915766f42d
This implements branched path tracing for the split kernel. General approach is to store the ray state at a branch point, trace the branched ray as normal, then restore the state as necessary before iterating to the next part of the path. A state machine is used to advance the indirect loop state, which avoids the need to add any new kernels. Each iteration the state machine recreates as much state as possible from the stored ray to keep overall storage down. Its kind of hard to keep all the different integration loops in sync, so this needs lots of testing to make sure everything is working correctly. We should probably start trying to deduplicate the integration loops more now. Nonbranched BMW is ~2% slower, while classroom is ~2% faster, other scenes could use more testing still. Reviewers: sergey, nirved Reviewed By: nirved Subscribers: Blendify, bliblubli Differential Revision: https://developer.blender.org/D2611
79 lines
2.1 KiB
C
79 lines
2.1 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 __KERNEL_SPLIT_H__
|
|
#define __KERNEL_SPLIT_H__
|
|
|
|
#include "kernel/kernel_math.h"
|
|
#include "kernel/kernel_types.h"
|
|
|
|
#include "kernel/split/kernel_split_data.h"
|
|
|
|
#include "kernel/kernel_globals.h"
|
|
|
|
#ifdef __OSL__
|
|
# include "kernel/osl/osl_shader.h"
|
|
#endif
|
|
|
|
#ifdef __KERNEL_OPENCL__
|
|
# include "kernel/kernel_image_opencl.h"
|
|
#endif
|
|
#ifdef __KERNEL_CPU__
|
|
# include "kernel/kernels/cpu/kernel_cpu_image.h"
|
|
#endif
|
|
|
|
#include "util/util_atomic.h"
|
|
|
|
#include "kernel/kernel_path.h"
|
|
#ifdef __BRANCHED_PATH__
|
|
# include "kernel/kernel_path_branched.h"
|
|
#endif
|
|
|
|
#include "kernel/kernel_queues.h"
|
|
#include "kernel/kernel_work_stealing.h"
|
|
|
|
#ifdef __BRANCHED_PATH__
|
|
# include "kernel/split/kernel_branched.h"
|
|
#endif
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
ccl_device_inline void kernel_split_path_end(KernelGlobals *kg, int ray_index)
|
|
{
|
|
ccl_global char *ray_state = kernel_split_state.ray_state;
|
|
|
|
#ifdef __BRANCHED_PATH__
|
|
if(IS_FLAG(ray_state, ray_index, RAY_BRANCHED_LIGHT_INDIRECT)) {
|
|
ASSIGN_RAY_STATE(ray_state, ray_index, RAY_LIGHT_INDIRECT_NEXT_ITER);
|
|
}
|
|
else if(IS_FLAG(ray_state, ray_index, RAY_BRANCHED_VOLUME_INDIRECT)) {
|
|
ASSIGN_RAY_STATE(ray_state, ray_index, RAY_VOLUME_INDIRECT_NEXT_ITER);
|
|
}
|
|
else if(IS_FLAG(ray_state, ray_index, RAY_BRANCHED_SUBSURFACE_INDIRECT)) {
|
|
ASSIGN_RAY_STATE(ray_state, ray_index, RAY_SUBSURFACE_INDIRECT_NEXT_ITER);
|
|
}
|
|
else {
|
|
ASSIGN_RAY_STATE(ray_state, ray_index, RAY_UPDATE_BUFFER);
|
|
}
|
|
#else
|
|
ASSIGN_RAY_STATE(ray_state, ray_index, RAY_UPDATE_BUFFER);
|
|
#endif
|
|
}
|
|
|
|
CCL_NAMESPACE_END
|
|
|
|
#endif /* __KERNEL_SPLIT_H__ */
|