This repository has been archived on 2023-10-09. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
blender-archive/intern/cycles/kernel/device/gpu/work_stealing.h
Brecht Van Lommel 9cfc7967dd Cycles: use SPDX license headers
* Replace license text in headers with SPDX identifiers.
* Remove specific license info from outdated readme.txt, instead leave details
  to the source files.
* Add list of SPDX license identifiers used, and corresponding license texts.
* Update copyright dates while we're at it.

Ref D14069, T95597
2022-02-11 17:47:34 +01:00

43 lines
1.3 KiB
C++

/* SPDX-License-Identifier: Apache-2.0
* Copyright 2011-2022 Blender Foundation */
#pragma once
CCL_NAMESPACE_BEGIN
/*
* Utility functions for work stealing
*/
/* Map global work index to tile, pixel X/Y and sample. */
ccl_device_inline void get_work_pixel(ccl_global const KernelWorkTile *tile,
uint global_work_index,
ccl_private uint *x,
ccl_private uint *y,
ccl_private uint *sample)
{
uint sample_offset, pixel_offset;
if (kernel_data.integrator.scrambling_distance < 0.9f) {
/* Keep threads for the same sample together. */
uint tile_pixels = tile->w * tile->h;
sample_offset = global_work_index / tile_pixels;
pixel_offset = global_work_index - sample_offset * tile_pixels;
}
else {
/* Keeping threads for the same pixel together.
* Appears to improve performance by a few % on CUDA and OptiX. */
sample_offset = global_work_index % tile->num_samples;
pixel_offset = global_work_index / tile->num_samples;
}
uint y_offset = pixel_offset / tile->w;
uint x_offset = pixel_offset - y_offset * tile->w;
*x = tile->x + x_offset;
*y = tile->y + y_offset;
*sample = tile->start_sample + sample_offset;
}
CCL_NAMESPACE_END