:00
bvh_shadow_all.h Cycles: Make regular bvh traversal functions close to each other 2016-09-20 16:58:39 +02:00
bvh_subsurface.h Cycles: Tweaks to support CUDA 8 toolkit 2016-08-01 15:54:29 +02:00
bvh_traversal.h Fix Cycles CUDA performance on CUDA 8.0. 2016-10-03 22:15:25 +02:00
bvh_types.h Fix Cycles CUDA performance on CUDA 8.0. 2016-10-03 22:15:25 +02:00
bvh_volume_all.h Cycles: Make regular bvh traversal functions close to each other 2016-09-20 16:58:39 +02:00
bvh_volume.h Cycles: Tweaks to support CUDA 8 toolkit 2016-08-01 15:54:29 +02:00
bvh.h Fix Cycles CUDA performance on CUDA 8.0. 2016-10-03 22:15:25 +02:00
qbvh_nodes.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00
qbvh_shadow_all.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00
qbvh_subsurface.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00
qbvh_traversal.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00
qbvh_volume_all.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00
qbvh_volume.h Cycles: Cleanup file headers 2016-09-29 10:11:40 +02:00