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

[Craig Topper via llvm-commits]

topperc wrote:

> 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.

It has test coverage in rv32zbb.ll and rv64zbb.ll which don't have +v command lines so I think it was semi-intentional. But I think I'm happy to remove it.

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