044a77352f
NOTE: this feature is not ready for user testing, and not yet enabled in daily builds. It is being merged now for easier collaboration on development. HIP is a heterogenous compute interface allowing C++ code to be executed on GPUs similar to CUDA. It is intended to bring back AMD GPU rendering support on Windows and Linux. https://github.com/ROCm-Developer-Tools/HIP. As of the time of writing, it should compile and run on Linux with existing HIP compilers and driver runtimes. Publicly available compilers and drivers for Windows will come later. See task T91571 for more details on the current status and work remaining to be done. Credits: Sayak Biswas (AMD) Arya Rafii (AMD) Brian Savery (AMD) Differential Revision: https://developer.blender.org/D12578
51 lines
1.4 KiB
C++
51 lines
1.4 KiB
C++
/*
|
|
* Copyright 2021 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.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
/* Parallel prefix sum.
|
|
*
|
|
* TODO: actually make this work in parallel.
|
|
*
|
|
* This is used for an array the size of the number of shaders in the scene
|
|
* which is not usually huge, so might not be a significant bottleneck. */
|
|
|
|
#include "util/util_atomic.h"
|
|
|
|
#ifdef __HIP__
|
|
# define GPU_PARALLEL_PREFIX_SUM_DEFAULT_BLOCK_SIZE 1024
|
|
#else
|
|
# define GPU_PARALLEL_PREFIX_SUM_DEFAULT_BLOCK_SIZE 512
|
|
#endif
|
|
|
|
template<uint blocksize> __device__ void gpu_parallel_prefix_sum(int *values, const int num_values)
|
|
{
|
|
if (!(ccl_gpu_block_idx_x == 0 && ccl_gpu_thread_idx_x == 0)) {
|
|
return;
|
|
}
|
|
|
|
int offset = 0;
|
|
for (int i = 0; i < num_values; i++) {
|
|
const int new_offset = offset + values[i];
|
|
values[i] = offset;
|
|
offset = new_offset;
|
|
}
|
|
}
|
|
|
|
CCL_NAMESPACE_END
|