6bf4115c13
Reduce thread divergence in kernel_shader_eval. Rays are sorted in blocks of 2048 according to shader->id. On R9 290 Classroom is ~30% faster, and Pabellon Barcelone is ~8% faster. No sorting for CUDA split kernel. Reviewers: sergey, maiself Reviewed By: maiself Differential Revision: https://developer.blender.org/D2598
28 lines
969 B
Common Lisp
28 lines
969 B
Common Lisp
/*
|
|
* Copyright 2011-2017 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.
|
|
*/
|
|
|
|
#include "kernel/kernel_compat_opencl.h"
|
|
#include "kernel/split/kernel_split_common.h"
|
|
#include "kernel/split/kernel_shader_setup.h"
|
|
|
|
__kernel void kernel_ocl_path_trace_shader_setup(
|
|
ccl_global char *kg,
|
|
ccl_constant KernelData *data)
|
|
{
|
|
ccl_local unsigned int local_queue_atomics;
|
|
kernel_shader_setup((KernelGlobals*)kg, &local_queue_atomics);
|
|
}
|