[all-commits] [llvm/llvm-project] 12e433: [mlir][nvgpu] Fix the TMA stride setup (#75838)

[Adam Paszke via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 12e4332501bca3bc1e29be94e134eea231578985
      https://github.com/llvm/llvm-project/commit/12e4332501bca3bc1e29be94e134eea231578985
  Author: Adam Paszke <apaszke at google.com>
  Date:   2023-12-19 (Tue, 19 Dec 2023)

  Changed paths:
    M mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp

  Log Message:
  -----------
  [mlir][nvgpu] Fix the TMA stride setup (#75838)

There were two issues with the previous computation:
* it never looked at dimensions past the second one
* the definition was recursive, making each dimension have an extra
`elementSize` power