[Mlir-commits] [mlir] [mlir][tensor] Preserve encoding in more canonicalizers (concat, reshape, pad) (PR #207241)

[Dmitrii Makarenko]

Devjiu wrote:

Returned the previous behavior for CollapseShapeOp and ConcatOp, but with Pad - it's a little bit tricky as "FoldStaticPadding" depends on "PadOp::inferResultType" - I left it with encoding propagation, for now. I am not sure that it's the same issue with Concat, but feel free to share your thoughts. 

https://github.com/llvm/llvm-project/pull/207241