[llvm] [VPlan] First step towards VPlan cost modeling. (PR #92555)

[via llvm-commits]

ayalz wrote:

> > BTW, could any pre-computation be avoided by computing VPlan's cost earlier, before some VPlan transform takes place?
> 
> It would have to happen directly after initial construction, which in turn would us require to maintain a VPlan -> Cost mapping. I've left things as is for now

OK. Measuring sub-optimal cost of initial VPlan would help demonstrate the current state of CM, and VPlan's ability to measure more accurate costs after various VPlan transforms are applied.

https://github.com/llvm/llvm-project/pull/92555