Exact

Exact Union RegExp

Brecht Van Lommel 5c328388f3 Cycles: Add concurrent states growth and shrinking for all GPU backends ... This helps avoid out of memory errors for complex scenes, and improves performance for smaller scenes with more memory available for states. Metal already had logic like this, now the logic is centralized and can be used for all GPU backends. The parameters have been somewhat tuned per device, based on earlier work for oneAPI in #163437 and CUDA in #163532. For Metal the behavior should remain basically the same. For oneAPI, this enables free_memory queries on iGPUs, as driver have been exposing this for some time. Co-authored-by: Patrick Mours <pmours@nvidia.com> Co-authored-by; Xavier Hallade <xavier.hallade@intel.com> Pull Request: https://projects.blender.org/blender/blender/pulls/163930		2026-09-23 15:22:57 +02:00
..
device.cpp	Cycles: Switch to CUDA 13 and enable DLSS	2026-09-18 19:30:10 +02:00
device.h	Refactor: Cycles: Replace new/delete by unique_ptr, in simple cases	2025-01-03 10:23:30 +01:00
device_impl.cpp	Cycles: Fallback value for missing image or attribute in shader	2026-09-15 19:45:36 +02:00
device_impl.h	Cycles: Enable local shader sorting for CUDA/OptiX	2026-09-15 12:39:35 +02:00
graphics_interop.cpp	Fix: Cycles log levels conflict with macros on some platforms	2025-07-10 19:44:14 +02:00
graphics_interop.h	Fix: Properly free Vulkan interop handle for Cycles	2025-05-26 10:59:49 +02:00
kernel.cpp	Refactor: Cycles: Move MNEE walk into separate kernel	2026-05-27 20:34:06 +02:00
kernel.h
queue.cpp	Cycles: Add concurrent states growth and shrinking for all GPU backends	2026-09-23 15:22:57 +02:00
queue.h	Cycles: Add concurrent states growth and shrinking for all GPU backends	2026-09-23 15:22:57 +02:00
util.cpp
util.h	Cycles: Bump minimum supported CUDA architecture to sm_50	2025-07-21 19:49:21 +02:00