[llvm] [InstCombine] Transform high latency, dependent FSQRT/FDIV into FMUL (PR #87474)

[Florian Hahn via llvm-commits]

fhahn wrote:

I am wondering if instcombine is the right place to reason about this? At this point, we don't have any info on the cost of instructions. This seems like it would be better placed in the backend, e.g. as a pattern MachineCombiner uses (which already tries to reassociate expressions, if it improves the critical path or other metrics)

https://github.com/llvm/llvm-project/pull/87474