[AArch64] Handle XAR with v1i64 operand types (#141754)

When converting ROTR(XOR(a, b)) to XAR(a, b), or ROTR(a, a) to XAR(a, zero)
we were not handling v1i64 types, meaning illegal copies get generated. This
addresses that by generating insert_subreg and extract_subreg for v1i64 to
keep the values with the correct types.

Fixes #141746

Author: davemgreen

llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp

@@ -4637,15 +4637,38 @@ bool AArch64DAGToDAGISel::trySelectXAR(SDNode *N) {
 
   if (!IsXOROperand) {
     SDValue Zero = CurDAG->getTargetConstant(0, DL, MVT::i64);
-    SDNode *MOV = CurDAG->getMachineNode(AArch64::MOVIv2d_ns, DL, VT, Zero);
+    SDNode *MOV =
+        CurDAG->getMachineNode(AArch64::MOVIv2d_ns, DL, MVT::v2i64, Zero);
     SDValue MOVIV = SDValue(MOV, 0);
     R1 = N1->getOperand(0);
     R2 = MOVIV;
   }
 
+  // If the input is a v1i64, widen to a v2i64 to use XAR.
+  assert((VT == MVT::v1i64 || VT == MVT::v2i64) && "Unexpected XAR type!");
+  if (VT == MVT::v1i64) {
+    EVT SVT = MVT::v2i64;
+    SDValue Undef =
+        SDValue(CurDAG->getMachineNode(AArch64::IMPLICIT_DEF, DL, SVT), 0);
+    SDValue DSub = CurDAG->getTargetConstant(AArch64::dsub, DL, MVT::i32);
+    R1 = SDValue(CurDAG->getMachineNode(AArch64::INSERT_SUBREG, DL, SVT, Undef,
+                                        R1, DSub),
+                 0);
+    if (R2.getValueType() == MVT::v1i64)
+      R2 = SDValue(CurDAG->getMachineNode(AArch64::INSERT_SUBREG, DL, SVT,
+                                          Undef, R2, DSub),
+                   0);
+  }
+
   SDValue Ops[] = {R1, R2, Imm};
-  CurDAG->SelectNodeTo(N, AArch64::XAR, N0.getValueType(), Ops);
+  SDNode *XAR = CurDAG->getMachineNode(AArch64::XAR, DL, MVT::v2i64, Ops);
 
+  if (VT == MVT::v1i64) {
+    SDValue DSub = CurDAG->getTargetConstant(AArch64::dsub, DL, MVT::i32);
+    XAR = CurDAG->getMachineNode(AArch64::EXTRACT_SUBREG, DL, VT,
+                                 SDValue(XAR, 0), DSub);
+  }
+  ReplaceNode(N, XAR);
   return true;
 }
 

llvm/test/CodeGen/AArch64/xar.ll

@@ -19,6 +19,26 @@ define <2 x i64> @xar(<2 x i64> %x, <2 x i64> %y) {
     ret <2 x i64> %b
 }
 
+define <1 x i64> @xar_v1i64(<1 x i64> %a, <1 x i64> %b) {
+; SHA3-LABEL: xar_v1i64:
+; SHA3:       // %bb.0:
+; SHA3-NEXT:    // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT:    // kill: def $d1 killed $d1 def $q1
+; SHA3-NEXT:    xar v0.2d, v0.2d, v1.2d, #63
+; SHA3-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT:    ret
+;
+; NOSHA3-LABEL: xar_v1i64:
+; NOSHA3:       // %bb.0:
+; NOSHA3-NEXT:    eor v1.8b, v0.8b, v1.8b
+; NOSHA3-NEXT:    shl d0, d1, #1
+; NOSHA3-NEXT:    usra d0, d1, #63
+; NOSHA3-NEXT:    ret
+  %v.val = xor <1 x i64> %a, %b
+  %fshl = tail call <1 x i64> @llvm.fshl.v1i64(<1 x i64> %v.val, <1 x i64> %v.val, <1 x i64> splat (i64 1))
+  ret <1 x i64> %fshl
+}
+
 define <2 x i64> @xar_instead_of_or1(<2 x i64> %r) {
 ; SHA3-LABEL: xar_instead_of_or1:
 ; SHA3:       // %bb.0: // %entry
@@ -37,6 +57,25 @@ entry:
   ret <2 x i64> %or
 }
 
+define <1 x i64> @xar_instead_of_or_v1i64(<1 x i64> %v.val) {
+; SHA3-LABEL: xar_instead_of_or_v1i64:
+; SHA3:       // %bb.0:
+; SHA3-NEXT:    movi v1.2d, #0000000000000000
+; SHA3-NEXT:    // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT:    xar v0.2d, v0.2d, v1.2d, #63
+; SHA3-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT:    ret
+;
+; NOSHA3-LABEL: xar_instead_of_or_v1i64:
+; NOSHA3:       // %bb.0:
+; NOSHA3-NEXT:    shl d1, d0, #1
+; NOSHA3-NEXT:    usra d1, d0, #63
+; NOSHA3-NEXT:    fmov d0, d1
+; NOSHA3-NEXT:    ret
+  %fshl = tail call <1 x i64> @llvm.fshl.v1i64(<1 x i64> %v.val, <1 x i64> %v.val, <1 x i64> splat (i64 1))
+  ret <1 x i64> %fshl
+}
+
 define <4 x i32> @xar_instead_of_or2(<4 x i32> %r) {
 ; SHA3-LABEL: xar_instead_of_or2:
 ; SHA3:       // %bb.0: // %entry