feat: Add 32-bit floating-point atomics #6234
Open
+544
−49
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Current supported platforms: Metal * Platforms to support in the future: Vulkan Related issues or PRs: * gfx-rs#1020
* atomicSub for f32 in the previous commits is removed.
Update: Add support for VulkanDescription Currently, it supports Vulkan through the device extension Some operations that Vulkan can but not Metal, are not supported here including:
The supported atomic operations by Vulkan with
Note The recent update has removed validation for |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Connections
#1020
Description
It enables 32-bit floating point atomic operations on backends including Metal v3.0+ (Apple 7+). Currently, it does not support Vulkan, which has a feature flag
VK_EXT_shader_atomic_floatthough.However, Metal doesn't support all atomic operations and all address spaces. The Metal specification (2024-06-06) said:
This indicates we can't have workgroup-level floating-point atomic value.
It means that there are some read-modify-write functions we can't use.
The supported atomic operations by Metal are checked below:
atomicStoreatomicLoadatomicAddatomicSubatomicMaxatomicMinatomicAndatomicOratomicXoratomicExchangeatomicCompareExchangeWeak(Though it is unimplemented on MSL backend)In
wgpu-types, I have added the feature flagSHADER_FLT32_ATOMIC.Testing
Checklist
cargo fmt.cargo clippy. If applicable, add:--target wasm32-unknown-unknown--target wasm32-unknown-emscriptencargo xtask testto run tests.CHANGELOG.md. See simple instructions inside file.cargo xtask validate mslto validate shaders.cargo xtask validate spvto validate shaders.