[llvm] AMDGPU][True16][CodeGen] FP_Round f64 to f16 in true16 (PR #128911)

[Ivan Kosarev via llvm-commits]

================
@@ -6899,9 +6899,21 @@ SDValue SITargetLowering::lowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const {
     if (Op.getOpcode() != ISD::FP_ROUND)
       return Op;
 
-    SDValue FpToFp16 = DAG.getNode(ISD::FP_TO_FP16, DL, MVT::i32, Src);
-    SDValue Trunc = DAG.getNode(ISD::TRUNCATE, DL, MVT::i16, FpToFp16);
-    return DAG.getNode(ISD::BITCAST, DL, MVT::f16, Trunc);
+    if (Subtarget->has16BitInsts()) {
+      if (getTargetMachine().Options.UnsafeFPMath) {
+        SDValue Flags = Op.getOperand(1);
+        SDValue Src32 = DAG.getNode(ISD::FP_ROUND, DL, MVT::f32, Src, Flags);
+        return DAG.getNode(ISD::FP_ROUND, DL, MVT::f16, Src32, Flags);
+      } else {
+        SDValue FpToFp16 = LowerF64ToF16(Src, DL, DAG);
+        SDValue Trunc = DAG.getNode(ISD::TRUNCATE, DL, MVT::i16, FpToFp16);
+        return DAG.getNode(ISD::BITCAST, DL, MVT::f16, Trunc);
+      }
+    } else {
+      SDValue FpToFp16 = DAG.getNode(ISD::FP_TO_FP16, DL, MVT::i32, Src);
+      SDValue Trunc = DAG.getNode(ISD::TRUNCATE, DL, MVT::i16, FpToFp16);
+      return DAG.getNode(ISD::BITCAST, DL, MVT::f16, Trunc);
+    }
----------------
kosarev wrote:

```suggestion
    if (!Subtarget->has16BitInsts()) {
      SDValue FpToFp16 = DAG.getNode(ISD::FP_TO_FP16, DL, MVT::i32, Src);
      SDValue Trunc = DAG.getNode(ISD::TRUNCATE, DL, MVT::i16, FpToFp16);
      return DAG.getNode(ISD::BITCAST, DL, MVT::f16, Trunc);
    }
    if (getTargetMachine().Options.UnsafeFPMath) {
      SDValue Flags = Op.getOperand(1);
      SDValue Src32 = DAG.getNode(ISD::FP_ROUND, DL, MVT::f32, Src, Flags);
      return DAG.getNode(ISD::FP_ROUND, DL, MVT::f16, Src32, Flags);
    }
    SDValue FpToFp16 = LowerF64ToF16(Src, DL, DAG);
    SDValue Trunc = DAG.getNode(ISD::TRUNCATE, DL, MVT::i16, FpToFp16);
    return DAG.getNode(ISD::BITCAST, DL, MVT::f16, Trunc);
```

https://github.com/llvm/llvm-project/pull/128911