Index: lib/Support/Parallel.cpp
===================================================================
--- lib/Support/Parallel.cpp
+++ lib/Support/Parallel.cpp
@@ -23,7 +23,7 @@
 class Executor {
 public:
   virtual ~Executor() = default;
-  virtual void add(std::function<void()> func) = 0;
+  virtual void add(std::function<void()> F, parallel::detail::Latch *L) = 0;
 
   static Executor *getDefaultExecutor();
 };
@@ -91,9 +91,9 @@
     // Wait for ~Latch.
   }
 
-  void add(std::function<void()> F) override {
+  void add(std::function<void()> F, parallel::detail::Latch *L) override {
     std::unique_lock<std::mutex> Lock(Mutex);
-    WorkStack.push(F);
+    WorkStack.push({std::move(F), L});
     Lock.unlock();
     Cond.notify_one();
   }
@@ -105,16 +105,18 @@
       Cond.wait(Lock, [&] { return Stop || !WorkStack.empty(); });
       if (Stop)
         break;
-      auto Task = WorkStack.top();
+      auto Task = std::move(WorkStack.top());
       WorkStack.pop();
       Lock.unlock();
-      Task();
+      Task.first();
+      Task.second->dec();
     }
     Done.dec();
   }
 
   std::atomic<bool> Stop{false};
-  std::stack<std::function<void()>> WorkStack;
+  std::stack<std::pair<std::function<void()>, parallel::detail::Latch *>>
+      WorkStack;
   std::mutex Mutex;
   std::condition_variable Cond;
   parallel::detail::Latch Done;
@@ -130,9 +132,6 @@
 #if LLVM_ENABLE_THREADS
 void parallel::detail::TaskGroup::spawn(std::function<void()> F) {
   L.inc();
-  Executor::getDefaultExecutor()->add([&, F] {
-    F();
-    L.dec();
-  });
+  Executor::getDefaultExecutor()->add(std::move(F), &L);
 }
 #endif