[Mlir-commits] [mlir] [mlir][linalg] Use maximumf with a finite neutral element in softmax decomposition (PR #213797)

[Renato Golin]

rengolin wrote:

The previous PR did not explain what was being folded or where, and `maxnumf` really isn't the best choice for softmax. 

The PR also references the difference between decomposition and generalization, but did not argue that the decomposition was wrong, and not the generalization.

I'm guessing the folding was in IREE and not MLIR upstream, which makes it the wrong fix. Upstream softmax should decompose and generalize to `maximumf`, and downstream projects can update their own folding.

Did you make sure that both decomposition AND generalization agree on the form? We should have LIT tests for a round trip.

https://github.com/llvm/llvm-project/pull/213797