[llvm] [AArch64][SVE] Use SVE for scalar FP converts in streaming[-compatible] functions (1/n) (PR #118505)

[Paul Walker via llvm-commits]

================
@@ -18989,13 +18989,75 @@ static SDValue performVectorCompareAndMaskUnaryOpCombine(SDNode *N,
   return SDValue();
 }
 
+/// Tries to replace scalar FP <-> INT conversions with SVE in streaming
+/// functions, this can help to reduce the number of fmovs to/from GPRs.
+static SDValue
+tryToReplaceScalarFPConversionWithSVE(SDNode *N, SelectionDAG &DAG,
+                                      const AArch64Subtarget *Subtarget) {
+  if (N->isStrictFPOpcode())
+    return SDValue();
+
+  if (!Subtarget->isSVEorStreamingSVEAvailable() ||
+      (!Subtarget->isStreaming() && !Subtarget->isStreamingCompatible()))
+    return SDValue();
+
+  auto isSupportedType = [](EVT VT) {
+    if (!VT.isSimple())
+      return false;
+    // There are SVE instructions that can convert to/from all pairs of these
+    // int and float types. Note: We don't bother with i8 or i16 as those are
+    // illegal types for scalars.
+    return is_contained({MVT::i32, MVT::i64, MVT::f16, MVT::f32, MVT::f64},
+                        VT.getSimpleVT().SimpleTy);
+  };
----------------
paulwalker-arm wrote:

By making this a post legalisation combine you likely don't need the lambda and can instead use `is_contained` in place. 

https://github.com/llvm/llvm-project/pull/118505