[llvm] [RISCV] Don't vectorize for loops with small trip count (PR #132176)

[Pengcheng Wang via llvm-commits]

wangpc-pp wrote:

> Do we still want to vectorize small trip counts with EVL tail folding?

I think we should not, EVL tail folding doesn't help a lot for small trip count  loops.

> I can also queue up a performance run for this on the BPI-F3 (without tail folding)

That'll be helpful! Based on my experience years ago, we should have some gains on SPEC CPU because LV vectorizes some small loops and causes more instructions/stalls.

https://github.com/llvm/llvm-project/pull/132176