forked from bartvdbraak/blender
7f4479da42
This commit contains all the work related on the AMD megakernel split work which was mainly done by Varun Sundar, George Kyriazis and Lenny Wang, plus some help from Sergey Sharybin, Martijn Berger, Thomas Dinges and likely someone else which we're forgetting to mention. Currently only AMD cards are enabled for the new split kernel, but it is possible to force split opencl kernel to be used by setting the following environment variable: CYCLES_OPENCL_SPLIT_KERNEL_TEST=1. Not all the features are supported yet, and that being said no motion blur, camera blur, SSS and volumetrics for now. Also transparent shadows are disabled on AMD device because of some compiler bug. This kernel is also only implements regular path tracing and supporting branched one will take a bit. Branched path tracing is exposed to the interface still, which is a bit misleading and will be hidden there soon. More feature will be enabled once they're ported to the split kernel and tested. Neither regular CPU nor CUDA has any difference, they're generating the same exact code, which means no regressions/improvements there. Based on the research paper: https://research.nvidia.com/sites/default/files/publications/laine2013hpg_paper.pdf Here's the documentation: https://docs.google.com/document/d/1LuXW-CV-sVJkQaEGZlMJ86jZ8FmoPfecaMdR-oiWbUY/edit Design discussion of the patch: https://developer.blender.org/T44197 Differential Revision: https://developer.blender.org/D1200
100 lines
2.5 KiB
C
100 lines
2.5 KiB
C
/*
|
|
* Copyright 2011-2015 Blender Foundation
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
#ifndef SD_VAR
|
|
#define SD_VAR(type, what)
|
|
#endif
|
|
#ifndef SD_CLOSURE_VAR
|
|
#define SD_CLOSURE_VAR(type, what, max_closure)
|
|
#endif
|
|
|
|
/* position */
|
|
SD_VAR(float3, P)
|
|
/* smooth normal for shading */
|
|
SD_VAR(float3, N)
|
|
/* true geometric normal */
|
|
SD_VAR(float3, Ng)
|
|
/* view/incoming direction */
|
|
SD_VAR(float3, I)
|
|
/* shader id */
|
|
SD_VAR(int, shader)
|
|
/* booleans describing shader, see ShaderDataFlag */
|
|
SD_VAR(int, flag)
|
|
|
|
/* primitive id if there is one, ~0 otherwise */
|
|
SD_VAR(int, prim)
|
|
|
|
/* combined type and curve segment for hair */
|
|
SD_VAR(int, type)
|
|
|
|
/* parametric coordinates
|
|
* - barycentric weights for triangles */
|
|
SD_VAR(float, u)
|
|
SD_VAR(float, v)
|
|
/* object id if there is one, ~0 otherwise */
|
|
SD_VAR(int, object)
|
|
|
|
/* motion blur sample time */
|
|
SD_VAR(float, time)
|
|
|
|
/* length of the ray being shaded */
|
|
SD_VAR(float, ray_length)
|
|
|
|
/* ray bounce depth */
|
|
SD_VAR(int, ray_depth)
|
|
|
|
/* ray transparent depth */
|
|
SD_VAR(int, transparent_depth)
|
|
|
|
#ifdef __RAY_DIFFERENTIALS__
|
|
/* differential of P. these are orthogonal to Ng, not N */
|
|
SD_VAR(differential3, dP)
|
|
/* differential of I */
|
|
SD_VAR(differential3, dI)
|
|
/* differential of u, v */
|
|
SD_VAR(differential, du)
|
|
SD_VAR(differential, dv)
|
|
#endif
|
|
#ifdef __DPDU__
|
|
/* differential of P w.r.t. parametric coordinates. note that dPdu is
|
|
* not readily suitable as a tangent for shading on triangles. */
|
|
SD_VAR(float3, dPdu)
|
|
SD_VAR(float3, dPdv)
|
|
#endif
|
|
|
|
#ifdef __OBJECT_MOTION__
|
|
/* object <-> world space transformations, cached to avoid
|
|
* re-interpolating them constantly for shading */
|
|
SD_VAR(Transform, ob_tfm)
|
|
SD_VAR(Transform, ob_itfm)
|
|
#endif
|
|
|
|
/* Closure data, we store a fixed array of closures */
|
|
SD_CLOSURE_VAR(ShaderClosure, closure, MAX_CLOSURE)
|
|
SD_VAR(int, num_closure)
|
|
SD_VAR(float, randb_closure)
|
|
|
|
/* ray start position, only set for backgrounds */
|
|
SD_VAR(float3, ray_P)
|
|
SD_VAR(differential3, ray_dP)
|
|
|
|
#ifdef __OSL__
|
|
SD_VAR(struct KernelGlobals *, osl_globals)
|
|
#endif
|
|
|
|
#undef SD_VAR
|
|
#undef SD_CLOSURE_VAR
|