[all-commits] [llvm/llvm-project] f33a0a: [mlir][nvgpu] Improve `tensormap.descriptor` Type ...

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f33a0a483550e3441aae4059d6b3d81eab6a398c
      https://github.com/llvm/llvm-project/commit/f33a0a483550e3441aae4059d6b3d81eab6a398c
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2024-02-05 (Mon, 05 Feb 2024)

  Changed paths:
    M mlir/include/mlir/Dialect/NVGPU/IR/NVGPUDialect.h
    M mlir/lib/Dialect/NVGPU/IR/NVGPUDialect.cpp
    M mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir
    M mlir/test/Dialect/NVGPU/invalid.mlir
    M mlir/test/Dialect/NVGPU/tmaload-transform.mlir

  Log Message:
  -----------
  [mlir][nvgpu] Improve `tensormap.descriptor` Type Verifier (#77904)

This PR improves the verifier for the `nvgpu.tensormap.descriptor` type.
The descriptor contains information for TMA, and the compile-time check
ensures its restrictions, such as the last memory dimension being
128-byte. This prevents runtime crashes.

See cuda driver for more explanation:

https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__TENSOR__MEMORY.html#group__CUDA__TENSOR__MEMORY_1ga7c7d2aaac9e49294304e755e6f341d7