[Mlir-commits] [mlir] [MLIR][Linalg] Introduce linalg.contract (PR #123618)

[Andrzej Warzyński]

banach-space wrote:

> How should we denote - in terms of the perfect loop nests correspondence for "structured ops" - that only on the first run of the body we should apply the scaling to C's elements? 

Ah, now I see what the problem is. Yeah, I don't see how that could be represented with a single GenericOp 🤔

> If by "scaling factor" you mean Micro-Scaling (https://arxiv.org/pdf/2310.10537), then this will be added later across all linalg ops,

Oh, that's way ahead of what I was thinking 😅 But also important one to keep in mind.

https://github.com/llvm/llvm-project/pull/123618