[StreamExecutor] Fix allocateDeviceMemory

[jhen]

Summary

The return value from PlatformExecutor::allocateDeviceMemory needs to be
converted from Expected<GlobalDeviceMemoryBase> to
Expected<GlobalDeviceMemory<T>> in Executor::allocateDeviceMemory.

A similar bug is also fixed for Executor::allocateHostMemory.

Thanks to jprice for identifying this bug.

parallel-libs/trunk/streamexecutor/include/streamexecutor/Executor.h

getKernelImplementation(const MultiKernelLoaderSpec &Spec) {
     return nullptr;
   }
 
   Expected<std::unique_ptr<Stream>> createStream();
 
   /// Allocates an array of ElementCount entries of type T in device memory.
   template <typename T>
   Expected<GlobalDeviceMemory<T>> allocateDeviceMemory(size_t ElementCount) {
-    return PExecutor->allocateDeviceMemory(ElementCount * sizeof(T));
+    Expected<GlobalDeviceMemoryBase> MaybeBase =
+        PExecutor->allocateDeviceMemory(ElementCount * sizeof(T));
+    if (!MaybeBase)
+      return MaybeBase.takeError();
+    return GlobalDeviceMemory<T>(*MaybeBase);
   }
 
   /// Frees memory previously allocated with allocateDeviceMemory.
   template <typename T> Error freeDeviceMemory(GlobalDeviceMemory<T> Memory) {
     return PExecutor->freeDeviceMemory(Memory);
   }
 
   /// Allocates an array of ElementCount entries of type T in host memory.
   ///
   /// Host memory allocated by this function can be used for asynchronous memory
   /// copies on streams. See Stream::thenCopyD2H and Stream::thenCopyH2D.
   template <typename T> Expected<T *> allocateHostMemory(size_t ElementCount) {
-    return PExecutor->allocateHostMemory(ElementCount * sizeof(T));
+    Expected<void *> MaybeMemory =
+        PExecutor->allocateHostMemory(ElementCount * sizeof(T));
+    if (!MaybeMemory)
+      return MaybeMemory.takeError();
+    return static_cast<T *>(*MaybeMemory);
   }
 
   /// Frees memory previously allocated with allocateHostMemory.
   template <typename T> Error freeHostMemory(T *Memory) {
     return PExecutor->freeHostMemory(Memory);
   }
 
   /// Registers a previously allocated host array of type T for asynchronous

parallel-libs/trunk/streamexecutor/lib/unittests/ExecutorTest.cpp

se::Expected<void *> allocateHostMemory(size_t ByteCount) override {
     return std::malloc(ByteCount);
   }
 
   se::Error freeHostMemory(void *Memory) override {
     std::free(Memory);
     return se::Error::success();
   }
 
+  se::Error registerHostMemory(void *, size_t) override {
+    return se::Error::success();
+  }
+
+  se::Error unregisterHostMemory(void *) override {
+    return se::Error::success();
+  }
+
   se::Error synchronousCopyD2H(const se::GlobalDeviceMemoryBase &DeviceSrc,
                                size_t SrcByteOffset, void *HostDst,
                                size_t DstByteOffset,
                                size_t ByteCount) override {
     std::memcpy(static_cast<char *>(HostDst) + DstByteOffset,
                 static_cast<const char *>(DeviceSrc.getHandle()) +
                     SrcByteOffset,
                 ByteCount);
do {                                                                         \
     se::Error E__ = E;                                                         \
     EXPECT_TRUE(static_cast<bool>(E__));                                       \
     consumeError(std::move(E__));                                              \
   } while (false)
 
 using llvm::ArrayRef;
 using llvm::MutableArrayRef;
 
+TEST_F(ExecutorTest, AllocateAndFreeDeviceMemory) {
+  se::Expected<se::GlobalDeviceMemory<int>> MaybeMemory =
+      Executor.allocateDeviceMemory<int>(10);
+  EXPECT_TRUE(static_cast<bool>(MaybeMemory));
+  EXPECT_NO_ERROR(Executor.freeDeviceMemory(*MaybeMemory));
+}
+
+TEST_F(ExecutorTest, AllocateAndFreeHostMemory) {
+  se::Expected<int *> MaybeMemory = Executor.allocateHostMemory<int>(10);
+  EXPECT_TRUE(static_cast<bool>(MaybeMemory));
+  EXPECT_NO_ERROR(Executor.freeHostMemory(*MaybeMemory));
+}
+
+TEST_F(ExecutorTest, RegisterAndUnregisterHostMemory) {
+  std::vector<int> Data(10);
+  EXPECT_NO_ERROR(Executor.registerHostMemory(Data.data(), 10));
+  EXPECT_NO_ERROR(Executor.unregisterHostMemory(Data.data()));
+}
+
 // D2H tests
 
 TEST_F(ExecutorTest, SyncCopyD2HToMutableArrayRefByCount) {
   EXPECT_NO_ERROR(
       Executor.synchronousCopyD2H(DeviceA5, MutableArrayRef<int>(Host5), 5));
   for (int I = 0; I < 5; ++I) {
     EXPECT_EQ(HostA5[I], Host5[I]);
   }