Check was misc-const-correctness, combined with readability-isolate-declaration
as suggested by the docs.
Temporarily clang-format "QualifierAlignment: Left" was used to get consistency
with the prevailing order of keywords.
Pull Request: https://projects.blender.org/blender/blender/pulls/132361
* Use .empty() and .data()
* Use nullptr instead of 0
* No else after return
* Simple class member initialization
* Add override for virtual methods
* Include C++ instead of C headers
* Remove some unused includes
* Use default constructors
* Always use braces
* Consistent names in definition and declaration
* Change typedef to using
Pull Request: https://projects.blender.org/blender/blender/pulls/132361
Happens for renders from command line, when kernel specialization
thread is still working after the allocators on the Blender side
have been deinitialized.
Add an explicit deinitializaiton, which ensures all Cycles worker
and cache threads are finished before the allocators are deinitialized.
This should solve occasional crashes when running regression tests
for Metal or Metal-RT.
Pull Request: https://projects.blender.org/blender/blender/pulls/128239
This PR fixes live viewport stability issues on Mac when MetalRT is enabled.
There were two sources of instability:
1) `MTLAccelerationStructure` instances were not being correctly retained meaning that use-after-free crashes could occur following a geometry sync.
2) `MTLIntersectionFunctionTable` objects could be unsafely shared between multiple `MetalDeviceQueue` instances (in this case, `setBuffer` being the unsafe mutation)
The solution to 2 involves creating a new `MetalDispatchPipeline` type which is strictly used by only 1 `MetalDeviceQueue` instance.
Pull Request: https://projects.blender.org/blender/blender/pulls/124055
This is because with the addition of new features to Cycles, these GPUs
experienced significant performance regressions and bugs, all stemming
from bugs in the Metal GPU driver/compiler. The only reasonable way to
work around these issues was to disable parts of Cycles code on
these GPUs to avoid the driver/compiler bugs.
This resulted in increased development time maintaining these platforms
while being unable to deliver feature parity with other
GPU backends.
It has been decided that this development time is better spent
maintaining platforms that are still actively maintained by
hardware/software vendors, and so AMD and Intel GPU support will be
removed from the Metal backend for Cycles.
Pull Request: https://projects.blender.org/blender/blender/pulls/123551
This PR contains optimisations and a general tidy-up of the MetalRT backend.
- Currently `scene_intersect` is used for both normal and (opaque) shadow rays, however the usage patterns are different enough to warrant specialisation. Shadow intersection tests (flagged with `PATH_RAY_SHADOW_OPAQUE`) only need a bool result, but need a larger "self" payload in order to exclude hits against target lights. By specialising we can minimise the payload size in each case (which is helps performance) and avoid some dynamic branching. This PR introduces a new `scene_intersect_shadow` function which is specialised in Metal, and currently redirects to `scene_intersect` in the other backends.
- Currently `scene_intersect_local` is implemented for worst-case payload requirements as demanded by `subsurface_disk` (where `max_hits` is 4). The random_walk case only demands 1 hit result which we can retrieve directly from the intersector object (rather than stashing it in the payload). By specialising, we significantly reduce the payload size for random_walk queries, which has a big impact on performance. Additionally, we only need to use a custom intersection function for the first ray test in a random walk (for self-primitive filtering), so this PR forces faster `opaque` intersection testing for all but the first random walk test.
- Currently `scene_intersect_volume` has a lot of redundant code to handle non-triangle primitives despite volumes only being enclosed by trimeshes. This PR removes this code.
Additionally, this PR tidies up the convoluted intersection function linking code, removes some redundant intersection handlers, and uses more consistent naming of intersection functions.
On a M3 MacBook Pro, these changes give 2-3% performance increase on typical scenes with opaque trimesh materials (e.g. barbershop, classroom junkshop), but can give over 15% performance increase for certain scenes using random walk SSS (e.g. monster).
Pull Request: https://projects.blender.org/blender/blender/pulls/121397
Running a very simple files when Blender is built with the
WITH_COMPILER_ASAN=ON and WITH_CYCLES_KERNEL_ASAN=ON CMake options
leads to ASAN reporting an unknown-crash at line where the worker
pool is being filled in.
It is not entirely clear if it is a real issue in the code, since
placing debug prints with `this` address report proper addresses,
however there is no harm on capturing `this` pointer by value and
it does solve the ASAN reporting issues.
It is possible to reproduce the ASAN crash with the following steps:
- Start with --factory-startup
- Enable Metal device in User Preferences
- Switch render device to GPU Compute
- Switch viewport more to Rendered
Pull Request: https://projects.blender.org/blender/blender/pulls/119867
Along with the 4.1 libraries upgrade, we are bumping the clang-format
version from 8-12 to 17. This affects quite a few files.
If not already the case, you may consider pointing your IDE to the
clang-format binary bundled with the Blender precompiled libraries.
This PR adds tunings for the [newly announced](https://www.youtube.com/watch?v=ctkW3V0Mh-k) M3 family of chips. In particular, MetalRT will be enabled as the automatic default for intersection testing on M3 and beyond to take advantage of hardware raytracing. This will result in significant path-tracing speedups, as well as faster BVH builds.
Pull Request: https://projects.blender.org/blender/blender/pulls/114296
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 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
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
Workaround for a crash when `addComputePipelineFunctionsWithDescriptor` is called *after* `newComputePipelineStateWithDescriptor` with linked functions (i.e. with MetalRT enabled). Ideally we would like to call `newComputePipelineStateWithDescriptor` (async) first so we can bail out if needed, but we can stop the crash by flipping the order when there are linked functions. However when addComputePipelineFunctionsWithDescriptor is called first it will block while it builds the pipeline, offering no way of bailing out.
Note that this only has an impact when the "MetalRT (Experimental)" option is checked.
Pull Request: https://projects.blender.org/blender/blender/pulls/105629
When running unit tests or other fast completing renders, forced crashes can occur if there are any slow, outstanding PSO compilation requests (due to the `std::terminate` fall-back case in `~ShaderCache`).
This patch eliminates the need for this shutdown hack by using of the async version of `newComputePipelineStateWithDescriptor` when creating a PSO for the first time. In doing so, we are able to explicitly respond to app shutdown instead of waiting for the pipeline to finish compiling (..and then timing out and force-crashing). We still use the blocking version of `newComputePipelineStateWithDescriptor` when loading from an archive, as this can handle loading from a corrupted archive gracefully. Finally, we move `addComputePipelineFunctionsWithDescriptor` to *after* the PSO is built (as this will trigger a full blocking compile if the PSO has not yet been built, which would bring back the original issue).
Pull Request: https://projects.blender.org/blender/blender/pulls/105506
This patch fixes hanging unit tests when MetalRT is enabled. It simplifies and fixes the kernel selection logic by baking the MetalRT-specific options into `kernels_md5` rather than expanding out and testing MetalRT bit flags explicitly.
Pull Request #105270
This is a workaround for [issue #104087](https://projects.blender.org/blender/blender/issues/104087). We encounter crashes when using shader binary archives on AMD, so this disables them while we investigate a proper fix. Kernels will still be cached automatically by the OS file system cache. This cache may occasionally be purged due to external factors, in which case kernels will get compiled again.
Pull Request #105186
This fixes issue [#105100](https://projects.blender.org/blender/blender/issues/105100) where multi-pass renders can be incorrect due to kernels using stale specialisation constants (e.g. when rendering Pokedstudio).
This patch adds a new group of md5 hashes (`global_defines_md5`) to track whether the injected block of #defines is stale and regenerate the source string as appropriate. It also renames the existing group of md5 hashes from `source_md5` to `kernels_md5` to clarify that these refer to a specific kernel set rather than just the source (which might build an arbitrarily large number of kernel sets).
Pull Request #105103
This patch optimises subsurface intersection queries on MetalRT. Currently intersect_local traverses from the scene root, retrospectively discarding all non-local hits. Using a lookup of bottom level acceleration structures, we can explicitly query only the relevant instance. On M1 Max, with MetalRT selected, this can give a render speedup of 15-20% for scenes like Monster which make heavy use of subsurface scattering.
Patch authored by Marco Giordano.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D17153
This patch adds two new kernels: SORT_BUCKET_PASS and SORT_WRITE_PASS. These replace PREFIX_SUM and SORTED_PATHS_ARRAY on supported devices (currently implemented on Metal, but will be trivial to enable on the other backends). The new kernels exploit sort partitioning (see D15331) by sorting each partition separately using local atomics. This can give an overall render speedup of 2-3% depending on architecture. As before, we fall back to the original non-partitioned sorting when the shader count is "too high".
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D16909
This patch adds markup to specify that certain kernel data constants should not be specialised. Currently it is used for `tabulated_sobol_sequence_size` and `sobol_index_mask` which change frequently based on the aa sample count, trash the shader cache, and have little bearing on performance.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D16968
This patch adds occupancy tuning for the newly announced high-end M2 machines, giving 10-15% render speedup over a pre-tuned build.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D17037
This patch adds a new "Kernel Optimization Level" dropdown menu to control Metal kernel specialisation. Currently this defaults to "full" optimisation, on the assumption that the changes proposed in D16371 will address usability concerns around app responsiveness and shader cache housekeeping.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D16514
All kernel specialisation is now performed in the background regardless of kernel type, meaning that the first render will be visible a few seconds sooner. The only exception is during benchmark warm up, in which case we wait for all kernels to be cached. When stopping a render, we call a new `cancel()` method on the device which causes any outstanding compilation work to be cancelled, and we destroy the device in a detached thread so that any stale queued compilations can be safely purged without blocking the UI for longer than necessary.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D16371
This patch adapts D14754 for the Metal backend. Kernels of the same type are already organised into subdirectories which simplifies type matching.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D16469
This patch tunes maximum threads-per-threadgroup and threads-per-block for faster renders on Apple GPUs. Appropriate tuning is selected based on the GPU architecture (M1 or M2). We see a benchmark uplift of around 5-10% on M1 family chips. Similar uplift is expected on M2 with upcoming OS changes. (Ref T101931)
Reviewed By: brecht
Maniphest Tasks: T101931
Differential Revision: https://developer.blender.org/D16299
