The increased amount of BSDF code from Principled BSDF v2 and the
microfacet BSDF led to a big performance regression on Metal and AMD.
We have not been able to find a good workaround for all scenes.
This change disables the Principled Hair BSDF code when it is not used
in the scene. This makes common benchmark scenes faster, but
performance is still bad in scenes that do use it.
Ref #112596
Pull Request: https://projects.blender.org/blender/blender/pulls/113904
The first public Windows driver version with a higher number is
101.4824, so we bump the min-required driver version on Windows to this
one to ensure compatibility.
<algorithm> header include is missing from some sycl headers, this will
be fixed upstream with https://github.com/intel/llvm/pull/10424,
meanwhile, we work around it by including it directly.
This PR fixes T39823, the sole failing unit test when running with MetalRT. It does so by implementing and binding a missing intersection handler (`__anyhit__cycles_metalrt_volume_test_tri`) which is required for `scene_intersect_volume` (as used by `integrator_volume_stack_update_for_subsurface`) to work as intended. This scene exposed the error as it uses subsurface scattering on a sphere which is intersected by volume.
Pull Request: https://projects.blender.org/blender/blender/pulls/112876
This patch adds `BVHMetalBuildThrottler` which limits the amount of Metal BVH building work that runs concurrently on the GPU. Previously we submitted BVH build requests to the GPU as fast as possible, but in extreme cases this could fail when the device's working set size passes safe limits.
Pull Request: https://projects.blender.org/blender/blender/pulls/112821
This patch fixes the memory leak described in #107714 by adding an `@autoreleasepool` around Metal BVH builds. Certain NSObjects were being retained indefinitely, specifically ones which had been value-passed via an NSArray into acceleration structure descriptors.
Pull Request: https://projects.blender.org/blender/blender/pulls/112820
This patch adds a check to see whether we're actually using NanoVDB textures, and if not, removes `#define WITH_NANOVDB` when generating the scene-optimised kernels. This results in marginally faster render times (maybe 2 or 3%) for scenes that do not use NanoVDB. The generic kernels are unaffected, so this will not impact responsiveness on first render.
Pull Request: https://projects.blender.org/blender/blender/pulls/112822
This patch updates the experimental MetalRT code path to use new [curve primitives](https://developer.apple.com/videos/play/wwdc2023/10128/) which were recently added in macOS 14. This replaces the previous custom box intersection implementation, allowing the driver to better optimise curve acceleration structures for the GPU. On existing hardware, this can speed up MetalRT renders by up to 40% for scenes that use hair / curve primitives extensively.
The MetalRT option will only be available on macOS >= 14, and requires Xcode >= 15 to build (otherwise the option will be compiled out).
Authored by Marco Giordano, Michael Jones, and Jason Fielder
---
Before / after render times (M1 Max MacBook Pro, macOS 14 beta, MetalRT enabled):
```
Custom box intersection MetalRT curve primitives Speedup
fishy_cat 111.5 80.5 1.39
koro 114.4 86.7 1.32
sinosauropteryx 291.8 279.2 1.05
spring 142.3 142.2 1.00
victor 442.7 347.7 1.27
```
---
Pull Request: https://projects.blender.org/blender/blender/pulls/111795
Recent versions of DPC++ dropped using the environment variable
SYCL_PI_LEVEL_ZERO_USE_COPY_ENGINE_FOR_IN_ORDER_QUEUE=0 we were setting.
We're now also setting SYCL_PI_LEVEL_ZERO_USE_COPY_ENGINE=0 by default
to keep a consistent behavior.
In the commonly used cycles headers, it's enough to include
much smaller <iosfwd> than the full <iostream>. While looking at it,
removed inclusion of some other headers from commonly used headers,
that seemed to not be needed.
Pull Request: https://projects.blender.org/blender/blender/pulls/111063
During recent testing, the oldest 101.4032 (windows) and <25812 (linux)
drivers led to crashes during JIT compilation, so we bump the
requirement to newer 101.4313 and 25812.14 drivers that do incorporate
the required fixes.
Pull Request: https://projects.blender.org/blender/blender/pulls/109281
Better to disable than crashing, as we are not expecting a quick fix. The cause
is likely similar to issues with the light tree, which was already disabled.
Ref #104013
On an iMac (Retina 5K, 27-inch, Late 2015) it crashed when rendering using Cycles. This was due to the fact that it incorrectly detected that the machine supported ray tracing. This uses the device.supportsRaytracing flag to fill in the use_hardware_raytracing flag for the device.
This patch removes a workaround for an issue that is now understood to be undefined behaviour (and fixed by #108176). It also adds two useful debug flags that we would like to be available in Blender 3.6.
Pull Request: https://projects.blender.org/blender/blender/pulls/108322
This patch fixes an undefined behaviour where we were trying to use linked functions with binary archives. This isn't supported yet. At best this will fail silently, but this is not guaranteed in future. To fix this we simply disable binary archives if any linked functions are involved. The impact of this is that the `SHADE_SURFACE_RAYTRACE` and `SHADE_SURFACE_MNEE` kernels will fall back to the file system cache when MetalRT is enabled. The file system cache will occasionally be purged due to factors beyond Blender's control.
Pull Request: https://projects.blender.org/blender/blender/pulls/108176
Only Embree CPU BVH was built in the multi-device case. However, one
Embree GPU BVH is needed per GPU, so we now reuse the same logic as in
the other backends.
Pull Request: https://projects.blender.org/blender/blender/pulls/107992
