[llvm] [AArch64][ISel] Enable profile-aware branch condition merging (PR #201486)

[Ricardo Jesus via llvm-commits]

rj-jesus wrote:

> > It looks like this regresses 709.cactus_r by ~8% on Neoverse V2 with `-O3`/`-O3 -mcpu=neoverse-v2`. Other options show similar slowdowns, except with `-ffast-math`. Have you seen anything similar?
> 
> I didn't see it. Let me take a look. edit: do you see any benchmarks that shows improvement?

Thanks! I don't see anything significant in SPEC 2026.

https://github.com/llvm/llvm-project/pull/201486