[DDG] Data Dependence Graph - Topological Sort (Memory Leak Fix)

Summary:
This fixes the memory leak in bec37c3fc766a7b97f8c52c181c325fd47b75259
and re-delivers the reverted patch.
In this patch the DDG DAG is sorted topologically to put the
nodes in the graph in the order that would satisfy all
dependencies. This helps transformations that would like to
generate code based on the DDG. Since the DDG is a DAG a
reverse-post-order traversal would give us the topological
ordering. This patch also sorts the basic blocks passed to
the builder based on program order to ensure that the
dependencies are computed in the correct direction.

Authored By: bmahjour

Reviewer: Meinersbur, fhahn, myhsu, xtian, dmgreen, kbarton, jdoerfert

Reviewed By: Meinersbur

Subscribers: ychen, arphaman, simoll, a.elovikov, mgorny, hiraditya, jfb, wuzish, llvm-commits, jsji, Whitney, etiotto, ppc-slack

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70609

8 files changed, 417 insertions, 355 deletions

diff --git a/llvm/include/llvm/Analysis/DDG.h b/llvm/include/llvm/Analysis/DDG.h
index 7a572afccd6..22df60efd84 100644
--- a/llvm/include/llvm/Analysis/DDG.h
+++ b/llvm/include/llvm/Analysis/DDG.h
@@ -300,6 +300,7 @@ using DDGInfo = DependenceGraphInfo<DDGNode>;
 
 /// Data Dependency Graph
 class DataDependenceGraph : public DDGBase, public DDGInfo {
+  friend AbstractDependenceGraphBuilder<DataDependenceGraph>;
   friend class DDGBuilder;
 
 public:
@@ -311,7 +312,7 @@ public:
   DataDependenceGraph(DataDependenceGraph &&G)
       : DDGBase(std::move(G)), DDGInfo(std::move(G)) {}
   DataDependenceGraph(Function &F, DependenceInfo &DI);
-  DataDependenceGraph(const Loop &L, DependenceInfo &DI);
+  DataDependenceGraph(Loop &L, LoopInfo &LI, DependenceInfo &DI);
   ~DataDependenceGraph();
 
   /// If node \p N belongs to a pi-block return a pointer to the pi-block,
@@ -381,6 +382,12 @@ public:
     return *E;
   }
 
+  const NodeListType &getNodesInPiBlock(const DDGNode &N) final override {
+    auto *PiNode = dyn_cast<const PiBlockDDGNode>(&N);
+    assert(PiNode && "Expected a pi-block node.");
+    return PiNode->getNodes();
+  }
+
   bool shouldCreatePiBlocks() const final override;
 };
 
diff --git a/llvm/include/llvm/Analysis/DependenceGraphBuilder.h b/llvm/include/llvm/Analysis/DependenceGraphBuilder.h
index 876ccbc5c9a..99465ef39a0 100644
--- a/llvm/include/llvm/Analysis/DependenceGraphBuilder.h
+++ b/llvm/include/llvm/Analysis/DependenceGraphBuilder.h
@@ -59,6 +59,7 @@ public:
     createMemoryDependencyEdges();
     createAndConnectRootNode();
     createPiBlocks();
+    sortNodesTopologically();
   }
 
   /// Create fine grained nodes. These are typically atomic nodes that
@@ -84,6 +85,9 @@ public:
   /// the dependence graph into an acyclic graph.
   void createPiBlocks();
 
+  /// Topologically sort the graph nodes.
+  void sortNodesTopologically();
+
 protected:
   /// Create the root node of the graph.
   virtual NodeType &createRootNode() = 0;
@@ -104,6 +108,10 @@ protected:
   /// Create a rooted edge going from \p Src to \p Tgt .
   virtual EdgeType &createRootedEdge(NodeType &Src, NodeType &Tgt) = 0;
 
+  /// Given a pi-block node, return a vector of all the nodes contained within
+  /// it.
+  virtual const NodeListType &getNodesInPiBlock(const NodeType &N) = 0;
+
   /// Deallocate memory of edge \p E.
   virtual void destroyEdge(EdgeType &E) { delete &E; }
 
diff --git a/llvm/lib/Analysis/DDG.cpp b/llvm/lib/Analysis/DDG.cpp
index 82ccea06f28..90ce13e6f65 100644
--- a/llvm/lib/Analysis/DDG.cpp
+++ b/llvm/lib/Analysis/DDG.cpp
@@ -9,7 +9,9 @@
 // The implementation for the data dependence graph.
 //===----------------------------------------------------------------------===//
 #include "llvm/Analysis/DDG.h"
+#include "llvm/ADT/SCCIterator.h"
 #include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/LoopIterator.h"
 #include "llvm/Support/CommandLine.h"
 
 using namespace llvm;
@@ -179,19 +181,28 @@ using BasicBlockListType = SmallVector<BasicBlock *, 8>;
 
 DataDependenceGraph::DataDependenceGraph(Function &F, DependenceInfo &D)
     : DependenceGraphInfo(F.getName().str(), D) {
+  // Put the basic blocks in program order for correct dependence
+  // directions.
   BasicBlockListType BBList;
-  for (auto &BB : F.getBasicBlockList())
-    BBList.push_back(&BB);
+  for (auto &SCC : make_range(scc_begin(&F), scc_end(&F)))
+    for (BasicBlock * BB : SCC)
+      BBList.push_back(BB);
+  std::reverse(BBList.begin(), BBList.end());
   DDGBuilder(*this, D, BBList).populate();
 }
 
-DataDependenceGraph::DataDependenceGraph(const Loop &L, DependenceInfo &D)
+DataDependenceGraph::DataDependenceGraph(Loop &L, LoopInfo &LI,
+                                         DependenceInfo &D)
     : DependenceGraphInfo(Twine(L.getHeader()->getParent()->getName() + "." +
                                 L.getHeader()->getName())
                               .str(),
                           D) {
+  // Put the basic blocks in program order for correct dependence
+  // directions.
+  LoopBlocksDFS DFS(&L);
+  DFS.perform(&LI);
   BasicBlockListType BBList;
-  for (BasicBlock *BB : L.blocks())
+  for (BasicBlock *BB : make_range(DFS.beginRPO(), DFS.endRPO()))
     BBList.push_back(BB);
   DDGBuilder(*this, D, BBList).populate();
 }
@@ -259,7 +270,7 @@ DDGAnalysis::Result DDGAnalysis::run(Loop &L, LoopAnalysisManager &AM,
                                      LoopStandardAnalysisResults &AR) {
   Function *F = L.getHeader()->getParent();
   DependenceInfo DI(F, &AR.AA, &AR.SE, &AR.LI);
-  return std::make_unique<DataDependenceGraph>(L, DI);
+  return std::make_unique<DataDependenceGraph>(L, AR.LI, DI);
 }
 AnalysisKey DDGAnalysis::Key;
 
diff --git a/llvm/lib/Analysis/DependenceGraphBuilder.cpp b/llvm/lib/Analysis/DependenceGraphBuilder.cpp
index 115f5d6e814..98bb09d792b 100644
--- a/llvm/lib/Analysis/DependenceGraphBuilder.cpp
+++ b/llvm/lib/Analysis/DependenceGraphBuilder.cpp
@@ -353,5 +353,34 @@ void AbstractDependenceGraphBuilder<G>::createMemoryDependencyEdges() {
   }
 }
 
+template <class G>
+void AbstractDependenceGraphBuilder<G>::sortNodesTopologically() {
+
+  // If we don't create pi-blocks, then we may not have a DAG.
+  if (!shouldCreatePiBlocks())
+    return;
+
+  SmallVector<NodeType *, 64> NodesInPO;
+  using NodeKind = typename NodeType::NodeKind;
+  for (NodeType *N : post_order(&Graph)) {
+    if (N->getKind() == NodeKind::PiBlock) {
+      // Put members of the pi-block right after the pi-block itself, for
+      // convenience.
+      const NodeListType &PiBlockMembers = getNodesInPiBlock(*N);
+      NodesInPO.insert(NodesInPO.end(), PiBlockMembers.begin(),
+                       PiBlockMembers.end());
+    }
+    NodesInPO.push_back(N);
+  }
+
+  size_t OldSize = Graph.Nodes.size();
+  Graph.Nodes.clear();
+  for (NodeType *N : reverse(NodesInPO))
+    Graph.Nodes.push_back(N);
+  if (Graph.Nodes.size() != OldSize)
+    assert(false &&
+           "Expected the number of nodes to stay the same after the sort");
+}
+
 template class llvm::AbstractDependenceGraphBuilder<DataDependenceGraph>;
 template class llvm::DependenceGraphInfo<DDGNode>;
diff --git a/llvm/test/Analysis/DDG/basic-a.ll b/llvm/test/Analysis/DDG/basic-a.ll
index 920e71f6717..a52e8c258f5 100644
--- a/llvm/test/Analysis/DDG/basic-a.ll
+++ b/llvm/test/Analysis/DDG/basic-a.ll
@@ -1,7 +1,44 @@
 ; RUN: opt < %s -disable-output "-passes=print<ddg>" 2>&1 | FileCheck %s
 
 ; CHECK-LABEL: 'DDG' for loop 'test1.for.body':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
+
+; CHECK: Node Address:[[PI:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT: --- start of nodes in pi-block ---
+; CHECK-NEXT: Node Address:[[N10:0x[0-9a-f]*]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %inc = add i64 %i.02, 1
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N11:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N11]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test1.for.body ], [ 0, %test1.for.body.preheader ]
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N10]]
+; CHECK-NEXT: --- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N1:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N7]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %exitcond = icmp ne i64 %inc, %n
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    br i1 %exitcond, label %test1.for.body, label %for.end.loopexit
+; CHECK-NEXT: Edges:none!
+
+; CHECK: Node Address:[[N6]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %arrayidx1 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N1]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
 ; CHECK-NEXT: Edges:
@@ -23,12 +60,6 @@
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %add = fadd float %0, %conv
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N6:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx1 = getelementptr inbounds float, float* %a, i64 %i.02
-; CHECK-NEXT: Edges:
 ; CHECK-NEXT:  [def-use] to [[N5]]
 
 ; CHECK: Node Address:[[N5]]:single-instruction
@@ -36,36 +67,6 @@
 ; CHECK-NEXT:    store float %add, float* %arrayidx1, align 4
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N7:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %exitcond = icmp ne i64 %inc, %n
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N8]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %exitcond, label %test1.for.body, label %for.end.loopexit
-; CHECK-NEXT: Edges:none!
-
-; CHECK: Node Address:[[N9:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT: --- start of nodes in pi-block ---
-; CHECK-NEXT: Node Address:[[N10:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %i.02, 1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N11:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N11]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test1.for.body ], [ 0, %test1.for.body.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N10]]
-; CHECK-NEXT: --- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N1]]
-; CHECK-NEXT:  [def-use] to [[N6]]
-; CHECK-NEXT:  [def-use] to [[N7]]
-
 
 ;; No memory dependencies.
 ;; void test1(unsigned long n, float * restrict a, float * restrict b) {
@@ -96,78 +97,80 @@ for.end:                                          ; preds = %test1.for.body, %en
 
 
 ; CHECK-LABEL: 'DDG' for loop 'test2.for.body':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK: Node Address:[[PI:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT: --- start of nodes in pi-block ---
+; CHECK: Node Address:[[N11:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
+; CHECK-NEXT:    %inc = add i64 %i.02, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N4:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N12]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx1 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test2.for.body ], [ 0, %test2.for.body.preheader ]
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N11]]
+; CHECK-NEXT: --- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N1:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N5]]:single-instruction
+; CHECK: Node Address:[[N8]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %1 = load float, float* %arrayidx1, align 4
+; CHECK-NEXT:    %exitcond = icmp ne i64 %inc, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N3]]
-; CHECK-NEXT:  [memory] to [[N6:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N3]]:single-instruction
+; CHECK: Node Address:[[N9]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %add = fadd float %0, %1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N6]]
+; CHECK-NEXT:    br i1 %exitcond, label %test2.for.body, label %for.end.loopexit
+; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N7:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N7]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %arrayidx2 = getelementptr inbounds float, float* %a, i64 %i.02
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N6]]
+; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N6]]:single-instruction
+; CHECK: Node Address:[[N4]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    store float %add, float* %arrayidx2, align 4
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %arrayidx1 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N8:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N5]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %exitcond = icmp ne i64 %inc, %n
+; CHECK-NEXT:    %1 = load float, float* %arrayidx1, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
+; CHECK-NEXT:  [memory] to [[N6]]
 
-; CHECK: Node Address:[[N9]]:single-instruction
+; CHECK: Node Address:[[N1]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %exitcond, label %test2.for.body, label %for.end.loopexit
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N10:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT: --- start of nodes in pi-block ---
-; CHECK: Node Address:[[N11:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N2]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %i.02, 1
+; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N3]]
 
-; CHECK: Node Address:[[N12]]:single-instruction
+; CHECK: Node Address:[[N3]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test2.for.body ], [ 0, %test2.for.body.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N11]]
-; CHECK-NEXT: --- end of nodes in pi-block ---
+; CHECK-NEXT:    %add = fadd float %0, %1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N1]]
-; CHECK-NEXT:  [def-use] to [[N4]]
-; CHECK-NEXT:  [def-use] to [[N7]]
-; CHECK-NEXT:  [def-use] to [[N8]]
+; CHECK-NEXT:  [def-use] to [[N6]]
+
+; CHECK: Node Address:[[N6]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    store float %add, float* %arrayidx2, align 4
+; CHECK-NEXT: Edges:none!
+
 
 
 ;; Loop-independent memory dependencies.
diff --git a/llvm/test/Analysis/DDG/basic-b.ll b/llvm/test/Analysis/DDG/basic-b.ll
index f83f7fe92f3..757c706193a 100644
--- a/llvm/test/Analysis/DDG/basic-b.ll
+++ b/llvm/test/Analysis/DDG/basic-b.ll
@@ -1,19 +1,45 @@
 ; RUN: opt < %s -disable-output "-passes=print<ddg>" 2>&1 | FileCheck %s
 
 ; CHECK-LABEL: 'DDG' for loop 'test1.for.body':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
+
+; CHECK: Node Address:[[N9:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N13:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
+; CHECK-NEXT:    %inc = add i64 %i.02, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N14:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK: Node Address:[[N14]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
+; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %test1.for.body.preheader ]
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N13]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N1:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N7]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %cmp = icmp ult i64 %inc, %sub
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    br i1 %cmp, label %test1.for.body, label %for.end.loopexit
+; CHECK-NEXT: Edges:none!
+
+; CHECK: Node Address:[[N6]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
 ; CHECK-NEXT: Edges:
 ; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N4:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N4]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %sub1 = add i64 %i.02, -1
 ; CHECK-NEXT: Edges:
@@ -25,22 +51,17 @@
 ; CHECK-NEXT: Edges:
 ; CHECK-NEXT:  [def-use] to [[N3]]
 
-; CHECK: Node Address:[[N6:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N1]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N3]]
+; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N7:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N2]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp = icmp ult i64 %inc, %sub
+; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N8]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp, label %test1.for.body, label %for.end.loopexit
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:  [def-use] to [[N3]]
 
 ; CHECK: Node Address:[[N3]]:pi-block
 ; CHECK-NEXT: --- start of nodes in pi-block ---
@@ -64,25 +85,6 @@
 ; CHECK-NEXT:--- end of nodes in pi-block ---
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N9:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N13:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %i.02, 1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N14:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N14]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %test1.for.body.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N13]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N1]]
-; CHECK-NEXT:  [def-use] to [[N4]]
-; CHECK-NEXT:  [def-use] to [[N6]]
-; CHECK-NEXT:  [def-use] to [[N7]]
 
 
 ;; Loop-carried dependence requiring edge-reversal to expose a cycle
@@ -117,19 +119,45 @@ for.end:                                          ; preds = %test1.for.body, %en
 }
 
 ; CHECK-LABEL: 'DDG' for loop 'test2.for.body':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
+
+; CHECK: Node Address:[[N11:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N12:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
+; CHECK-NEXT:    %inc = add i64 %i.02, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N13:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK: Node Address:[[N13]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
+; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %test2.for.body.preheader ]
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N12]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N1:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N9]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %cmp = icmp ult i64 %inc, %sub
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N10:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N10]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    br i1 %cmp, label %test2.for.body, label %for.end.loopexit
+; CHECK-NEXT: Edges:none!
+
+; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N4:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N4]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %add1 = add i64 %i.02, 1
 ; CHECK-NEXT: Edges:
@@ -145,57 +173,33 @@ for.end:                                          ; preds = %test1.for.body, %en
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %1 = load float, float* %arrayidx2, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N3]]
-; CHECK-NEXT:  [memory] to [[N7:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
+; CHECK-NEXT:  [memory] to [[N7]]
 
-; CHECK: Node Address:[[N3]]:single-instruction
+; CHECK: Node Address:[[N1]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %add = fadd float %0, %1
+; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N7]]
+; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N8:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N2]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
+; CHECK-NEXT:    %0 = load float, float* %arrayidx, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N7]]
+; CHECK-NEXT:  [def-use] to [[N3]]
 
-; CHECK: Node Address:[[N7]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    store float %add, float* %arrayidx3, align 4
-; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N9:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N3]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp = icmp ult i64 %inc, %sub
+; CHECK-NEXT:    %add = fadd float %0, %1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N10:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N7]]
 
-; CHECK: Node Address:[[N10]]:single-instruction
+; CHECK: Node Address:[[N7]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp, label %test2.for.body, label %for.end.loopexit
+; CHECK-NEXT:    store float %add, float* %arrayidx3, align 4
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N11:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N12:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %i.02, 1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N13:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N13]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %test2.for.body.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N12]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N1]]
-; CHECK-NEXT:  [def-use] to [[N4]]
-; CHECK-NEXT:  [def-use] to [[N8]]
-; CHECK-NEXT:  [def-use] to [[N9]]
-
 
 ;; Forward loop-carried dependence *not* causing a cycle.
 ;; void test2(unsigned long n, float * restrict a, float * restrict b) {
diff --git a/llvm/test/Analysis/DDG/basic-loopnest.ll b/llvm/test/Analysis/DDG/basic-loopnest.ll
index aded488ef23..41c2cbbdc7a 100644
--- a/llvm/test/Analysis/DDG/basic-loopnest.ll
+++ b/llvm/test/Analysis/DDG/basic-loopnest.ll
@@ -2,73 +2,65 @@
 
 
 ; CHECK-LABEL: 'DDG' for loop 'test1.for.cond1.preheader':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %sub = add i64 %n, -1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
-; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N3]]:single-instruction
+; CHECK: Node Address:[[N28:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N29:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp21 = icmp ult i64 1, %sub
+; CHECK-NEXT:    %inc = add i64 %j.02, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N4]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp21, label %for.body4.preheader, label %for.inc12
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:  [def-use] to [[N30:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N5:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N30]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %0 = mul nsw i64 %i.04, %n
+; CHECK-NEXT:    %j.02 = phi i64 [ %inc, %for.body4 ], [ 1, %for.body4.preheader ]
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N6]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %0
+; CHECK-NEXT:  [def-use] to [[N29]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
 ; CHECK-NEXT: Edges:
 ; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N13:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N16:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N7]]:single-instruction
+; CHECK: Node Address:[[N13]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx5 = getelementptr inbounds float, float* %arrayidx, i64 %j.02
+; CHECK-NEXT:    %sub7 = add i64 %j.02, -1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK: Node Address:[[N25:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N26:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %1 = load float, float* %arrayidx5, align 4
+; CHECK-NEXT:    %inc13 = add i64 %i.04, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N27:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N10:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N27]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %2 = mul nsw i64 %i.04, %n
+; CHECK-NEXT:    %i.04 = phi i64 [ %inc13, %for.inc12 ], [ 0, %test1.for.cond1.preheader.preheader ]
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N11:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N11]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx6 = getelementptr inbounds float, float* %a, i64 %2
+; CHECK-NEXT:  [def-use] to [[N26]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N10:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N14:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N18:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N13:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N18]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %sub7 = add i64 %j.02, -1
+; CHECK-NEXT:    %exitcond = icmp ne i64 %inc13, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N12]]
+; CHECK-NEXT:  [def-use] to [[N19:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N12]]:single-instruction
+; CHECK: Node Address:[[N19]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx8 = getelementptr inbounds float, float* %arrayidx6, i64 %sub7
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9]]
+; CHECK-NEXT:    br i1 %exitcond, label %test1.for.cond1.preheader, label %for.end14.loopexit
+; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N14:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N14]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %4 = mul nsw i64 %i.04, %n
 ; CHECK-NEXT: Edges:
@@ -78,45 +70,55 @@
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %arrayidx10 = getelementptr inbounds float, float* %a, i64 %4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N16:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N16]]
 
 ; CHECK: Node Address:[[N16]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %arrayidx11 = getelementptr inbounds float, float* %arrayidx10, i64 %j.02
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9]]
+; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK: Node Address:[[N10]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp2 = icmp ult i64 %inc, %sub
+; CHECK-NEXT:    %2 = mul nsw i64 %i.04, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N17:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N11:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N17]]:single-instruction
+; CHECK: Node Address:[[N11]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp2, label %for.body4, label %for.inc12.loopexit
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %arrayidx6 = getelementptr inbounds float, float* %a, i64 %2
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N12]]
 
-; CHECK: Node Address:[[N18:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N12]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %exitcond = icmp ne i64 %inc13, %n
+; CHECK-NEXT:    %arrayidx8 = getelementptr inbounds float, float* %arrayidx6, i64 %sub7
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N19:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N9]]
 
-; CHECK: Node Address:[[N19]]:single-instruction
+; CHECK: Node Address:[[N5]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %exitcond, label %test1.for.cond1.preheader, label %for.end14.loopexit
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %0 = mul nsw i64 %i.04, %n
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N20:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N6]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br label %for.body4
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %0
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N7]]
 
-; CHECK: Node Address:[[N21:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N7]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br label %for.inc12
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %arrayidx5 = getelementptr inbounds float, float* %arrayidx, i64 %j.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %1 = load float, float* %arrayidx5, align 4
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N9]]
 
 ; CHECK: Node Address:[[N9]]:pi-block
 ; CHECK-NEXT:--- start of nodes in pi-block ---
@@ -140,46 +142,44 @@
 ; CHECK-NEXT:--- end of nodes in pi-block ---
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N25:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N26:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N21:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc13 = add i64 %i.04, 1
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N27:0x[0-9a-f]*]]
+; CHECK-NEXT:    br label %for.inc12
+; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N27]]:single-instruction
+; CHECK: Node Address:[[N20:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.04 = phi i64 [ %inc13, %for.inc12 ], [ 0, %test1.for.cond1.preheader.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N26]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N5]]
-; CHECK-NEXT:  [def-use] to [[N10]]
-; CHECK-NEXT:  [def-use] to [[N14]]
-; CHECK-NEXT:  [def-use] to [[N18]]
+; CHECK-NEXT:    br label %for.body4
+; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N28:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N29:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %j.02, 1
+; CHECK-NEXT:    %sub = add i64 %n, -1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N30:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N2]]
+; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N30]]:single-instruction
+; CHECK: Node Address:[[N3]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %j.02 = phi i64 [ %inc, %for.body4 ], [ 1, %for.body4.preheader ]
+; CHECK-NEXT:    %cmp21 = icmp ult i64 1, %sub
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N29]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
+; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N4]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    br i1 %cmp21, label %for.body4.preheader, label %for.inc12
+; CHECK-NEXT: Edges:none!
+
+; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %cmp2 = icmp ult i64 %inc, %sub
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N7]]
-; CHECK-NEXT:  [def-use] to [[N13]]
-; CHECK-NEXT:  [def-use] to [[N16]]
-; CHECK-NEXT:  [def-use] to [[N2]]
+; CHECK-NEXT:  [def-use] to [[N17:0x[0-9a-f]*]]
 
+; CHECK: Node Address:[[N17]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    br i1 %cmp2, label %for.body4, label %for.inc12.loopexit
+; CHECK-NEXT: Edges:none!
 
 
 ;; This test has a cycle.
@@ -232,49 +232,83 @@ for.end14:                                        ; preds = %for.inc12, %entry
 
 
 ; CHECK-LABEL: 'DDG' for loop 'test2.for.cond1.preheader':
-; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
+
+; CHECK: Node Address:[[PI1:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N28:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %sub = add i64 %n, -1
+; CHECK-NEXT:    %inc = add i64 %j.02, 1
 ; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N29:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N29]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %j.02 = phi i64 [ %inc, %for.body4 ], [ 1, %for.body4.preheader ]
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N28]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N13:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N18:0x[0-9a-f]*]]
 ; CHECK-NEXT:  [def-use] to [[N2:0x[0-9a-f]*]]
-; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N3]]:single-instruction
+; CHECK: Node Address:[[N13]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp21 = icmp ult i64 1, %sub
+; CHECK-NEXT:    %add7 = add i64 %j.02, 1
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N4]]:single-instruction
+; CHECK: Node Address:[[N24:0x[0-9a-f]*]]:pi-block
+; CHECK-NEXT:--- start of nodes in pi-block ---
+; CHECK: Node Address:[[N25:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp21, label %for.body4.preheader, label %for.inc12
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %inc13 = add i64 %i.04, 1
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N26:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N5:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N26]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %0 = mul nsw i64 %i.04, %n
+; CHECK-NEXT:    %i.04 = phi i64 [ %inc13, %for.inc12 ], [ 0, %test2.for.cond1.preheader.preheader ]
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N25]]
+; CHECK-NEXT:--- end of nodes in pi-block ---
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N5:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N10:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N16:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N20:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N6]]:single-instruction
+; CHECK: Node Address:[[N20]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %0
+; CHECK-NEXT:    %exitcond = icmp ne i64 %inc13, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N7:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N21:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N7]]:single-instruction
+; CHECK: Node Address:[[N21]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx5 = getelementptr inbounds float, float* %arrayidx, i64 %j.02
+; CHECK-NEXT:    br i1 %exitcond, label %test2.for.cond1.preheader, label %for.end14.loopexit
+; CHECK-NEXT: Edges:none!
+
+; CHECK: Node Address:[[N16]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %4 = mul nsw i64 %i.04, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N17:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N8]]:single-instruction
+; CHECK: Node Address:[[N17]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %1 = load float, float* %arrayidx5, align 4
+; CHECK-NEXT:    %arrayidx10 = getelementptr inbounds float, float* %a, i64 %4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N18]]
 
-; CHECK: Node Address:[[N10:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N18]]:single-instruction
+; CHECK-NEXT: Instructions:
+; CHECK-NEXT:    %arrayidx11 = getelementptr inbounds float, float* %arrayidx10, i64 %j.02
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N15:0x[0-9a-f]*]]
+
+; CHECK: Node Address:[[N10]]:single-instruction
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %2 = mul nsw i64 %i.04, %n
 ; CHECK-NEXT: Edges:
@@ -284,12 +318,6 @@ for.end14:                                        ; preds = %for.inc12, %entry
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %arrayidx6 = getelementptr inbounds float, float* %a, i64 %2
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N12:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N13:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %add7 = add i64 %j.02, 1
-; CHECK-NEXT: Edges:
 ; CHECK-NEXT:  [def-use] to [[N12]]
 
 ; CHECK: Node Address:[[N12]]:single-instruction
@@ -302,58 +330,47 @@ for.end14:                                        ; preds = %for.inc12, %entry
 ; CHECK-NEXT: Instructions:
 ; CHECK-NEXT:    %3 = load float, float* %arrayidx8, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N9]]
-; CHECK-NEXT:  [memory] to [[N15:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N9:0x[0-9a-f]*]]
+; CHECK-NEXT:  [memory] to [[N15]]
 
-; CHECK: Node Address:[[N9]]:single-instruction
+; CHECK: Node Address:[[N5]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %add = fadd float %1, %3
+; CHECK-NEXT:    %0 = mul nsw i64 %i.04, %n
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N15]]
+; CHECK-NEXT:  [def-use] to [[N6:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N16:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N6]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %4 = mul nsw i64 %i.04, %n
+; CHECK-NEXT:    %arrayidx = getelementptr inbounds float, float* %b, i64 %0
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N17:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N7]]
 
-; CHECK: Node Address:[[N17]]:single-instruction
+; CHECK: Node Address:[[N7]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx10 = getelementptr inbounds float, float* %a, i64 %4
+; CHECK-NEXT:    %arrayidx5 = getelementptr inbounds float, float* %arrayidx, i64 %j.02
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N18:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N8:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N18]]:single-instruction
+; CHECK: Node Address:[[N8]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %arrayidx11 = getelementptr inbounds float, float* %arrayidx10, i64 %j.02
+; CHECK-NEXT:    %1 = load float, float* %arrayidx5, align 4
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N15]]
-
-; CHECK: Node Address:[[N15]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    store float %add, float* %arrayidx11, align 4
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:  [def-use] to [[N9]]
 
-; CHECK: Node Address:[[N2]]:single-instruction
+; CHECK: Node Address:[[N9]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %cmp2 = icmp ult i64 %inc, %sub
+; CHECK-NEXT:    %add = fadd float %1, %3
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N19:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N15]]
 
-; CHECK: Node Address:[[N19]]:single-instruction
+; CHECK: Node Address:[[N15]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %cmp2, label %for.body4, label %for.inc12.loopexit
+; CHECK-NEXT:    store float %add, float* %arrayidx11, align 4
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N20:0x[0-9a-f]*]]:single-instruction
-; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %exitcond = icmp ne i64 %inc13, %n
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N21:0x[0-9a-f]*]]
-
-; CHECK: Node Address:[[N21]]:single-instruction
+; CHECK: Node Address:[[N23:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br i1 %exitcond, label %test2.for.cond1.preheader, label %for.end14.loopexit
+; CHECK-NEXT:    br label %for.inc12
 ; CHECK-NEXT: Edges:none!
 
 ; CHECK: Node Address:[[N22:0x[0-9a-f]*]]:single-instruction
@@ -361,50 +378,34 @@ for.end14:                                        ; preds = %for.inc12, %entry
 ; CHECK-NEXT:    br label %for.body4
 ; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N23:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    br label %for.inc12
-; CHECK-NEXT: Edges:none!
+; CHECK-NEXT:    %sub = add i64 %n, -1
+; CHECK-NEXT: Edges:
+; CHECK-NEXT:  [def-use] to [[N2]]
+; CHECK-NEXT:  [def-use] to [[N3:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N24:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N25:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N3]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc13 = add i64 %i.04, 1
+; CHECK-NEXT:    %cmp21 = icmp ult i64 1, %sub
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N26:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N4:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N26]]:single-instruction
+; CHECK: Node Address:[[N4]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %i.04 = phi i64 [ %inc13, %for.inc12 ], [ 0, %test2.for.cond1.preheader.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N25]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N5]]
-; CHECK-NEXT:  [def-use] to [[N10]]
-; CHECK-NEXT:  [def-use] to [[N16]]
-; CHECK-NEXT:  [def-use] to [[N20]]
+; CHECK-NEXT:    br i1 %cmp21, label %for.body4.preheader, label %for.inc12
+; CHECK-NEXT: Edges:none!
 
-; CHECK: Node Address:[[N27:0x[0-9a-f]*]]:pi-block
-; CHECK-NEXT:--- start of nodes in pi-block ---
-; CHECK: Node Address:[[N28:0x[0-9a-f]*]]:single-instruction
+; CHECK: Node Address:[[N2]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %inc = add i64 %j.02, 1
+; CHECK-NEXT:    %cmp2 = icmp ult i64 %inc, %sub
 ; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N29:0x[0-9a-f]*]]
+; CHECK-NEXT:  [def-use] to [[N19:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N29]]:single-instruction
+; CHECK: Node Address:[[N19]]:single-instruction
 ; CHECK-NEXT: Instructions:
-; CHECK-NEXT:    %j.02 = phi i64 [ %inc, %for.body4 ], [ 1, %for.body4.preheader ]
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N28]]
-; CHECK-NEXT:--- end of nodes in pi-block ---
-; CHECK-NEXT: Edges:
-; CHECK-NEXT:  [def-use] to [[N7]]
-; CHECK-NEXT:  [def-use] to [[N13]]
-; CHECK-NEXT:  [def-use] to [[N18]]
-; CHECK-NEXT:  [def-use] to [[N2]]
+; CHECK-NEXT:    br i1 %cmp2, label %for.body4, label %for.inc12.loopexit
+; CHECK-NEXT: Edges:none!
 
 
 ;; This test has no cycles.
diff --git a/llvm/test/Analysis/DDG/root-node.ll b/llvm/test/Analysis/DDG/root-node.ll
index 34d6437ef9c..868fb72d452 100644
--- a/llvm/test/Analysis/DDG/root-node.ll
+++ b/llvm/test/Analysis/DDG/root-node.ll
@@ -7,12 +7,11 @@
 ; CHECK-NEXT:  [rooted] to [[N1:0x[0-9a-f]*]]
 ; CHECK-NEXT:  [rooted] to [[N2:0x[0-9a-f]*]]
 
-; CHECK: Node Address:[[N1]]:pi-block
-; CHECK: %i2.03 = phi i64 [ 0, %for.body.lr.ph ], [ %inc2, %test1.for.body ]
-
 ; CHECK: Node Address:[[N2]]:pi-block
 ; CHECK: %i1.02 = phi i64 [ 0, %for.body.lr.ph ], [ %inc, %test1.for.body ]
 
+; CHECK: Node Address:[[N1]]:pi-block
+; CHECK: %i2.03 = phi i64 [ 0, %for.body.lr.ph ], [ %inc2, %test1.for.body ]
 
 ;; // Two separate components in the graph. Root node must link to both.
 ;; void test1(unsigned long n, float * restrict a, float * restrict b) {