[libclc] [libclc] Optimize generic CLC fmin/fmax (PR #128506)

[Matt Arsenault via cfe-commits]

arsenm wrote:

> I don't suppose the recent [clarifications](https://github.com/llvm/llvm-project/commit/363b05944f92) to `llvm.minnum` and `llvm.maxnum` change anything here?

It depends on whether the conformance test is fixed to match the fuzzy language of the spec or not. If the decision is fmin/fmax should match the IEEE behavior, the implementation directly maps to llvm.minnum/llvm.maxnum. If the decision is the conformance test continues doing what it has been doing, it should directly map to llvm.minimumnum/maximumnum. In either case, we should not have code using canonicalizes 

https://github.com/llvm/llvm-project/pull/128506