[llvm] [LoopVectorize] Vectorize select-cmp reduction pattern for increasing integer induction variable (PR #67812)

[Graham Hunter via llvm-commits]

https://github.com/huntergr-arm approved this pull request.

I think this is in good shape. There's some overlap with the CSA PR, but this patch should generate more efficient code on many targets due to the narrower focus on induction values alone. We may be able to do some refactoring later, but that shouldn't hold this up further.

(Sorry it took me so long to get back to this and finish off the review)

https://github.com/llvm/llvm-project/pull/67812