[Mlir-commits] [mlir] [mlir][linalg] Extend `FuseElementwiseOps` pattern to work with named ops (PR #144922)

[Oleksandr Alex Zinenko]

ftynse wrote:

On the change itself, the rationale https://mlir.llvm.org/docs/Rationale/RationaleLinalgDialect/#progressive-lowering-dont-lose-information-too-quicklya-nameprogressive_loweringa explicitly lists fusion as a transformation that drops high-level information, which can be interpreted as a desire to give users control over generalization behavior during fusion. This would be aligned with @MaheshRavishankar's suggestion, though _not because it breaks downstreams_ but because it would better reflect the design rationale of linalg. The control function does so, but maybe we can have several pre-defined for an easy switch?

https://github.com/llvm/llvm-project/pull/144922