[Support] Reduce allocations in parallelForEach with move

llvm/lib/Support/Parallel.cpp

public:
   };
   struct Deleter {
     static void call(void *Ptr) { ((ThreadPoolExecutor *)Ptr)->stop(); }
   };
 
   void add(std::function<void()> F) override {
     {
       std::lock_guard<std::mutex> Lock(Mutex);
-      WorkStack.push(F);
+      WorkStack.push(std::move(F));
     }
     Cond.notify_one();
   }
 
 private:
   void work(ThreadPoolStrategy S, unsigned ThreadID) {
     S.apply_thread_strategy(ThreadID);
     while (true) {
       std::unique_lock<std::mutex> Lock(Mutex);
       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();
     }
   }
 
   std::atomic<bool> Stop{false};
   std::stack<std::function<void()>> WorkStack;
TaskGroup::~TaskGroup() {
   // instances count.
   L.sync();
   --TaskGroupInstances;
 }
 
 void TaskGroup::spawn(std::function<void()> F) {
   if (Parallel) {
     L.inc();
-    Executor::getDefaultExecutor()->add([&, F] {
+    Executor::getDefaultExecutor()->add([&, F = std::move(F)] {
       F();
       L.dec();
     });
   } else {
     F();
   }
 }