[llvm] [LoopVectorize][AArch64][SVE] Generate wide active lane masks (PR #81140)

[Paul Walker via llvm-commits]

paulwalker-arm wrote:

Perhaps this is a nonsensical suggestion but why not just always emit a VF*UF sized active lane mask when it is used for control flow.  Then leave the code generator to split it when necessary.  Perhaps we'll need to add wrap flag support to get.active.mask to make that job easier but this should not be all that different to what LoopVectorize would have to do anyway.

https://github.com/llvm/llvm-project/pull/81140