[llvm] [VPlan] Add support for in-loop AnyOf reductions (PR #131830)

[Luke Lau via llvm-commits]

lukel97 wrote:

Rebased now that #131300 is landed

>From the discussion in #132180 it looks like there is still some interest in having this available for certain targets and cores to enable, and potentially if we ever allow vectorizing with larger LMULs on RISC-V.

https://github.com/llvm/llvm-project/pull/131830