Merge branch 'blender-v3.0-release' to bring in D13042:

Fix performance decrease with Scrambling Distance on

1 files changed, 14 insertions, 11 deletions

diff --git a/intern/cycles/kernel/device/gpu/work_stealing.h b/intern/cycles/kernel/device/gpu/work_stealing.h
index fab0915c38e..c3083948057 100644
--- a/intern/cycles/kernel/device/gpu/work_stealing.h
+++ b/intern/cycles/kernel/device/gpu/work_stealing.h
@@ -29,17 +29,20 @@ ccl_device_inline void get_work_pixel(ccl_global const KernelWorkTile *tile,
                                       ccl_private uint *y,
                                       ccl_private uint *sample)
 {
-#if 0
-  /* Keep threads for the same sample together. */
-  uint tile_pixels = tile->w * tile->h;
-  uint sample_offset = global_work_index / tile_pixels;
-  uint 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. */
-  uint sample_offset = global_work_index % tile->num_samples;
-  uint pixel_offset = global_work_index / tile->num_samples;
-#endif
+  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;