[PM] Add a new "lazy" call graph analysis pass for the new pass manager.

The primary motivation for this pass is to separate the call graph
analysis used by the new pass manager's CGSCC pass management from the
existing call graph analysis pass. That analysis pass is (somewhat
unfortunately) over-constrained by the existing CallGraphSCCPassManager
requirements. Those requirements make it *really* hard to cleanly layer
the needed functionality for the new pass manager on top of the existing
analysis.

However, there are also a bunch of things that the pass manager would
specifically benefit from doing differently from the existing call graph
analysis, and this new implementation tries to address several of them:

- Be lazy about scanning function definitions. The existing pass eagerly
  scans the entire module to build the initial graph. This new pass is
  significantly more lazy, and I plan to push this even further to
  maximize locality during CGSCC walks.
- Don't use a single synthetic node to partition functions with an
  indirect call from functions whose address is taken. This node creates
  a huge choke-point which would preclude good parallelization across
  the fanout of the SCC graph when we got to the point of looking at
  such changes to LLVM.
- Use a memory dense and lightweight representation of the call graph
  rather than value handles and tracking call instructions. This will
  require explicit update calls instead of some updates working
  transparently, but should end up being significantly more efficient.
  The explicit update calls ended up being needed in many cases for the
  existing call graph so we don't really lose anything.
- Doesn't explicitly model SCCs and thus doesn't provide an "identity"
  for an SCC which is stable across updates. This is essential for the
  new pass manager to work correctly.
- Only form the graph necessary for traversing all of the functions in
  an SCC friendly order. This is a much simpler graph structure and
  should be more memory dense. It does limit the ways in which it is
  appropriate to use this analysis. I wish I had a better name than
  "call graph". I've commented extensively this aspect.

This is still very much a WIP, in fact it is really just the initial
bits. But it is about the fourth version of the initial bits that I've
implemented with each of the others running into really frustrating
problms. This looks like it will actually work and I'd like to split the
actual complexity across commits for the sake of my reviewers. =] The
rest of the implementation along with lots of wiring will follow
somewhat more rapidly now that there is a good path forward.

Naturally, this doesn't impact any of the existing optimizer. This code
is specific to the new pass manager.

A bunch of thanks are deserved for the various folks that have helped
with the design of this, especially Nick Lewycky who actually sat with
me to go through the fundamentals of the final version here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200903 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 670 insertions, 0 deletions

diff --git a/include/llvm/Analysis/LazyCallGraph.h b/include/llvm/Analysis/LazyCallGraph.h
new file mode 100644
index 0000000000..d355b9cf5a
--- /dev/null
+++ b/include/llvm/Analysis/LazyCallGraph.h
@@ -0,0 +1,337 @@
+//===- LazyCallGraph.h - Analysis of a Module's call graph ------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+/// \file
+///
+/// Implements a lazy call graph analysis and related passes for the new pass
+/// manager.
+///
+/// NB: This is *not* a traditional call graph! It is a graph which models both
+/// the current calls and potential calls. As a consequence there are many
+/// edges in this call graph that do not correspond to a 'call' or 'invoke'
+/// instruction.
+///
+/// The primary use cases of this graph analysis is to facilitate iterating
+/// across the functions of a module in ways that ensure all callees are
+/// visited prior to a caller (given any SCC constraints), or vice versa. As
+/// such is it particularly well suited to organizing CGSCC optimizations such
+/// as inlining, outlining, argument promotion, etc. That is its primary use
+/// case and motivates the design. It may not be appropriate for other
+/// purposes. The use graph of functions or some other conservative analysis of
+/// call instructions may be interesting for optimizations and subsequent
+/// analyses which don't work in the context of an overly specified
+/// potential-call-edge graph.
+///
+/// To understand the specific rules and nature of this call graph analysis,
+/// see the documentation of the \c LazyCallGraph below.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_LAZY_CALL_GRAPH
+#define LLVM_ANALYSIS_LAZY_CALL_GRAPH
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/PointerUnion.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/Support/Allocator.h"
+#include <iterator>
+
+namespace llvm {
+class ModuleAnalysisManager;
+class PreservedAnalyses;
+class raw_ostream;
+
+/// \brief A lazily constructed view of the call graph of a module.
+///
+/// With the edges of this graph, the motivating constraint that we are
+/// attempting to maintain is that function-local optimization, CGSCC-local
+/// optimizations, and optimizations transforming a pair of functions connected
+/// by an edge in the graph, do not invalidate a bottom-up traversal of the SCC
+/// DAG. That is, no optimizations will delete, remove, or add an edge such
+/// that functions already visited in a bottom-up order of the SCC DAG are no
+/// longer valid to have visited, or such that functions not yet visited in
+/// a bottom-up order of the SCC DAG are not required to have already been
+/// visited.
+///
+/// Within this constraint, the desire is to minimize the merge points of the
+/// SCC DAG. The greater the fanout of the SCC DAG and the fewer merge points
+/// in the SCC DAG, the more independence there is in optimizing within it.
+/// There is a strong desire to enable parallelization of optimizations over
+/// the call graph, and both limited fanout and merge points will (artificially
+/// in some cases) limit the scaling of such an effort.
+///
+/// To this end, graph represents both direct and any potential resolution to
+/// an indirect call edge. Another way to think about it is that it represents
+/// both the direct call edges and any direct call edges that might be formed
+/// through static optimizations. Specifically, it considers taking the address
+/// of a function to be an edge in the call graph because this might be
+/// forwarded to become a direct call by some subsequent function-local
+/// optimization. The result is that the graph closely follows the use-def
+/// edges for functions. Walking "up" the graph can be done by looking at all
+/// of the uses of a function.
+///
+/// The roots of the call graph are the external functions and functions
+/// escaped into global variables. Those functions can be called from outside
+/// of the module or via unknowable means in the IR -- we may not be able to
+/// form even a potential call edge from a function body which may dynamically
+/// load the function and call it.
+///
+/// This analysis still requires updates to remain valid after optimizations
+/// which could potentially change the set of potential callees. The
+/// constraints it operates under only make the traversal order remain valid.
+///
+/// The entire analysis must be re-computed if full interprocedural
+/// optimizations run at any point. For example, globalopt completely
+/// invalidates the information in this analysis.
+///
+/// FIXME: This class is named LazyCallGraph in a lame attempt to distinguish
+/// it from the existing CallGraph. At some point, it is expected that this
+/// will be the only call graph and it will be renamed accordingly.
+class LazyCallGraph {
+public:
+  class Node;
+  typedef SmallVector<PointerUnion<Function *, Node *>, 4> NodeVectorT;
+  typedef SmallVectorImpl<PointerUnion<Function *, Node *> > NodeVectorImplT;
+
+  /// \brief A lazy iterator used for both the entry nodes and child nodes.
+  ///
+  /// When this iterator is dereferenced, if not yet available, a function will
+  /// be scanned for "calls" or uses of functions and its child information
+  /// will be constructed. All of these results are accumulated and cached in
+  /// the graph.
+  class iterator : public std::iterator<std::bidirectional_iterator_tag, Node *,
+                                        ptrdiff_t, Node *, Node *> {
+    friend class LazyCallGraph;
+    friend class LazyCallGraph::Node;
+    typedef std::iterator<std::bidirectional_iterator_tag, Node *, ptrdiff_t,
+                          Node *, Node *> BaseT;
+
+    /// \brief Nonce type to select the constructor for the end iterator.
+    struct IsAtEndT {};
+
+    LazyCallGraph &G;
+    NodeVectorImplT::iterator NI;
+
+    // Build the begin iterator for a node.
+    explicit iterator(LazyCallGraph &G, NodeVectorImplT &Nodes)
+        : G(G), NI(Nodes.begin()) {}
+
+    // Build the end iterator for a node. This is selected purely by overload.
+    iterator(LazyCallGraph &G, NodeVectorImplT &Nodes, IsAtEndT /*Nonce*/)
+        : G(G), NI(Nodes.end()) {}
+
+  public:
+    iterator(const iterator &Arg) : G(Arg.G), NI(Arg.NI) {}
+
+    iterator &operator=(iterator Arg) {
+      std::swap(Arg, *this);
+      return *this;
+    }
+
+    bool operator==(const iterator &Arg) { return NI == Arg.NI; }
+    bool operator!=(const iterator &Arg) { return !operator==(Arg); }
+
+    reference operator*() const {
+      if (NI->is<Node *>())
+        return NI->get<Node *>();
+
+      Function *F = NI->get<Function *>();
+      Node *ChildN = G.get(*F);
+      *NI = ChildN;
+      return ChildN;
+    }
+    pointer operator->() const { return operator*(); }
+
+    iterator &operator++() {
+      ++NI;
+      return *this;
+    }
+    iterator operator++(int) {
+      iterator prev = *this;
+      ++*this;
+      return prev;
+    }
+
+    iterator &operator--() {
+      --NI;
+      return *this;
+    }
+    iterator operator--(int) {
+      iterator next = *this;
+      --*this;
+      return next;
+    }
+  };
+
+  /// \brief Construct a graph for the given module.
+  ///
+  /// This sets up the graph and computes all of the entry points of the graph.
+  /// No function definitions are scanned until their nodes in the graph are
+  /// requested during traversal.
+  LazyCallGraph(Module &M);
+
+  /// \brief Copy constructor.
+  ///
+  /// This does a deep copy of the graph. It does no verification that the
+  /// graph remains valid for the module. It is also relatively expensive.
+  LazyCallGraph(const LazyCallGraph &G);
+
+#if LLVM_HAS_RVALUE_REFERENCES
+  /// \brief Move constructor.
+  ///
+  /// This is a deep move. It leaves G in an undefined but destroyable state.
+  /// Any other operation on G is likely to fail.
+  LazyCallGraph(LazyCallGraph &&G);
+#endif
+
+  iterator begin() { return iterator(*this, EntryNodes); }
+  iterator end() { return iterator(*this, EntryNodes, iterator::IsAtEndT()); }
+
+  /// \brief Lookup a function in the graph which has already been scanned and
+  /// added.
+  Node *lookup(const Function &F) const { return NodeMap.lookup(&F); }
+
+  /// \brief Get a graph node for a given function, scanning it to populate the
+  /// graph data as necessary.
+  Node *get(Function &F) {
+    Node *&N = NodeMap[&F];
+    if (N)
+      return N;
+
+    return insertInto(F, N);
+  }
+
+private:
+  Module &M;
+
+  /// \brief Allocator that holds all the call graph nodes.
+  SpecificBumpPtrAllocator<Node> BPA;
+
+  /// \brief Maps function->node for fast lookup.
+  DenseMap<const Function *, Node *> NodeMap;
+
+  /// \brief The entry nodes to the graph.
+  ///
+  /// These nodes are reachable through "external" means. Put another way, they
+  /// escape at the module scope.
+  NodeVectorT EntryNodes;
+
+  /// \brief Set of the entry nodes to the graph.
+  SmallPtrSet<Function *, 4> EntryNodeSet;
+
+  /// \brief Helper to insert a new function, with an already looked-up entry in
+  /// the NodeMap.
+  Node *insertInto(Function &F, Node *&MappedN);
+
+  /// \brief Helper to copy a node from another graph into this one.
+  Node *copyInto(const Node &OtherN);
+
+#if LLVM_HAS_RVALUE_REFERENCES
+  /// \brief Helper to move a node from another graph into this one.
+  Node *moveInto(Node &&OtherN);
+#endif
+};
+
+/// \brief A node in the call graph.
+///
+/// This represents a single node. It's primary roles are to cache the list of
+/// callees, de-duplicate and provide fast testing of whether a function is
+/// a callee, and facilitate iteration of child nodes in the graph.
+class LazyCallGraph::Node {
+  friend LazyCallGraph;
+
+  LazyCallGraph &G;
+  Function &F;
+  mutable NodeVectorT Callees;
+  SmallPtrSet<Function *, 4> CalleeSet;
+
+  /// \brief Basic constructor implements the scanning of F into Callees and
+  /// CalleeSet.
+  Node(LazyCallGraph &G, Function &F);
+
+  /// \brief Constructor used when copying a node from one graph to another.
+  Node(LazyCallGraph &G, const Node &OtherN);
+
+#if LLVM_HAS_RVALUE_REFERENCES
+  /// \brief Constructor used when moving a node from one graph to another.
+  Node(LazyCallGraph &G, Node &&OtherN);
+#endif
+
+public:
+  typedef LazyCallGraph::iterator iterator;
+
+  Function &getFunction() const {
+    return F;
+  };
+
+  iterator begin() const { return iterator(G, Callees); }
+  iterator end() const { return iterator(G, Callees, iterator::IsAtEndT()); }
+
+  /// Equality is defined as address equality.
+  bool operator==(const Node &N) const { return this == &N; }
+  bool operator!=(const Node &N) const { return !operator==(N); }
+};
+
+// Provide GraphTraits specializations for call graphs.
+template <> struct GraphTraits<LazyCallGraph::Node *> {
+  typedef LazyCallGraph::Node NodeType;
+  typedef LazyCallGraph::iterator ChildIteratorType;
+
+  static NodeType *getEntryNode(NodeType *N) { return N; }
+  static ChildIteratorType child_begin(NodeType *N) { return N->begin(); }
+  static ChildIteratorType child_end(NodeType *N) { return N->end(); }
+};
+template <> struct GraphTraits<LazyCallGraph *> {
+  typedef LazyCallGraph::Node NodeType;
+  typedef LazyCallGraph::iterator ChildIteratorType;
+
+  static NodeType *getEntryNode(NodeType *N) { return N; }
+  static ChildIteratorType child_begin(NodeType *N) { return N->begin(); }
+  static ChildIteratorType child_end(NodeType *N) { return N->end(); }
+};
+
+/// \brief An analysis pass which computes the call graph for a module.
+class LazyCallGraphAnalysis {
+public:
+  /// \brief Inform generic clients of the result type.
+  typedef LazyCallGraph Result;
+
+  static void *ID() { return (void *)&PassID; }
+
+  /// \brief Compute the \c LazyCallGraph for a the module \c M.
+  ///
+  /// This just builds the set of entry points to the call graph. The rest is
+  /// built lazily as it is walked.
+  LazyCallGraph run(Module *M) { return LazyCallGraph(*M); }
+
+private:
+  static char PassID;
+};
+
+/// \brief A pass which prints the call graph to a \c raw_ostream.
+///
+/// This is primarily useful for testing the analysis.
+class LazyCallGraphPrinterPass {
+  raw_ostream &OS;
+
+public:
+  explicit LazyCallGraphPrinterPass(raw_ostream &OS);
+
+  PreservedAnalyses run(Module *M, ModuleAnalysisManager *AM);
+
+  static StringRef name() { return "LazyCallGraphPrinterPass"; }
+};
+
+}
+
+#endif
diff --git a/lib/Analysis/CMakeLists.txt b/lib/Analysis/CMakeLists.txt
index 3624aac450..c6d4573885 100644
--- a/lib/Analysis/CMakeLists.txt
+++ b/lib/Analysis/CMakeLists.txt
@@ -23,6 +23,7 @@ add_llvm_library(LLVMAnalysis
   InstructionSimplify.cpp
   Interval.cpp
   IntervalPartition.cpp
+  LazyCallGraph.cpp
   LazyValueInfo.cpp
   LibCallAliasAnalysis.cpp
   LibCallSemantics.cpp
diff --git a/lib/Analysis/LazyCallGraph.cpp b/lib/Analysis/LazyCallGraph.cpp
new file mode 100644
index 0000000000..b89bf70b43
--- /dev/null
+++ b/lib/Analysis/LazyCallGraph.cpp
@@ -0,0 +1,195 @@
+//===- LazyCallGraph.cpp - Analysis of a Module's call graph --------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/LazyCallGraph.h"
+#include "llvm/ADT/SCCIterator.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/Support/CallSite.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/InstVisitor.h"
+
+using namespace llvm;
+
+static void findCallees(
+    SmallVectorImpl<Constant *> &Worklist, SmallPtrSetImpl<Constant *> &Visited,
+    SmallVectorImpl<PointerUnion<Function *, LazyCallGraph::Node *> > &Callees,
+    SmallPtrSetImpl<Function *> &CalleeSet) {
+  while (!Worklist.empty()) {
+    Constant *C = Worklist.pop_back_val();
+
+    if (Function *F = dyn_cast<Function>(C)) {
+      // Note that we consider *any* function with a definition to be a viable
+      // edge. Even if the function's definition is subject to replacement by
+      // some other module (say, a weak definition) there may still be
+      // optimizations which essentially speculate based on the definition and
+      // a way to check that the specific definition is in fact the one being
+      // used. For example, this could be done by moving the weak definition to
+      // a strong (internal) definition and making the weak definition be an
+      // alias. Then a test of the address of the weak function against the new
+      // strong definition's address would be an effective way to determine the
+      // safety of optimizing a direct call edge.
+      if (!F->isDeclaration() && CalleeSet.insert(F))
+          Callees.push_back(F);
+      continue;
+    }
+
+    for (User::value_op_iterator OI = C->value_op_begin(),
+                                 OE = C->value_op_end();
+         OI != OE; ++OI)
+      if (Visited.insert(cast<Constant>(*OI)))
+        Worklist.push_back(cast<Constant>(*OI));
+  }
+}
+
+LazyCallGraph::Node::Node(LazyCallGraph &G, Function &F) : G(G), F(F) {
+  SmallVector<Constant *, 16> Worklist;
+  SmallPtrSet<Constant *, 16> Visited;
+  // Find all the potential callees in this function. First walk the
+  // instructions and add every operand which is a constant to the worklist.
+  for (Function::iterator BBI = F.begin(), BBE = F.end(); BBI != BBE; ++BBI)
+    for (BasicBlock::iterator II = BBI->begin(), IE = BBI->end(); II != IE;
+         ++II)
+      for (User::value_op_iterator OI = II->value_op_begin(),
+                                   OE = II->value_op_end();
+           OI != OE; ++OI)
+        if (Constant *C = dyn_cast<Constant>(*OI))
+          if (Visited.insert(C))
+            Worklist.push_back(C);
+
+  // We've collected all the constant (and thus potentially function or
+  // function containing) operands to all of the instructions in the function.
+  // Process them (recursively) collecting every function found.
+  findCallees(Worklist, Visited, Callees, CalleeSet);
+}
+
+LazyCallGraph::Node::Node(LazyCallGraph &G, const Node &OtherN)
+    : G(G), F(OtherN.F), CalleeSet(OtherN.CalleeSet) {
+  // Loop over the other node's callees, adding the Function*s to our list
+  // directly, and recursing to add the Node*s.
+  Callees.reserve(OtherN.Callees.size());
+  for (NodeVectorImplT::iterator OI = OtherN.Callees.begin(),
+                                 OE = OtherN.Callees.end();
+       OI != OE; ++OI)
+    if (Function *Callee = OI->dyn_cast<Function *>())
+      Callees.push_back(Callee);
+    else
+      Callees.push_back(G.copyInto(*OI->get<Node *>()));
+}
+
+#if LLVM_HAS_RVALUE_REFERENCES
+LazyCallGraph::Node::Node(LazyCallGraph &G, Node &&OtherN)
+    : G(G), F(OtherN.F), Callees(std::move(OtherN.Callees)),
+      CalleeSet(std::move(OtherN.CalleeSet)) {
+  // Loop over our Callees. They've been moved from another node, but we need
+  // to move the Node*s to live under our bump ptr allocator.
+  for (NodeVectorImplT::iterator CI = Callees.begin(), CE = Callees.end();
+       CI != CE; ++CI)
+    if (Node *ChildN = CI->dyn_cast<Node *>())
+      *CI = G.moveInto(std::move(*ChildN));
+}
+#endif
+
+LazyCallGraph::LazyCallGraph(Module &M) : M(M) {
+  for (Module::iterator FI = M.begin(), FE = M.end(); FI != FE; ++FI)
+    if (!FI->isDeclaration() && !FI->hasLocalLinkage())
+      if (EntryNodeSet.insert(&*FI))
+        EntryNodes.push_back(&*FI);
+
+  // Now add entry nodes for functions reachable via initializers to globals.
+  SmallVector<Constant *, 16> Worklist;
+  SmallPtrSet<Constant *, 16> Visited;
+  for (Module::global_iterator GI = M.global_begin(), GE = M.global_end(); GI != GE; ++GI)
+    if (GI->hasInitializer())
+      if (Visited.insert(GI->getInitializer()))
+        Worklist.push_back(GI->getInitializer());
+
+  findCallees(Worklist, Visited, EntryNodes, EntryNodeSet);
+}
+
+LazyCallGraph::LazyCallGraph(const LazyCallGraph &G)
+    : M(G.M), EntryNodeSet(G.EntryNodeSet) {
+  EntryNodes.reserve(EntryNodes.size());
+  for (NodeVectorImplT::iterator EI = EntryNodes.begin(),
+                                 EE = EntryNodes.end();
+       EI != EE; ++EI)
+    if (Function *Callee = EI->dyn_cast<Function *>())
+      EntryNodes.push_back(Callee);
+    else
+      EntryNodes.push_back(copyInto(*EI->get<Node *>()));
+}
+
+#if LLVM_HAS_RVALUE_REFERENCES
+// FIXME: This would be crazy simpler if BumpPtrAllocator were movable without
+// invalidating any of the allocated memory. We should make that be the case at
+// some point and delete this.
+LazyCallGraph::LazyCallGraph(LazyCallGraph &&G)
+    : M(G.M), EntryNodes(std::move(G.EntryNodes)),
+      EntryNodeSet(std::move(G.EntryNodeSet)) {
+  // Loop over our EntryNodes. They've been moved from another graph, but we
+  // need to move the Node*s to live under our bump ptr allocator.
+  for (NodeVectorImplT::iterator EI = EntryNodes.begin(), EE = EntryNodes.end();
+       EI != EE; ++EI)
+    if (Node *EntryN = EI->dyn_cast<Node *>())
+      *EI = G.moveInto(std::move(*EntryN));
+}
+#endif
+
+LazyCallGraph::Node *LazyCallGraph::insertInto(Function &F, Node *&MappedN) {
+  return new (MappedN = BPA.Allocate()) Node(*this, F);
+}
+
+LazyCallGraph::Node *LazyCallGraph::copyInto(const Node &OtherN) {
+  Node *&N = NodeMap[&OtherN.F];
+  if (N)
+    return N;
+
+  return new (N = BPA.Allocate()) Node(*this, OtherN);
+}
+
+#if LLVM_HAS_RVALUE_REFERENCES
+LazyCallGraph::Node *LazyCallGraph::moveInto(Node &&OtherN) {
+  Node *&N = NodeMap[&OtherN.F];
+  if (N)
+    return N;
+
+  return new (N = BPA.Allocate()) Node(*this, std::move(OtherN));
+}
+#endif
+
+char LazyCallGraphAnalysis::PassID;
+
+LazyCallGraphPrinterPass::LazyCallGraphPrinterPass(raw_ostream &OS) : OS(OS) {}
+
+static void printNodes(raw_ostream &OS, LazyCallGraph::Node &N,
+                       SmallPtrSetImpl<LazyCallGraph::Node *> &Printed) {
+  // Recurse depth first through the nodes.
+  for (LazyCallGraph::iterator I = N.begin(), E = N.end(); I != E; ++I)
+    if (Printed.insert(*I))
+      printNodes(OS, **I, Printed);
+
+  OS << "  Call edges in function: " << N.getFunction().getName() << "\n";
+  for (LazyCallGraph::iterator I = N.begin(), E = N.end(); I != E; ++I)
+    OS << "    -> " << I->getFunction().getName() << "\n";
+
+  OS << "\n";
+}
+
+PreservedAnalyses LazyCallGraphPrinterPass::run(Module *M, ModuleAnalysisManager *AM) {
+  LazyCallGraph &G = AM->getResult<LazyCallGraphAnalysis>(M);
+
+  OS << "Printing the call graph for module: " << M->getModuleIdentifier() << "\n\n";
+
+  SmallPtrSet<LazyCallGraph::Node *, 16> Printed;
+  for (LazyCallGraph::iterator I = G.begin(), E = G.end(); I != E; ++I)
+    if (Printed.insert(*I))
+      printNodes(OS, **I, Printed);
+
+  return PreservedAnalyses::all();
+}
diff --git a/test/Analysis/LazyCallGraph/basic.ll b/test/Analysis/LazyCallGraph/basic.ll
new file mode 100644
index 0000000000..ebadb75154
--- /dev/null
+++ b/test/Analysis/LazyCallGraph/basic.ll
@@ -0,0 +1,126 @@
+; RUN: opt -disable-output -passes=print-cg %s 2>&1 | FileCheck %s
+;
+; Basic validation of the call graph analysis used in the new pass manager.
+
+define void @f() {
+; CHECK-LABEL: Call edges in function: f
+; CHECK-NOT: ->
+
+entry:
+  ret void
+}
+
+; A bunch more functions just to make it easier to test several call edges at once.
+define void @f1() {
+  ret void
+}
+define void @f2() {
+  ret void
+}
+define void @f3() {
+  ret void
+}
+define void @f4() {
+  ret void
+}
+define void @f5() {
+  ret void
+}
+define void @f6() {
+  ret void
+}
+define void @f7() {
+  ret void
+}
+define void @f8() {
+  ret void
+}
+define void @f9() {
+  ret void
+}
+define void @f10() {
+  ret void
+}
+define void @f11() {
+  ret void
+}
+define void @f12() {
+  ret void
+}
+
+declare i32 @__gxx_personality_v0(...)
+
+define void @test0() {
+; CHECK-LABEL: Call edges in function: test0
+; CHECK-NEXT: -> f
+; CHECK-NOT: ->
+
+entry:
+  call void @f()
+  call void @f()
+  call void @f()
+  call void @f()
+  ret void
+}
+
+define void ()* @test1(void ()** %x) {
+; CHECK-LABEL: Call edges in function: test1
+; CHECK-NEXT: -> f12
+; CHECK-NEXT: -> f11
+; CHECK-NEXT: -> f10
+; CHECK-NEXT: -> f7
+; CHECK-NEXT: -> f9
+; CHECK-NEXT: -> f8
+; CHECK-NEXT: -> f6
+; CHECK-NEXT: -> f5
+; CHECK-NEXT: -> f4
+; CHECK-NEXT: -> f3
+; CHECK-NEXT: -> f2
+; CHECK-NEXT: -> f1
+; CHECK-NOT: ->
+
+entry:
+  br label %next
+
+dead:
+  br label %next
+
+next:
+  phi void ()* [ @f1, %entry ], [ @f2, %dead ]
+  select i1 true, void ()* @f3, void ()* @f4
+  store void ()* @f5, void ()** %x
+  call void @f6()
+  call void (void ()*, void ()*)* bitcast (void ()* @f7 to void (void ()*, void ()*)*)(void ()* @f8, void ()* @f9)
+  invoke void @f10() to label %exit unwind label %unwind
+
+exit:
+  ret void ()* @f11
+
+unwind:
+  %res = landingpad { i8*, i32 } personality i32 (...)* @__gxx_personality_v0
+          cleanup
+  resume { i8*, i32 } { i8* bitcast (void ()* @f12 to i8*), i32 42 }
+}
+
+@g = global void ()* @f1
+@g1 = global [4 x void ()*] [void ()* @f2, void ()* @f3, void ()* @f4, void ()* @f5]
+@g2 = global {i8, void ()*, i8} {i8 1, void ()* @f6, i8 2}
+@h = constant void ()* @f7
+
+define void @test2() {
+; CHECK-LABEL: Call edges in function: test2
+; CHECK-NEXT: -> f7
+; CHECK-NEXT: -> f6
+; CHECK-NEXT: -> f5
+; CHECK-NEXT: -> f4
+; CHECK-NEXT: -> f3
+; CHECK-NEXT: -> f2
+; CHECK-NEXT: -> f1
+; CHECK-NOT: ->
+
+  load i8** bitcast (void ()** @g to i8**)
+  load i8** bitcast (void ()** getelementptr ([4 x void ()*]* @g1, i32 0, i32 2) to i8**)
+  load i8** bitcast (void ()** getelementptr ({i8, void ()*, i8}* @g2, i32 0, i32 1) to i8**)
+  load i8** bitcast (void ()** @h to i8**)
+  ret void
+}
diff --git a/tools/opt/NewPMDriver.cpp b/tools/opt/NewPMDriver.cpp
index c25bd73cbc..fc4a1bf76c 100644
--- a/tools/opt/NewPMDriver.cpp
+++ b/tools/opt/NewPMDriver.cpp
@@ -16,6 +16,7 @@
 #include "NewPMDriver.h"
 #include "Passes.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/Bitcode/BitcodeWriterPass.h"
 #include "llvm/IR/IRPrintingPasses.h"
 #include "llvm/IR/LLVMContext.h"
@@ -35,6 +36,10 @@ bool llvm::runPassPipeline(StringRef Arg0, LLVMContext &Context, Module &M,
   FunctionAnalysisManager FAM;
   ModuleAnalysisManager MAM;
 
+  // FIXME: Lift this registration of analysis passes into a .def file adjacent
+  // to the one used to associate names with passes.
+  MAM.registerPass(LazyCallGraphAnalysis());
+
   // Cross register the analysis managers through their proxies.
   MAM.registerPass(FunctionAnalysisManagerModuleProxy(FAM));
   FAM.registerPass(ModuleAnalysisManagerFunctionProxy(MAM));
diff --git a/tools/opt/Passes.cpp b/tools/opt/Passes.cpp
index 36fe6ad126..ca143042f6 100644
--- a/tools/opt/Passes.cpp
+++ b/tools/opt/Passes.cpp
@@ -15,6 +15,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "Passes.h"
+#include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/IR/IRPrintingPasses.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Verifier.h"
@@ -43,6 +44,7 @@ struct NoOpFunctionPass {
 static bool isModulePassName(StringRef Name) {
   if (Name == "no-op-module") return true;
   if (Name == "print") return true;
+  if (Name == "print-cg") return true;
 
   return false;
 }
@@ -63,6 +65,10 @@ static bool parseModulePassName(ModulePassManager &MPM, StringRef Name) {
     MPM.addPass(PrintModulePass(dbgs()));
     return true;
   }
+  if (Name == "print-cg") {
+    MPM.addPass(LazyCallGraphPrinterPass(dbgs()));
+    return true;
+  }
   return false;
 }