[llvm-branch-commits] [mlir] [mlir][linalg] Enable scalable vectorization of linalg.unpack (PR #149293)

[Andrzej Warzyński via llvm-branch-commits]

banach-space wrote:

>  I'm not very familiar with the linalg vectorization, so I might've left more questions than comments, sorry about that!

No need to apologize! You took the time to review my PR, and it’s totally expected that you'd have questions - I'm more than happy to clarify things :)

This code should be clear to everyone, not just those who've worked on it before, so thanks for highlighting areas that could use more explanation. I’m happy to expand further if anything’s still unclear.

I’ve pushed quite a few changes and added links to the relevant commits in the comments. That’s introduced a bit of noise, though, so it might be easier to review this as one large change rather than commit-by-commit.

Thanks again for taking a look 🙏🏻

https://github.com/llvm/llvm-project/pull/149293