[ARM64] PR19792: Fix cycle in DAG after performPostLD1Combine

Povray and dealII currently assert with "Overran sorted position" in
AssignTopologicalOrder.  The problem is that performPostLD1Combine can
introduce cycles.

Consider:

(insert_vector_elt (INSERT_SUBREG undef,
                                  (load (add %vreg0, Constant<8>), undef),  <= A
                                  TargetConstant<2>),
                   (load %vreg0, undef),                                    <= B
                   Constant<1>)

This is turned into a LD1LANEpost node.  However the address in A is not a
valid user of the post-incremented address of B in LD1LANEpost.

llvm-svn: 209242

llvm/lib/Target/ARM64/ARM64ISelLowering.cpp

@@ -7298,6 +7298,7 @@ static SDValue performPostLD1Combine(SDNode *N,
   }
 
   SDValue Addr = LD->getOperand(1);
+  SDValue Vector = N->getOperand(0);
   // Search for a use of the address operand that is an increment.
   for (SDNode::use_iterator UI = Addr.getNode()->use_begin(), UE =
        Addr.getNode()->use_end(); UI != UE; ++UI) {
@@ -7310,6 +7311,10 @@ static SDValue performPostLD1Combine(SDNode *N,
     // would create a cycle.
     if (User->isPredecessorOf(LD) || LD->isPredecessorOf(User))
       continue;
+    // Also check that add is not used in the vector operand.  This would also
+    // create a cycle.
+    if (User->isPredecessorOf(Vector.getNode()))
+      continue;
 
     // If the increment is a constant, it must match the memory ref size.
     SDValue Inc = User->getOperand(User->getOperand(0) == Addr ? 1 : 0);
@@ -7324,7 +7329,7 @@ static SDValue performPostLD1Combine(SDNode *N,
     SmallVector<SDValue, 8> Ops;
     Ops.push_back(LD->getOperand(0));  // Chain
     if (IsLaneOp) {
-      Ops.push_back(N->getOperand(0)); // The vector to be inserted
+      Ops.push_back(Vector);           // The vector to be inserted
       Ops.push_back(N->getOperand(2)); // The lane to be inserted in the vector
     }
     Ops.push_back(Addr);

llvm/test/CodeGen/ARM64/indexed-vector-ldst-2.ll

@@ -0,0 +1,40 @@
+; RUN: llc %s
+
+; This used to assert with "Overran sorted position" in AssignTopologicalOrder
+; due to a cycle created in performPostLD1Combine.
+
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-apple-ios7.0.0"
+
+; Function Attrs: nounwind ssp
+define void @f(double* %P1) #0 {
+entry:
+  %arrayidx4 = getelementptr inbounds double* %P1, i64 1
+  %0 = load double* %arrayidx4, align 8, !tbaa !1
+  %1 = load double* %P1, align 8, !tbaa !1
+  %2 = insertelement <2 x double> undef, double %0, i32 0
+  %3 = insertelement <2 x double> %2, double %1, i32 1
+  %4 = fsub <2 x double> zeroinitializer, %3
+  %5 = fmul <2 x double> undef, %4
+  %6 = extractelement <2 x double> %5, i32 0
+  %cmp168 = fcmp olt double %6, undef
+  br i1 %cmp168, label %if.then172, label %return
+
+if.then172:                                       ; preds = %cond.end90
+  %7 = tail call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 false)
+  br label %return
+
+return:                                           ; preds = %if.then172, %cond.end90, %entry
+  ret void
+}
+
+; Function Attrs: nounwind readnone
+declare i64 @llvm.objectsize.i64.p0i8(i8*, i1) #1
+
+attributes #0 = { nounwind ssp "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone }
+
+!1 = metadata !{metadata !2, metadata !2, i64 0}
+!2 = metadata !{metadata !"double", metadata !3, i64 0}
+!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
+!4 = metadata !{metadata !"Simple C/C++ TBAA"}