930a942dd0
This change puts all the block size macros in the same common header, so they can be included in host side code without needing to also include the kernels that are defined in the device headers that contained these values. This change also removes a magic number used to enqueue a kernel, which happened to agree with the GPU_PARALLEL_SORT_BLOCK_SIZE macro. Pull Request: https://projects.blender.org/blender/blender/pulls/143646
19 lines
592 B
C
19 lines
592 B
C
/* SPDX-FileCopyrightText: 2017-2025 Blender Foundation
|
|
*
|
|
* SPDX-License-Identifier: Apache-2.0 */
|
|
|
|
#pragma once
|
|
|
|
#ifdef __HIP__
|
|
# define GPU_PARALLEL_ACTIVE_INDEX_DEFAULT_BLOCK_SIZE 1024
|
|
# define GPU_PARALLEL_PREFIX_SUM_DEFAULT_BLOCK_SIZE 1024
|
|
# define GPU_PARALLEL_SORTED_INDEX_DEFAULT_BLOCK_SIZE 1024
|
|
#else
|
|
# define GPU_PARALLEL_ACTIVE_INDEX_DEFAULT_BLOCK_SIZE 512
|
|
# define GPU_PARALLEL_PREFIX_SUM_DEFAULT_BLOCK_SIZE 512
|
|
# define GPU_PARALLEL_SORTED_INDEX_DEFAULT_BLOCK_SIZE 512
|
|
#endif
|
|
|
|
#define GPU_PARALLEL_SORTED_INDEX_INACTIVE_KEY (~0)
|
|
#define GPU_PARALLEL_SORT_BLOCK_SIZE 1024
|