[all-commits] [llvm/llvm-project] cc14b5: [MLIR][Linalg] Fix winograd op lowering for types ...

[Isaac Nudelman via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: cc14b589659b6c6c9fb65de7a274287f2490d345
      https://github.com/llvm/llvm-project/commit/cc14b589659b6c6c9fb65de7a274287f2490d345
  Author: Isaac Nudelman <62861466+nuudlman at users.noreply.github.com>
  Date:   2025-10-08 (Wed, 08 Oct 2025)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/WinogradConv2D.cpp
    M mlir/test/Dialect/Linalg/winograd-conv2d-rewrite.mlir

  Log Message:
  -----------
  [MLIR][Linalg] Fix winograd op lowering for types smaller than f32 (#158500)

The winograd transform constant array is always emitted as f32, but
previously the creation would pass through the original type. If this
type was smaller (like f16), you would get an assertion failure during
attribute creation.

This fixes this by ensuring that the types match and adding a test for
this case.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications