[llvm] [AArch64][LoopVectorize] Use either fixed-width or scalable VF when tail-folding (PR #67543)

[David Sherwood via llvm-commits]

david-arm wrote:

> we can use either fixed-width or scalable vectors.

And I guess the point here is that we're letting the cost model decide the most optimal VF. This is particularly important for tail-folded loops where the fixed-width versions of masked loads/stores may be expensive.

https://github.com/llvm/llvm-project/pull/67543