[mlir][vector] Verify non-unit strides on `masked/expand/compress` ops (#216485) Closes the stride-verification gap left open by #204611 and #205869 (**Stacked on #211004**). `vector.maskedload`/`maskedstore`/`expandload`/`compressstore` lower to LLVM masked intrinsics that read/write N *consecutive* elements from a single pointer (see [LangRef](https://llvm.org/docs/LangRef.htm)), but none of them verified the memref's minor-dim stride, so `strided<[2]>` verified successfully and silently miscompiled. This PR rejects statically-known non-unit and dynamic strides. --- The original PR (#210952, **identical to this one**) has been reverted (#215224) due to `Linalg/CPU/ArmSME/matmul.mlir` and `Linalg/CPU/ArmSME/multi-tile-matmul-mixed-types.mlir` e2e test failures (see the [buildbot](https://lab.llvm.org/buildbot/#/builders/121/builds/2588)). With #215296 merged I'm able to run the SME test and with #214959 the failures should be resolved. Note that `multi-tile-matmul-mixed-types.mlir` is disabled on macOS (my machine), while for `matmul.mlir` I can confirm that it passes without any problems. However, since the failure was the same, I think we can say with fairly certainty that `multi-tile-matmul-mixed-types.mlir` is solved as well. <details> <summary>My output</summary> ```bash $ llvm-project git:(vmls) llvm-mlir-helper test mlir/test/Integration/Dialect/Linalg/CPU/ArmSME/ -- Testing: 7 tests, 7 workers -- UNSUPPORTED: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/multi-tile-matmul.mlir (1 of 7) PASS: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/matmul.mlir (2 of 7) UNSUPPORTED: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/multi-tile-matmul-mixed-types.mlir (3 of 7) PASS: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/fill-2d.mlir (4 of 7) PASS: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/use-too-many-tiles.mlir (5 of 7) PASS: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/pack-unpack-mmt4d.mlir (6 of 7) PASS: MLIR :: Integration/Dialect/Linalg/CPU/ArmSME/matmul-transpose-a.mlir (7 of 7) Testing Time: 0.56s Total Discovered Tests: 7 Unsupported: 2 (28.57%) Passed : 5 (71.43%) ``` </details> --------- Signed-off-by: Federico Bruzzone <federico.bruzzone.i@gmail.com>
Welcome to the LLVM project!
This repository contains the source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.
The LLVM project has multiple components. The core of the project is itself called “LLVM”. This contains all of the tools, libraries, and header files needed to process intermediate representations and convert them into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer.
C-like languages use the Clang frontend. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.
Other components include: the libc++ C++ standard library, the LLD linker, and more.
Consult the Getting Started with LLVM page for information on building and running LLVM.
For information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.
Join the LLVM Discourse forums, Discord chat, LLVM Office Hours or Regular sync-ups.
The LLVM project has adopted a code of conduct for participants to all modes of communication within the project.