x86: lowering of `llvm.minnum` and `llvm.maxnum` does not handle signed zeroes correctly

https://github.com/llvm/llvm-project/pull/112852 updated the documentation and semantics around the `llvm.minnum` and `llvm.maxnum` intrinsics. The langref for e.g. `llvm.minnum` now says (emphasis mine):

> Follows the semantics of minNum in IEEE-754-2008, **except that -0.0 < +0.0 for the purposes of this intrinsic.**
[...]
> **If the intrinsic is marked with the nsz attribute,** then the effect is as in the definition in C and IEEE-754-2008: the result of `minnum(-0.0, +0.0)` may be either -0.0 or +0.0.

However, this is not respected for x86. It lowers these operations to a `minps`/`minpd` plus a `cmpunord` to handle NaN, but makes no effort to handle signed zeroes if the nsz attribute is absent.

You can see this behavior in [this godbolt example](https://godbolt.org/z/Wz39s5czr). Note that the Rust `min` intrinsic is lowered to `llvm.minnum` (without any nsz attribute), which is then compiled into a `minps`+`cmpunordps` sequence.

Start by reading the linked PR 112852 and reproducing the behavior in the linked Godbolt example. Then trace the x86 lowering of llvm.minnum and llvm.maxnum, comparing minps/minpd plus cmpunord behavior with the documented signed-zero semantics; done means both intrinsic forms lower correctly with and without nsz.

Written by the indexing model from the issue text.