[all-commits] [llvm/llvm-project] c118fd: [mlir] Remove incorrect folding for SubTensorInsertOp

MaheshRavishankar via All-commits all-commits at lists.llvm.org
Wed Mar 3 13:58:36 PST 2021


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c118fdcd5970d66abf9cc3f0d09544b269b01cc8
      https://github.com/llvm/llvm-project/commit/c118fdcd5970d66abf9cc3f0d09544b269b01cc8
  Author: MaheshRavishankar <ravishankarm at google.com>
  Date:   2021-03-03 (Wed, 03 Mar 2021)

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

  Log Message:
  -----------
  [mlir] Remove incorrect folding for SubTensorInsertOp

The SubTensorInsertOp has a requirement that dest type and result
type match. Just folding the tensor.cast operation violates this and
creates verification errors during canonicalization. Also fix other
canonicalization methods that werent inserting casts properly.

Differential Revision: https://reviews.llvm.org/D97800




More information about the All-commits mailing list