[llvm] [AArch64][SVE] Fix v16i8 -> v2i64 partial_reduce for VL > 128 (PR #204938)

[Sander de Smalen via llvm-commits]

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

Thanks for the fix, LGTM as well

https://github.com/llvm/llvm-project/pull/204938