[Mlir-commits] [mlir] [mlir] Fix #93973 - linalg::ReduceOp verifier crash (PR #107005)

[Diego Caballero]

dcaballe wrote:

Thanks for the PR!

```
  linalg.reduce
      ins(%input, %input2:memref<16x32x64xi32>, memref<16x32x64xi32>)
      outs(%init:memref<16x64xi32>)
      dimensions = [1]
      (%in: i32, %in2: i32, %out: i32) {
        %0 = arith.muli %in, %in2: i32
        %1 = arith.addi %out, %0: i32
        linalg.yield %1: i32
```

Not sure I follow this change. Shouldn't we just combine the two tensors before the `linalg.reduce` with a mul and then just add reduce the result of that?

https://github.com/llvm/llvm-project/pull/107005