[llvm] [X86] Lower mathlib call ldexp into scalef when avx512 is enabled (PR #69710)

[Phoebe Wang via llvm-commits]

================
@@ -31814,6 +31820,45 @@ static StringRef getInstrStrFromOpNo(const SmallVectorImpl<StringRef> &AsmStrs,
   return StringRef();
 }
 
+static SDValue LowerFLDEXP(SDValue Op, SelectionDAG &DAG) {
+  SDValue X = Op.getOperand(0);
+  EVT XScalarTy = X.getValueType();
+  SDValue Exp = Op.getOperand(1);
+
+  SDLoc DL(Op);
+  EVT XVT, ExpVT;
+  SDValue IID;
+  switch (Op.getSimpleValueType().SimpleTy) {
+  default:
+    return SDValue();
+  case MVT::f16:
+    X = DAG.getNode(ISD::FP_EXTEND, DL, MVT::f32, X);
----------------
phoebewang wrote:

Good point! LangRef doesn't give an example f16 case. Should we define it as `@llvm.ldexp.f16.i16(half, i16)`? `i32` is a too large range to be useful for FP16.

https://github.com/llvm/llvm-project/pull/69710