diff --git a/llvm/include/llvm/Support/Parallel.h b/llvm/include/llvm/Support/Parallel.h
--- a/llvm/include/llvm/Support/Parallel.h
+++ b/llvm/include/llvm/Support/Parallel.h
@@ -48,8 +48,13 @@
   }
 
   void dec() {
-    std::lock_guard<std::mutex> lock(Mutex);
-    if (--Count == 0)
+    bool Zero = false;
+    {
+      std::lock_guard<std::mutex> lock(Mutex);
+      if (--Count == 0)
+        Zero = true;
+    }
+    if (Zero)
       Cond.notify_all();
   }
 
diff --git a/llvm/lib/Support/Parallel.cpp b/llvm/lib/Support/Parallel.cpp
--- a/llvm/lib/Support/Parallel.cpp
+++ b/llvm/lib/Support/Parallel.cpp
@@ -151,7 +151,10 @@
 // lock, only allow the first TaskGroup to run tasks parallelly. In the scenario
 // of nested parallel_for_each(), only the outermost one runs parallelly.
 TaskGroup::TaskGroup() : Parallel(TaskGroupInstances++ == 0) {}
-TaskGroup::~TaskGroup() { --TaskGroupInstances; }
+TaskGroup::~TaskGroup() {
+  L.sync();
+  --TaskGroupInstances;
+}
 
 void TaskGroup::spawn(std::function<void()> F) {
   if (Parallel) {