diff --git a/mlir/include/mlir/IR/Threading.h b/mlir/include/mlir/IR/Threading.h
--- a/mlir/include/mlir/IR/Threading.h
+++ b/mlir/include/mlir/IR/Threading.h
@@ -71,15 +71,10 @@
   // Otherwise, process the elements in parallel.
   llvm::ThreadPool &threadPool = context->getThreadPool();
   size_t numActions = std::min(numElements, threadPool.getThreadCount());
-  SmallVector<std::shared_future<void>> threadFutures;
-  threadFutures.reserve(numActions - 1);
   for (unsigned i = 1; i < numActions; ++i)
-    threadFutures.emplace_back(threadPool.async(processFn));
+    threadPool.async(processFn);
   processFn();
-
-  // Wait for all of the threads to finish.
-  for (std::shared_future<void> &future : threadFutures)
-    future.wait();
+  threadPool.wait();
   return failure(processingFailed);
 }