Index: parallel-libs/trunk/streamexecutor/examples/Example.cpp
===================================================================
--- parallel-libs/trunk/streamexecutor/examples/Example.cpp
+++ parallel-libs/trunk/streamexecutor/examples/Example.cpp
@@ -121,13 +121,13 @@
       getOrDie(Device->allocateDeviceMemory<float>(ArraySize));
 
   // Run operations on a stream.
-  std::unique_ptr<se::Stream> Stream = getOrDie(Device->createStream());
-  Stream->thenCopyH2D<float>(HostX, X)
+  se::Stream Stream = getOrDie(Device->createStream());
+  Stream.thenCopyH2D<float>(HostX, X)
       .thenCopyH2D<float>(HostY, Y)
       .thenLaunch(ArraySize, 1, *Kernel, A, X, Y)
       .thenCopyD2H<float>(X, HostX);
   // Wait for the stream to complete.
-  se::dieIfError(Stream->blockHostUntilDone());
+  se::dieIfError(Stream.blockHostUntilDone());
 
   // Process output data in HostX.
   std::vector<float> ExpectedX = {4, 47, 90, 133};
Index: parallel-libs/trunk/streamexecutor/include/streamexecutor/Device.h
===================================================================
--- parallel-libs/trunk/streamexecutor/include/streamexecutor/Device.h
+++ parallel-libs/trunk/streamexecutor/include/streamexecutor/Device.h
@@ -50,7 +50,8 @@
                                       std::move(*MaybeKernelHandle));
   }
 
-  Expected<std::unique_ptr<Stream>> createStream();
+  /// Creates a stream object for this device.
+  Expected<Stream> createStream();
 
   /// Allocates an array of ElementCount entries of type T in device memory.
   template <typename T>
Index: parallel-libs/trunk/streamexecutor/include/streamexecutor/Stream.h
===================================================================
--- parallel-libs/trunk/streamexecutor/include/streamexecutor/Stream.h
+++ parallel-libs/trunk/streamexecutor/include/streamexecutor/Stream.h
@@ -61,19 +61,22 @@
 public:
   explicit Stream(std::unique_ptr<PlatformStreamHandle> PStream);
 
+  Stream(Stream &&Other) = default;
+  Stream &operator=(Stream &&Other) = default;
+
   ~Stream();
 
   /// Returns whether any error has occurred while entraining work on this
   /// stream.
   bool isOK() const {
-    llvm::sys::ScopedReader ReaderLock(ErrorMessageMutex);
+    llvm::sys::ScopedReader ReaderLock(*ErrorMessageMutex);
     return !ErrorMessage;
   }
 
   /// Returns the status created by the first error that occurred while
   /// entraining work on this stream.
   Error getStatus() const {
-    llvm::sys::ScopedReader ReaderLock(ErrorMessageMutex);
+    llvm::sys::ScopedReader ReaderLock(*ErrorMessageMutex);
     if (ErrorMessage)
       return make_error(*ErrorMessage);
     else
@@ -315,7 +318,7 @@
   /// Does not overwrite the error if it is already set.
   void setError(Error &&E) {
     if (E) {
-      llvm::sys::ScopedWriter WriterLock(ErrorMessageMutex);
+      llvm::sys::ScopedWriter WriterLock(*ErrorMessageMutex);
       if (!ErrorMessage)
         ErrorMessage = consumeAndGetMessage(std::move(E));
     }
@@ -325,7 +328,7 @@
   ///
   /// Does not overwrite the error if it is already set.
   void setError(llvm::Twine Message) {
-    llvm::sys::ScopedWriter WriterLock(ErrorMessageMutex);
+    llvm::sys::ScopedWriter WriterLock(*ErrorMessageMutex);
     if (!ErrorMessage)
       ErrorMessage = Message.str();
   }
@@ -337,9 +340,7 @@
   std::unique_ptr<PlatformStreamHandle> ThePlatformStream;
 
   /// Mutex that guards the error state flags.
-  ///
-  /// Mutable so that it can be obtained via const reader lock.
-  mutable llvm::sys::RWMutex ErrorMessageMutex;
+  std::unique_ptr<llvm::sys::RWMutex> ErrorMessageMutex;
 
   /// First error message for an operation in this stream or empty if there have
   /// been no errors.
Index: parallel-libs/trunk/streamexecutor/lib/Device.cpp
===================================================================
--- parallel-libs/trunk/streamexecutor/lib/Device.cpp
+++ parallel-libs/trunk/streamexecutor/lib/Device.cpp
@@ -27,7 +27,7 @@
 
 Device::~Device() = default;
 
-Expected<std::unique_ptr<Stream>> Device::createStream() {
+Expected<Stream> Device::createStream() {
   Expected<std::unique_ptr<PlatformStreamHandle>> MaybePlatformStream =
       PDevice->createStream();
   if (!MaybePlatformStream) {
@@ -35,7 +35,7 @@
   }
   assert((*MaybePlatformStream)->getDevice() == PDevice &&
          "an executor created a stream with a different stored executor");
-  return llvm::make_unique<Stream>(std::move(*MaybePlatformStream));
+  return Stream(std::move(*MaybePlatformStream));
 }
 
 } // namespace streamexecutor
Index: parallel-libs/trunk/streamexecutor/lib/Stream.cpp
===================================================================
--- parallel-libs/trunk/streamexecutor/lib/Stream.cpp
+++ parallel-libs/trunk/streamexecutor/lib/Stream.cpp
@@ -17,7 +17,8 @@
 namespace streamexecutor {
 
 Stream::Stream(std::unique_ptr<PlatformStreamHandle> PStream)
-    : PDevice(PStream->getDevice()), ThePlatformStream(std::move(PStream)) {}
+    : PDevice(PStream->getDevice()), ThePlatformStream(std::move(PStream)),
+      ErrorMessageMutex(llvm::make_unique<llvm::sys::RWMutex>()) {}
 
 Stream::~Stream() = default;