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
@@ -40,7 +40,10 @@
 
 public:
   explicit Latch(uint32_t Count = 0) : Count(Count) {}
-  ~Latch() { sync(); }
+  ~Latch() {
+    // Ensure at least that sync() was called.
+    assert(Count == 0);
+  }
 
   void inc() {
     std::lock_guard<std::mutex> lock(Mutex);
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 +151,12 @@
 // 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() {
+  // We must ensure that all the workloads have finished before decrementing the
+  // instances count.
+  L.sync();
+  --TaskGroupInstances;
+}
 
 void TaskGroup::spawn(std::function<void()> F) {
   if (Parallel) {