[AArch64] Combine signext_inreg of setcc(... != splat(0))

Add the following fold AArch64 DAGCombine:
    Fold setcc_merge_zero(
            pred, insert_subvector(undef, signext_inreg(vNi1), 0),
                != splat(0))
         -> setcc_merge_zero(pred, insert_subvector(undef, shl(vNi1), 0),
                != splat(0))

as the comparison (!= 0) depends only on bit 0 of the input, the left
shift is sufficient.

Author: hazzlim

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -26097,6 +26097,17 @@ static SDValue performSetCCPunpkCombine(SDNode *N, SelectionDAG &DAG) {
   return SDValue();
 }
 
+static bool isSignExtInReg(const SDValue &V) {
+  if (V.getOpcode() != AArch64ISD::VASHR ||
+      V.getOperand(0).getOpcode() != AArch64ISD::VSHL)
+    return false;
+
+  unsigned BitWidth = V->getValueType(0).getScalarSizeInBits();
+  unsigned ShiftAmtR = V.getConstantOperandVal(1);
+  unsigned ShiftAmtL = V.getOperand(0).getConstantOperandVal(1);
+  return (ShiftAmtR == ShiftAmtL && ShiftAmtR == (BitWidth - 1));
+}
+
 static SDValue
 performSetccMergeZeroCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI) {
   assert(N->getOpcode() == AArch64ISD::SETCC_MERGE_ZERO &&
@@ -26137,6 +26148,27 @@ performSetccMergeZeroCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI) {
                          LHS->getOperand(0), Pred);
   }
 
+  //    setcc_merge_zero(
+  //       pred, insert_subvector(undef, signext_inreg(vNi1), 0), != splat(0))
+  // => setcc_merge_zero(
+  //       pred, insert_subvector(undef, shl(vNi1), 0), != splat(0))
+  if (Cond == ISD::SETNE && isZerosVector(RHS.getNode()) &&
+      LHS->getOpcode() == ISD::INSERT_SUBVECTOR && LHS.hasOneUse()) {
+    SDValue L0 = LHS->getOperand(0);
+    SDValue L1 = LHS->getOperand(1);
+    SDValue L2 = LHS->getOperand(2);
+
+    if (L0.getOpcode() == ISD::UNDEF && isNullConstant(L2) &&
+        isSignExtInReg(L1)) {
+      SDLoc DL(N);
+      SDValue Shl = L1.getOperand(0);
+      SDValue NewLHS = DAG.getNode(ISD::INSERT_SUBVECTOR, DL,
+                                   LHS.getValueType(), L0, Shl, L2);
+      return DAG.getNode(AArch64ISD::SETCC_MERGE_ZERO, DL, N->getValueType(0),
+                         Pred, NewLHS, RHS, N->getOperand(3));
+    }
+  }
+
   return SDValue();
 }