[llvm] [RISCV] Improve fixed vector handling in isCtpopFast. (PR #158380)

[Philip Reames via llvm-commits]

https://github.com/preames commented:

Do we really want to be considering scalarized vector operations fast at all?  What's the implication of just requiring zvbb for this?  The prior code really looks more likely an oversight than an intentional fallthrough.

https://github.com/llvm/llvm-project/pull/158380