Add support for the Avx512 Compress/Expand intrinsics #116567
Merged
Conversation
This file contains hidden or 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
tannergooding
force-pushed
the
fix-87097
branch
2 times, most recently
from
9f26878 to
2b2edb4
Compare
tannergooding
added
area-CodeGen-coreclr
|
CC. @dotnet/jit-contrib, @EgorBo |
There was a problem hiding this comment.
Pull Request Overview
This pull request adds support for the AVX512 Compress/Expand intrinsics by implementing new APIs in the runtime libraries, updating the reference assemblies, and modifying the JIT and emitter to handle the new instructions. Key changes include:
- New definitions in System.Runtime.Intrinsics and System.Private.CoreLib for Compress and Expand intrinsics across multiple data types and vector sizes.
- Updates to the JIT lowering, code generation, and hardware intrinsic lists to correctly recognize and handle the new AVX512 compress/expand operations.
- Enhancements in test projects and intrinsic test generation to validate the new functionality.
Reviewed Changes
Copilot reviewed 32 out of 32 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| src/tests/JIT/HardwareIntrinsics/X86_Avx512/Avx512Vbmi2/Program.Avx512Vbmi2.cs | New test file for AVX512 Vbmi2 intrinsics support. |
| src/libraries/System.Runtime.Intrinsics/ref/System.Runtime.Intrinsics.cs | Added reference signatures for Compress and Expand intrinsics. |
| src/libraries/System.Private.CoreLib/ (multiple files) | Implementation of Compress/Expand intrinsics and platform stubs. |
| src/coreclr/jit/* and src/coreclr/jit/emitxarch.cpp, hwintrinsic* files | JIT lowering and codegen updates to support new intrinsics. |
| src/coreclr/jit/hwintrinsiclistxarch.h | New hardware intrinsic entries for Compress and Expand. |
Comments suppressed due to low confidence (1)
src/coreclr/jit/lowerxarch.cpp:10492
- The new case for NI_AVX512_CompressMask and NI_AVX512_ExpandMask efficiently optimizes merge with zero by containing the operand. Please verify that this zero merge optimization covers all expected scenarios and does not introduce side effects.
case NI_AVX512_CompressMask:
|
Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch |
EgorBo
approved these changes
Jun 13, 2025
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
This makes progress towards completing the remaining APIs from #87097