Brecht Van Lommel 3bf175f270 Cycles OSL: image texture lookup optimization, acquire the per thread handle ...

for texture system in advance. Patch by Martijn Berger, with some tweaks.

There was about a 10% performance improvement on OS X in my tests with the
images.blend test file. This may be less on other platforms because OS X has
particularly slow mutex locks.

2013-08-05 12:49:15 +00:00

..

closure

Cycles / SSS:

2013-08-03 13:12:09 +00:00

osl

Cycles OSL: image texture lookup optimization, acquire the per thread handle

2013-08-05 12:49:15 +00:00

shaders

Cycles / HSV Separator and Combine node:

2013-07-31 21:27:48 +00:00

svm

Code cleanup / Cycles:

2013-08-05 01:24:41 +00:00

CMakeLists.txt

Cycles / Vector Transform node:

2013-07-31 21:18:23 +00:00

kernel_accumulate.h

Cycles:

2013-08-03 21:45:57 +00:00

kernel_bvh_traversal.h

Cycles: optimized SSE BVH traversal now also works with SSE2 CPUs, so all the

2013-06-19 17:54:26 +00:00

kernel_bvh.h

Cycles: optimization for BVH traveral on CPU's with SSE3, using code from Embree.

2013-06-18 09:36:06 +00:00

kernel_camera.h

Fix #36053: slow GPU render with panorama camera + depth of field.

2013-07-10 17:25:52 +00:00

kernel_compat_cpu.h

Code cleanup: avoid some warnings due to implicit uint/int/float/double conversion.

2013-06-07 16:06:17 +00:00

kernel_compat_cuda.h

Cycles: initial subsurface multiple scattering support. It's not working as

2013-04-01 20:26:52 +00:00

kernel_compat_opencl.h

Code cleanup: cycles

2013-06-26 23:29:33 +00:00

kernel_curve.h

Cycles:

2013-06-04 17:20:00 +00:00

kernel_differential.h

Fix #35207: addition to previous fix to avoid OSL getting uninitialized

2013-05-03 21:34:51 +00:00

kernel_displace.h

Cycles / Ray Depth:

2013-07-31 20:30:37 +00:00

kernel_emission.h

Cycles / Ray Depth:

2013-07-31 20:30:37 +00:00

kernel_film.h

Cycles:

2013-05-14 21:18:20 +00:00

kernel_globals.h

Code cleanup: avoid some warnings due to implicit uint/int/float/double conversion.

2013-06-07 16:06:17 +00:00

kernel_jitter.h

Cycles: prepare to make CUDA 5.0 the official version we use

2013-06-19 17:54:23 +00:00

kernel_light.h

Cycles:

2013-08-03 21:45:57 +00:00

kernel_math.h

Cycles render engine, initial commit. This is the engine itself, blender modifications and build instructions will follow later.

2011-04-27 11:58:34 +00:00

kernel_montecarlo.h

Cycles:

2013-06-14 14:29:00 +00:00

kernel_object.h

Cycles / Vector Transform node:

2013-07-31 21:18:23 +00:00

kernel_passes.h

Cycles / SSS:

2013-08-03 13:12:09 +00:00

kernel_path.h

Cycles / SSS:

2013-08-03 13:12:09 +00:00

kernel_primitive.h

code cleanup: remove some paranoid checks which would have crashed anyway earlier on.

2013-01-20 14:50:50 +00:00

kernel_projection.h

Cycles:

2013-06-14 14:29:00 +00:00

kernel_random.h

Cycles / CMJ:

2013-07-23 16:23:30 +00:00

kernel_shader.h

Cycles / SSS:

2013-08-03 13:12:09 +00:00

kernel_sse2.cpp

Code cleanup: cycles

2013-06-26 23:29:33 +00:00

kernel_sse3.cpp

Cycles:

2013-06-27 00:03:48 +00:00

kernel_subsurface.h

Cycles / SSS:

2013-08-03 13:12:09 +00:00

kernel_textures.h

Cycles / GPU Image Textures:

2013-06-20 15:14:14 +00:00

kernel_triangle.h

Cycles Hair: refactoring to support generic attributes for hair curves. There

2013-01-03 12:08:54 +00:00

kernel_types.h

Cycles / OpenCL:

2013-08-04 12:40:46 +00:00

kernel.cl

Cycles OpenCL: make displacement and world importance sampling work.

2013-06-21 13:05:08 +00:00

kernel.cpp

Cycles:

2013-05-14 21:18:20 +00:00

kernel.cu

Cycles:

2013-05-14 21:18:20 +00:00

kernel.h

Cycles:

2013-05-14 21:18:20 +00:00

SConscript

Cycles: update build configurations to include CUDA sm_35 architecture. When using

2013-06-20 13:10:47 +00:00