Sergey Sharybin dde40989f3 Cycles: Store shadow intersections in the kernel globals ... Seems CUDA failed to de-duplicate the array across multiple inlined versions of the shadow_blocked(). Helped it a bit with that now. Gives about 100MB memory improvement on a scenes after previous commit and brings up memory "regression" to only 100MB comparing to the master branch now.		2017-02-08 14:00:48 +01:00
..
cpu	Cycles: Enable SSE math optimization for AVX kernels	2016-10-25 16:10:47 +02:00
cuda	Cycles: Store shadow intersections in the kernel globals	2017-02-08 14:00:48 +01:00
opencl	Cycles: OpenCL 3d textures support.	2016-10-22 23:49:29 +02:00