[llvm] [AArch64][VecLib] Add vector function mappings for the modf, sincos, sincospi vector intrinsics (PR #175098)

[David Sherwood via llvm-commits]

david-arm wrote:

I guess for my point about getMultipleResultIntrinsicVectorLibCallCost this could be done in a follow-on patch. I just mentioned it because even after this patch I think the loop vectoriser will still generate calls to the intrinsic and not directly to the ArmPL function due to this logic in LoopVectorize.cpp:

```
      if (VectorCost <= Cost) {
        Cost = VectorCost;
        Decision = CM_VectorCall;
      }

      if (IntrinsicCost <= Cost) {
        Cost = IntrinsicCost;
        Decision = CM_IntrinsicCall;
      }
```

https://github.com/llvm/llvm-project/pull/175098