Sergey Sharybin ba8c7d2ba1 Cycles: Use SSE-optimized version of triangle intersection for motion triangles ...

The title says it all actually. Gives up to 10% speedup on test scenes here
on i7-6800K.

Render times on GPU are unreliable here, but there might be some slowdown
caused by watertight nature of intersections.

2017-03-23 17:58:03 +01:00

..

bvh_nodes.h

Cycles: Cleanup, extra semicolon and space

2017-03-10 15:38:30 +01:00

bvh_shadow_all.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

bvh_subsurface.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

bvh_traversal.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

bvh_types.h

Cycles: Use dedicated debug passes for traversed nodes and intersection tests

2017-01-12 13:44:35 +01:00

bvh_volume_all.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

bvh_volume.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

bvh.h

Cycles: Optimize sorting of transparent intersections on CUDA

2017-02-13 18:24:45 +01:00

qbvh_nodes.h

Cycles: Move QBVH near/far offset calculation to an utility function

2016-10-25 15:08:33 +02:00

qbvh_shadow_all.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

qbvh_subsurface.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

qbvh_traversal.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

qbvh_volume_all.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00

qbvh_volume.h

Cycles: Use SSE-optimized version of triangle intersection for motion triangles

2017-03-23 17:58:03 +01:00