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
75 lines
2.4 KiB
C
75 lines
2.4 KiB
C
/*
|
|
* Copyright 2011-2013 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.
|
|
*/
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
/* Attributes
|
|
*
|
|
* We support an arbitrary number of attributes on various mesh elements.
|
|
* On vertices, triangles, curve keys, curves, meshes and volume grids.
|
|
* Most of the code for attribute reading is in the primitive files.
|
|
*
|
|
* Lookup of attributes is different between OSL and SVM, as OSL is ustring
|
|
* based while for SVM we use integer ids. */
|
|
|
|
/* Find attribute based on ID */
|
|
|
|
ccl_device_inline int find_attribute(KernelGlobals *kg, const ShaderData *sd, uint id, AttributeElement *elem)
|
|
{
|
|
if(ccl_fetch(sd, object) == PRIM_NONE)
|
|
return (int)ATTR_STD_NOT_FOUND;
|
|
|
|
/* for SVM, find attribute by unique id */
|
|
uint attr_offset = ccl_fetch(sd, object)*kernel_data.bvh.attributes_map_stride;
|
|
#ifdef __HAIR__
|
|
attr_offset = (ccl_fetch(sd, type) & PRIMITIVE_ALL_CURVE)? attr_offset + ATTR_PRIM_CURVE: attr_offset;
|
|
#endif
|
|
uint4 attr_map = kernel_tex_fetch(__attributes_map, attr_offset);
|
|
|
|
while(attr_map.x != id) {
|
|
if(UNLIKELY(attr_map.x == ATTR_STD_NONE)) {
|
|
return ATTR_STD_NOT_FOUND;
|
|
}
|
|
attr_offset += ATTR_PRIM_TYPES;
|
|
attr_map = kernel_tex_fetch(__attributes_map, attr_offset);
|
|
}
|
|
|
|
*elem = (AttributeElement)attr_map.y;
|
|
|
|
if(ccl_fetch(sd, prim) == PRIM_NONE && (AttributeElement)attr_map.y != ATTR_ELEMENT_MESH)
|
|
return ATTR_STD_NOT_FOUND;
|
|
|
|
/* return result */
|
|
return (attr_map.y == ATTR_ELEMENT_NONE) ? (int)ATTR_STD_NOT_FOUND : (int)attr_map.z;
|
|
}
|
|
|
|
/* Transform matrix attribute on meshes */
|
|
|
|
ccl_device Transform primitive_attribute_matrix(KernelGlobals *kg, const ShaderData *sd, int offset)
|
|
{
|
|
Transform tfm;
|
|
|
|
tfm.x = kernel_tex_fetch(__attributes_float3, offset + 0);
|
|
tfm.y = kernel_tex_fetch(__attributes_float3, offset + 1);
|
|
tfm.z = kernel_tex_fetch(__attributes_float3, offset + 2);
|
|
tfm.w = kernel_tex_fetch(__attributes_float3, offset + 3);
|
|
|
|
return tfm;
|
|
}
|
|
|
|
CCL_NAMESPACE_END
|
|
|