Index: llvm/trunk/include/llvm/Support/ThreadPool.h
===================================================================
--- llvm/trunk/include/llvm/Support/ThreadPool.h
+++ llvm/trunk/include/llvm/Support/ThreadPool.h
@@ -20,6 +20,7 @@
 #include <future>
 
 #include <atomic>
+#include <cassert>
 #include <condition_variable>
 #include <functional>
 #include <memory>
@@ -35,10 +36,21 @@
 /// The pool keeps a vector of threads alive, waiting on a condition variable
 /// for some work to become available.
 class ThreadPool {
-public:
-  using TaskTy = std::function<void()>;
-  using PackagedTaskTy = std::packaged_task<void()>;
+  struct TaskBase {
+    virtual ~TaskBase() {}
+    virtual void execute() = 0;
+  };
+
+  template <typename ReturnType> struct TypedTask : public TaskBase {
+    explicit TypedTask(std::packaged_task<ReturnType()> Task)
+        : Task(std::move(Task)) {}
+
+    void execute() override { Task(); }
+
+    std::packaged_task<ReturnType()> Task;
+  };
 
+public:
   /// Construct a pool with the number of threads found by
   /// hardware_concurrency().
   ThreadPool();
@@ -52,7 +64,8 @@
   /// Asynchronous submission of a task to the pool. The returned future can be
   /// used to wait for the task to finish and is *non-blocking* on destruction.
   template <typename Function, typename... Args>
-  inline std::shared_future<void> async(Function &&F, Args &&... ArgList) {
+  inline std::shared_future<typename std::result_of<Function(Args...)>::type>
+  async(Function &&F, Args &&... ArgList) {
     auto Task =
         std::bind(std::forward<Function>(F), std::forward<Args>(ArgList)...);
     return asyncImpl(std::move(Task));
@@ -61,7 +74,8 @@
   /// Asynchronous submission of a task to the pool. The returned future can be
   /// used to wait for the task to finish and is *non-blocking* on destruction.
   template <typename Function>
-  inline std::shared_future<void> async(Function &&F) {
+  inline std::shared_future<typename std::result_of<Function()>::type>
+  async(Function &&F) {
     return asyncImpl(std::forward<Function>(F));
   }
 
@@ -72,13 +86,35 @@
 private:
   /// Asynchronous submission of a task to the pool. The returned future can be
   /// used to wait for the task to finish and is *non-blocking* on destruction.
-  std::shared_future<void> asyncImpl(TaskTy F);
+  template <typename TaskTy>
+  std::shared_future<typename std::result_of<TaskTy()>::type>
+  asyncImpl(TaskTy &&Task) {
+    typedef decltype(Task()) ResultTy;
+
+    /// Wrap the Task in a packaged_task to return a future object.
+    std::packaged_task<ResultTy()> PackagedTask(std::move(Task));
+    auto Future = PackagedTask.get_future();
+    std::unique_ptr<TaskBase> TB =
+        llvm::make_unique<TypedTask<ResultTy>>(std::move(PackagedTask));
+
+    {
+      // Lock the queue and push the new task
+      std::unique_lock<std::mutex> LockGuard(QueueLock);
+
+      // Don't allow enqueueing after disabling the pool
+      assert(EnableFlag && "Queuing a thread during ThreadPool destruction");
+
+      Tasks.push(std::move(TB));
+    }
+    QueueCondition.notify_one();
+    return Future.share();
+  }
 
   /// Threads in flight
   std::vector<llvm::thread> Threads;
 
   /// Tasks waiting for execution in the pool.
-  std::queue<PackagedTaskTy> Tasks;
+  std::queue<std::unique_ptr<TaskBase>> Tasks;
 
   /// Locking and signaling for accessing the Tasks queue.
   std::mutex QueueLock;
Index: llvm/trunk/lib/Support/ThreadPool.cpp
===================================================================
--- llvm/trunk/lib/Support/ThreadPool.cpp
+++ llvm/trunk/lib/Support/ThreadPool.cpp
@@ -32,7 +32,7 @@
   for (unsigned ThreadID = 0; ThreadID < ThreadCount; ++ThreadID) {
     Threads.emplace_back([&] {
       while (true) {
-        PackagedTaskTy Task;
+        std::unique_ptr<TaskBase> Task;
         {
           std::unique_lock<std::mutex> LockGuard(QueueLock);
           // Wait for tasks to be pushed in the queue
@@ -54,7 +54,7 @@
           Tasks.pop();
         }
         // Run the task we just grabbed
-        Task();
+        Task->execute();
 
         {
           // Adjust `ActiveThreads`, in case someone waits on ThreadPool::wait()
@@ -79,23 +79,6 @@
                            [&] { return !ActiveThreads && Tasks.empty(); });
 }
 
-std::shared_future<void> ThreadPool::asyncImpl(TaskTy Task) {
-  /// Wrap the Task in a packaged_task to return a future object.
-  PackagedTaskTy PackagedTask(std::move(Task));
-  auto Future = PackagedTask.get_future();
-  {
-    // Lock the queue and push the new task
-    std::unique_lock<std::mutex> LockGuard(QueueLock);
-
-    // Don't allow enqueueing after disabling the pool
-    assert(EnableFlag && "Queuing a thread during ThreadPool destruction");
-
-    Tasks.push(std::move(PackagedTask));
-  }
-  QueueCondition.notify_one();
-  return Future.share();
-}
-
 // The destructor joins all threads, waiting for completion.
 ThreadPool::~ThreadPool() {
   {
Index: llvm/trunk/unittests/Support/ThreadPool.cpp
===================================================================
--- llvm/trunk/unittests/Support/ThreadPool.cpp
+++ llvm/trunk/unittests/Support/ThreadPool.cpp
@@ -147,6 +147,25 @@
   ASSERT_EQ(2, i.load());
 }
 
+TEST_F(ThreadPoolTest, TaskWithResult) {
+  CHECK_UNSUPPORTED();
+  // By making only 1 thread in the pool the two tasks are serialized with
+  // respect to each other, which means that the second one must return 2.
+  ThreadPool Pool{1};
+  std::atomic_int i{0};
+  Pool.async([this, &i] {
+    waitForMainThread();
+    ++i;
+  });
+  // Force the future using get()
+  std::shared_future<int> Future = Pool.async([&i] { return ++i; });
+  ASSERT_EQ(0, i.load());
+  setMainThreadReady();
+  int Result = Future.get();
+  ASSERT_EQ(2, i.load());
+  ASSERT_EQ(2, Result);
+}
+
 TEST_F(ThreadPoolTest, PoolDestruction) {
   CHECK_UNSUPPORTED();
   // Test that we are waiting on destruction