[all-commits] [llvm/llvm-project] 9a8248: [mlir][linalg] Fix pad tensor cast folding with ch...

[Yi Zhang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 9a824823131600bca71406f533c2ba051c23c7d7
      https://github.com/llvm/llvm-project/commit/9a824823131600bca71406f533c2ba051c23c7d7
  Author: Yi Zhang <cathyzhyi at google.com>
  Date:   2021-07-29 (Thu, 29 Jul 2021)

  Changed paths:
    M mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp
    M mlir/test/Dialect/Linalg/canonicalize.mlir

  Log Message:
  -----------
  [mlir][linalg] Fix pad tensor cast folding with changed type

`PadTensorOp` has verification logic to make sure
result dim must be static if all the padding values are static.
Cast folding might add more static information for the src operand
of `PadTensorOp` which might change a valid operation to be invalid.
Change the canonicalizing pattern to fix this.