Blender Git Loki
Git Commits -> Revision b41c72b
November 25, 2021, 08:32 (GMT) |
Fix performance decrease with Scrambling Distance on With the current code in master, scrambling distance is enabled on non-hardware accelerated ray tracing devices see a measurable performance decrease when compared scrambling distance on vs off. From testing, this performance decrease comes from the large tile sizes scheduled in `tile.cpp`. This patch attempts to address the performance decrease by using different algorithms to calculate the tile size for devices with hardware accelerated ray traversal and devices without. Large tile sizes for hardware accelerated devices and small tile sizes for others. Most of this code is based on proposals from @brecht and @leesonw Reviewed By: brecht, leesonw Differential Revision: https://developer.blender.org/D13042 |
Commit Details:
Full Hash: b41c72b710d4013fd6d67dc49a8ebb2a416b4462
Parent Commit: 8f2db94
Committed By: William Leeson
Lines Changed: +41, -24
7 Modified Paths:
/intern/cycles/integrator/path_trace_work_gpu.cpp (+2, -1) (Diff)
/intern/cycles/integrator/tile.cpp (+3, -2) (Diff)
/intern/cycles/integrator/tile.h (+2, -1) (Diff)
/intern/cycles/integrator/work_tile_scheduler.cpp (+6, -1) (Diff)
/intern/cycles/integrator/work_tile_scheduler.h (+6, -0) (Diff)
/intern/cycles/kernel/device/gpu/work_stealing.h (+14, -11) (Diff)
/intern/cycles/test/integrator_tile_test.cpp (+8, -8) (Diff)
/intern/cycles/integrator/tile.cpp (+3, -2) (Diff)
/intern/cycles/integrator/tile.h (+2, -1) (Diff)
/intern/cycles/integrator/work_tile_scheduler.cpp (+6, -1) (Diff)
/intern/cycles/integrator/work_tile_scheduler.h (+6, -0) (Diff)
/intern/cycles/kernel/device/gpu/work_stealing.h (+14, -11) (Diff)
/intern/cycles/test/integrator_tile_test.cpp (+8, -8) (Diff)