GPUPlace to CUDAPlace (#6960)

paddle/framework/init.cc

@@ -54,7 +54,7 @@ bool InitDevices(const std::vector<std::string> &devices) {
 #ifdef PADDLE_WITH_CUDA
       auto pos = string::RFind(p, ':', string::Piece::npos);
       auto number = device.substr(pos + 1);
-      places.emplace_back(platform::GPUPlace(std::stoi(number)));
+      places.emplace_back(platform::CUDAPlace(std::stoi(number)));
 #else
       LOG(WARNING)
           << "'GPU' is not supported, Please re-compile with WITH_GPU option";

paddle/framework/lod_tensor.cc

@@ -224,7 +224,7 @@ void SerializeToStream(std::ostream &os, const LoDTensor &tensor,
       while (size != 0) {
         size_t size_to_write = std::min(kBufSize, static_cast<size_t>(size));
         memory::Copy(cpu, buf.get(),
-                     boost::get<platform::GPUPlace>(tensor.place()),
+                     boost::get<platform::CUDAPlace>(tensor.place()),
                      reinterpret_cast<const void *>(data), size_to_write,
                      gpu_dev_ctx.stream());
         gpu_dev_ctx.Wait();

paddle/framework/lod_tensor_test.cu

@@ -27,7 +27,7 @@ __global__ void test(size_t* a, int size) {
 
 TEST(LoDTensor, LoDInGPU) {
   paddle::framework::LoDTensor lod_tensor;
-  paddle::platform::GPUPlace place(0);
+  paddle::platform::CUDAPlace place(0);
 
   paddle::framework::LoD src_lod;
   src_lod.push_back(std::vector<size_t>{0, 2, 4, 6, 8, 10, 12, 14});

paddle/framework/op_kernel_type_test.cc

@@ -37,13 +37,13 @@ TEST(OpKernelType, Hash) {
   using OpKernelType = paddle::framework::OpKernelType;
   using DataType = paddle::framework::proto::DataType;
   using CPUPlace = paddle::platform::CPUPlace;
-  using GPUPlace = paddle::platform::GPUPlace;
+  using CUDAPlace = paddle::platform::CUDAPlace;
   using DataLayout = paddle::framework::DataLayout;
   using LibraryType = paddle::framework::LibraryType;
 
   OpKernelType op_kernel_type_1(DataType::FP32, CPUPlace(), DataLayout::kNCHW,
                                 LibraryType::kCUDNN);
-  OpKernelType op_kernel_type_2(DataType::FP32, GPUPlace(0), DataLayout::kNCHW,
+  OpKernelType op_kernel_type_2(DataType::FP32, CUDAPlace(0), DataLayout::kNCHW,
                                 LibraryType::kCUDNN);
 
   OpKernelType::Hash hasher;

paddle/framework/op_registry.h

@@ -188,7 +188,7 @@ class OpKernelRegistrar : public Registrar {
   }
 
 #define REGISTER_OP_CUDA_KERNEL(op_type, ...) \
-  REGISTER_OP_KERNEL(op_type, CUDA, ::paddle::platform::GPUPlace, __VA_ARGS__)
+  REGISTER_OP_KERNEL(op_type, CUDA, ::paddle::platform::CUDAPlace, __VA_ARGS__)
 
 #define REGISTER_OP_CPU_KERNEL(op_type, ...) \
   REGISTER_OP_KERNEL(op_type, CPU, ::paddle::platform::CPUPlace, __VA_ARGS__)

paddle/framework/tensor.md

@@ -71,7 +71,7 @@ private:
 ```
 
 ```c++
-typedef boost::variant<GpuPlace, CpuPlace> Place;
+typedef boost::variant<CUDAPlace, CpuPlace> Place;
 typedef boost::variant<Dim<1>, Dim<2>, Dim<3>, Dim<4>, Dim<5>,
                        Dim<6>, Dim<7>, Dim<8>, Dim<9>> DDimVar;
 typedef boost::variant<

paddle/framework/tensor_impl.h

@@ -125,11 +125,11 @@ inline void* Tensor::mutable_data(platform::Place place, std::type_index type) {
           boost::get<platform::CPUPlace>(place), size, type));
     } else if (platform::is_gpu_place(place)) {
 #ifndef PADDLE_WITH_CUDA
-      PADDLE_THROW("'GPUPlace' is not supported in CPU only device.");
+      PADDLE_THROW("'CUDAPlace' is not supported in CPU only device.");
     }
 #else
-      holder_.reset(new PlaceholderImpl<platform::GPUPlace>(
-          boost::get<platform::GPUPlace>(place), size, type));
+      holder_.reset(new PlaceholderImpl<platform::CUDAPlace>(
+          boost::get<platform::CUDAPlace>(place), size, type));
     }
 #endif
     offset_ = 0;

paddle/framework/tensor_test.cc

@@ -80,20 +80,20 @@ TEST(Tensor, MutableData) {
     float* p1 = nullptr;
     float* p2 = nullptr;
     // initialization
-    p1 = src_tensor.mutable_data<float>(make_ddim({1, 2, 3}), GPUPlace());
+    p1 = src_tensor.mutable_data<float>(make_ddim({1, 2, 3}), CUDAPlace());
     EXPECT_NE(p1, nullptr);
     // set src_tensor a new dim with large size
     // momery is supposed to be re-allocated
-    p2 = src_tensor.mutable_data<float>(make_ddim({3, 4}), GPUPlace());
+    p2 = src_tensor.mutable_data<float>(make_ddim({3, 4}), CUDAPlace());
     EXPECT_NE(p2, nullptr);
     EXPECT_NE(p1, p2);
     // set src_tensor a new dim with same size
     // momery block is supposed to be unchanged
-    p1 = src_tensor.mutable_data<float>(make_ddim({2, 2, 3}), GPUPlace());
+    p1 = src_tensor.mutable_data<float>(make_ddim({2, 2, 3}), CUDAPlace());
     EXPECT_EQ(p1, p2);
     // set src_tensor a new dim with smaller size
     // momery block is supposed to be unchanged
-    p2 = src_tensor.mutable_data<float>(make_ddim({2, 2}), GPUPlace());
+    p2 = src_tensor.mutable_data<float>(make_ddim({2, 2}), CUDAPlace());
     EXPECT_EQ(p1, p2);
   }
 #endif
@@ -130,7 +130,7 @@ TEST(Tensor, ShareDataWith) {
   {
     Tensor src_tensor;
     Tensor dst_tensor;
-    src_tensor.mutable_data<int>(make_ddim({2, 3, 4}), GPUPlace());
+    src_tensor.mutable_data<int>(make_ddim({2, 3, 4}), CUDAPlace());
     dst_tensor.ShareDataWith(src_tensor);
     ASSERT_EQ(src_tensor.data<int>(), dst_tensor.data<int>());
   }
@@ -166,7 +166,7 @@ TEST(Tensor, Slice) {
 #ifdef PADDLE_WITH_CUDA
   {
     Tensor src_tensor;
-    src_tensor.mutable_data<double>(make_ddim({6, 9}), GPUPlace());
+    src_tensor.mutable_data<double>(make_ddim({6, 9}), CUDAPlace());
     Tensor slice_tensor = src_tensor.Slice(2, 6);
     DDim slice_dims = slice_tensor.dims();
     ASSERT_EQ(arity(slice_dims), 2);
@@ -176,11 +176,11 @@ TEST(Tensor, Slice) {
     uintptr_t src_data_address =
         reinterpret_cast<uintptr_t>(src_tensor.data<double>());
     uintptr_t src_mutable_data_address = reinterpret_cast<uintptr_t>(
-        src_tensor.mutable_data<double>(src_tensor.dims(), GPUPlace()));
+        src_tensor.mutable_data<double>(src_tensor.dims(), CUDAPlace()));
     uintptr_t slice_data_address =
         reinterpret_cast<uintptr_t>(slice_tensor.data<double>());
     uintptr_t slice_mutable_data_address = reinterpret_cast<uintptr_t>(
-        slice_tensor.mutable_data<double>(slice_tensor.dims(), GPUPlace()));
+        slice_tensor.mutable_data<double>(slice_tensor.dims(), CUDAPlace()));
     EXPECT_EQ(src_data_address, src_mutable_data_address);
     EXPECT_EQ(slice_data_address, slice_mutable_data_address);
     EXPECT_EQ(src_data_address + 9 * 2 * sizeof(double), slice_data_address);

paddle/framework/tensor_util.h

@@ -47,11 +47,11 @@ inline void CopyFrom(const Tensor& src, const platform::Place& dst_place,
 #ifdef PADDLE_WITH_CUDA
   else if (platform::is_gpu_place(src_place) &&  // NOLINT
            platform::is_cpu_place(dst_place)) {
-    auto src_gpu_place = boost::get<platform::GPUPlace>(src_place);
+    auto src_gpu_place = boost::get<platform::CUDAPlace>(src_place);
     auto dst_cpu_place = boost::get<platform::CPUPlace>(dst_place);
     auto ctx_place = ctx.GetPlace();
     PADDLE_ENFORCE(platform::is_gpu_place(ctx_place));
-    auto ctx_gpu_place = boost::get<platform::GPUPlace>(ctx_place);
+    auto ctx_gpu_place = boost::get<platform::CUDAPlace>(ctx_place);
     PADDLE_ENFORCE_EQ(src_gpu_place, ctx_gpu_place);
     memory::Copy(
         dst_cpu_place, dst_ptr, src_gpu_place, src_ptr, size,
@@ -59,21 +59,21 @@ inline void CopyFrom(const Tensor& src, const platform::Place& dst_place,
   } else if (platform::is_cpu_place(src_place) &&
              platform::is_gpu_place(dst_place)) {
     auto src_cpu_place = boost::get<platform::CPUPlace>(src_place);
-    auto dst_gpu_place = boost::get<platform::GPUPlace>(dst_place);
+    auto dst_gpu_place = boost::get<platform::CUDAPlace>(dst_place);
     auto ctx_place = ctx.GetPlace();
     PADDLE_ENFORCE(platform::is_gpu_place(ctx_place));
-    auto ctx_gpu_place = boost::get<platform::GPUPlace>(ctx_place);
+    auto ctx_gpu_place = boost::get<platform::CUDAPlace>(ctx_place);
     PADDLE_ENFORCE_EQ(dst_gpu_place, ctx_gpu_place);
     memory::Copy(
         dst_gpu_place, dst_ptr, src_cpu_place, src_ptr, size,
         reinterpret_cast<const platform::CUDADeviceContext&>(ctx).stream());
   } else if (platform::is_gpu_place(src_place) &&
              platform::is_gpu_place(dst_place)) {
-    auto src_gpu_place = boost::get<platform::GPUPlace>(src_place);
-    auto dst_gpu_place = boost::get<platform::GPUPlace>(dst_place);
+    auto src_gpu_place = boost::get<platform::CUDAPlace>(src_place);
+    auto dst_gpu_place = boost::get<platform::CUDAPlace>(dst_place);
     auto ctx_place = ctx.GetPlace();
     PADDLE_ENFORCE(platform::is_gpu_place(ctx_place));
-    auto ctx_gpu_place = boost::get<platform::GPUPlace>(ctx_place);
+    auto ctx_gpu_place = boost::get<platform::CUDAPlace>(ctx_place);
     PADDLE_ENFORCE_EQ(src_gpu_place, ctx_gpu_place);
     memory::Copy(
         dst_gpu_place, dst_ptr, src_gpu_place, src_ptr, size,
@@ -108,7 +108,7 @@ inline void CopyFromVector(const std::vector<T>& src,
 #ifdef PADDLE_WITH_CUDA
   else if (platform::is_gpu_place(dst_place)) {  // NOLINT
     memory::Copy(
-        boost::get<platform::GPUPlace>(dst_place), dst_ptr, src_place, src_ptr,
+        boost::get<platform::CUDAPlace>(dst_place), dst_ptr, src_place, src_ptr,
         size,
         reinterpret_cast<const platform::CUDADeviceContext&>(ctx).stream());
   }
@@ -141,7 +141,7 @@ inline void CopyToVector(const Tensor& src, const platform::DeviceContext& ctx,
 #ifdef PADDLE_WITH_CUDA
   else if (platform::is_gpu_place(src.place())) {  // NOLINT
     memory::Copy(
-        dst_place, dst_ptr, boost::get<platform::GPUPlace>(src.place()),
+        dst_place, dst_ptr, boost::get<platform::CUDAPlace>(src.place()),
         src_ptr, size,
         reinterpret_cast<const platform::CUDADeviceContext&>(ctx).stream());
   }

paddle/framework/tensor_util_test.cc

@@ -58,7 +58,7 @@ TEST(CopyFrom, Tensor) {
     memcpy(src_ptr, arr, 9 * sizeof(int));
 
     // CPU Tensor to GPU Tensor
-    auto gpu_place = new platform::GPUPlace(0);
+    auto gpu_place = new platform::CUDAPlace(0);
     platform::CUDADeviceContext gpu_ctx(*gpu_place);
     CopyFrom(src_tensor, *gpu_place, gpu_ctx, &gpu_tensor);
 
@@ -143,7 +143,7 @@ TEST(CopyFromVector, Tensor) {
 
     // Copy to GPUTensor
     gpu_tensor.Resize(make_ddim({3, 3}));
-    auto gpu_place = new paddle::platform::GPUPlace();
+    auto gpu_place = new paddle::platform::CUDAPlace();
     CUDADeviceContext gpu_ctx(*gpu_place);
     CopyFromVector<int>(src_vec, gpu_ctx, &gpu_tensor);
     // Copy from GPU to CPU tensor for comparison
@@ -210,7 +210,7 @@ TEST(CopyToVector, Tensor) {
   {
     std::vector<int> src_vec = {1, 2, 3, 4, 5, 6, 7, 8, 9};
     Tensor gpu_tensor;
-    GPUPlace place;
+    CUDAPlace place;
     CUDADeviceContext gpu_ctx(place);
     CopyFromVector<int>(src_vec, gpu_ctx, &gpu_tensor);
 

paddle/memory/README.md

@@ -12,13 +12,13 @@ p = memory::Alloc(platform::CPUPlace(), 4*1024);
 To allocate 4KB memory on the 3rd GPU:
 
 ```cpp
-p = memory::Alloc(platform::GPUPlace(2), 4*1024);
+p = memory::Alloc(platform::CUDAPlace(2), 4*1024);
 ```
 
 To free memory and check the so-far used amount of memory on a place:
 
 ```cpp
-auto pl = platform::GPUPlace(0);
+auto pl = platform::CUDAPlace(0);
 p = memory::Alloc(pl, 4*1024);
 cout << memory::Used(pl);
 memory::Free(pl, p);
@@ -36,7 +36,7 @@ template <typename Place> size_t Used(Place);
 }  // namespace memory
 ```
 
-These function templates have specializations on either `platform::CPUPlace` or `platform::GPUPlace`:
+These function templates have specializations on either `platform::CPUPlace` or `platform::CUDAPlace`:
 
 ```cpp
 template<>
@@ -49,7 +49,7 @@ and
 
 ```cpp
 template<>
-void Alloc<GPUPlace>(GPUPlace p, size_t size) {
+void Alloc<CUDAPlace>(CUDAPlace p, size_t size) {
   return GetGPUBuddyAllocator(p.id)->Alloc(size);
 }
 ```
@@ -122,7 +122,7 @@ There are two implementations of `Context`:
 
 1. [`CPUContext`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context.h#L105), whose [`New` method](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context.h#L131) calls [`g_cpu_allocator.get()->New(size_t)`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context.cc#L15) to allocate the memory.
 
-1. [`CUDAContext`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.h#L99), which has a data member [`int gpu_id_`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.h#L202).  This looks very similar to class `majel::GPUPlace`, who also has an `int id_` data member.   `CUDAContext::New(size_t)` calls [`g_cub_allocator->DeviceAllocate(&ptr, nbytes)`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.cu#L355) to allocate the memory.
+1. [`CUDAContext`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.h#L99), which has a data member [`int gpu_id_`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.h#L202).  This looks very similar to class `majel::CUDAPlace`, who also has an `int id_` data member.   `CUDAContext::New(size_t)` calls [`g_cub_allocator->DeviceAllocate(&ptr, nbytes)`](https://github.com/caffe2/caffe2/blob/v0.7.0/caffe2/core/context_gpu.cu#L355) to allocate the memory.
 
 ### Majel
 

paddle/memory/memcpy.cc

@@ -28,31 +28,25 @@ void Copy<platform::CPUPlace, platform::CPUPlace>(platform::CPUPlace, void* dst,
 
 #ifdef PADDLE_WITH_CUDA
 template <>
-void Copy<platform::CPUPlace, platform::GPUPlace>(platform::CPUPlace dst_place,
-                                                  void* dst,
-                                                  platform::GPUPlace src_place,
-                                                  const void* src, size_t num,
-                                                  cudaStream_t stream) {
+void Copy<platform::CPUPlace, platform::CUDAPlace>(
+    platform::CPUPlace dst_place, void* dst, platform::CUDAPlace src_place,
+    const void* src, size_t num, cudaStream_t stream) {
   platform::SetDeviceId(src_place.device);
   platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyDeviceToHost, stream);
 }
 
 template <>
-void Copy<platform::GPUPlace, platform::CPUPlace>(platform::GPUPlace dst_place,
-                                                  void* dst,
-                                                  platform::CPUPlace src_place,
-                                                  const void* src, size_t num,
-                                                  cudaStream_t stream) {
+void Copy<platform::CUDAPlace, platform::CPUPlace>(
+    platform::CUDAPlace dst_place, void* dst, platform::CPUPlace src_place,
+    const void* src, size_t num, cudaStream_t stream) {
   platform::SetDeviceId(dst_place.device);
   platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyHostToDevice, stream);
 }
 
 template <>
-void Copy<platform::GPUPlace, platform::GPUPlace>(platform::GPUPlace dst_place,
-                                                  void* dst,
-                                                  platform::GPUPlace src_place,
-                                                  const void* src, size_t num,
-                                                  cudaStream_t stream) {
+void Copy<platform::CUDAPlace, platform::CUDAPlace>(
+    platform::CUDAPlace dst_place, void* dst, platform::CUDAPlace src_place,
+    const void* src, size_t num, cudaStream_t stream) {
   if (dst_place == src_place) {
     platform::SetDeviceId(src_place.device);
     platform::GpuMemcpyAsync(dst, src, num, cudaMemcpyDeviceToDevice, stream);

paddle/memory/memory.cc

@@ -83,12 +83,12 @@ BuddyAllocator* GetGPUBuddyAllocator(int gpu_id) {
 }
 
 template <>
-size_t Used<platform::GPUPlace>(platform::GPUPlace place) {
+size_t Used<platform::CUDAPlace>(platform::CUDAPlace place) {
   return GetGPUBuddyAllocator(place.device)->Used();
 }
 
 template <>
-void* Alloc<platform::GPUPlace>(platform::GPUPlace place, size_t size) {
+void* Alloc<platform::CUDAPlace>(platform::CUDAPlace place, size_t size) {
   auto* buddy_allocator = GetGPUBuddyAllocator(place.device);
   auto* ptr = buddy_allocator->Alloc(size);
   if (ptr == nullptr) {
@@ -101,14 +101,14 @@ void* Alloc<platform::GPUPlace>(platform::GPUPlace place, size_t size) {
     LOG(WARNING) << "total " << total;
     LOG(WARNING) << "GpuMinChunkSize " << platform::GpuMinChunkSize();
     LOG(WARNING) << "GpuMaxChunkSize " << platform::GpuMaxChunkSize();
-    LOG(WARNING) << "GPU memory used: " << Used<platform::GPUPlace>(place);
+    LOG(WARNING) << "GPU memory used: " << Used<platform::CUDAPlace>(place);
     platform::SetDeviceId(cur_dev);
   }
   return ptr;
 }
 
 template <>
-void Free<platform::GPUPlace>(platform::GPUPlace place, void* p) {
+void Free<platform::CUDAPlace>(platform::CUDAPlace place, void* p) {
   GetGPUBuddyAllocator(place.device)->Free(p);
 }
 

paddle/memory/memory_test.cc

@@ -82,7 +82,7 @@ TEST(BuddyAllocator, CPUMultAlloc) {
 
 #ifdef PADDLE_WITH_CUDA
 
-size_t align(size_t size, paddle::platform::GPUPlace place) {
+size_t align(size_t size, paddle::platform::CUDAPlace place) {
   size += sizeof(paddle::memory::detail::Metadata);
   size_t alignment = paddle::platform::GpuMinChunkSize();
   size_t remaining = size % alignment;
@@ -94,7 +94,7 @@ TEST(BuddyAllocator, GPUAllocation) {
 
   EXPECT_EQ(p, nullptr);
 
-  paddle::platform::GPUPlace gpu(0);
+  paddle::platform::CUDAPlace gpu(0);
   p = paddle::memory::Alloc(gpu, 4096);
 
   EXPECT_NE(p, nullptr);
@@ -103,7 +103,7 @@ TEST(BuddyAllocator, GPUAllocation) {
 }
 
 TEST(BuddyAllocator, GPUMultAlloc) {
-  paddle::platform::GPUPlace gpu;
+  paddle::platform::CUDAPlace gpu;
 
   std::unordered_map<void *, size_t> ps;
 

paddle/operators/accuracy_op.cu

@@ -56,7 +56,7 @@ class AccuracyOpCUDAKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     auto* inference = ctx.Input<Tensor>("Out");
     auto* indices = ctx.Input<Tensor>("Indices");
     auto* label = ctx.Input<Tensor>("Label");

paddle/operators/batch_norm_op.cu.cc

@@ -53,7 +53,7 @@ class BatchNormKernel<platform::CUDADeviceContext, T>
  public:
   void Compute(const framework::ExecutionContext &ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     double epsilon = static_cast<double>(ctx.Attr<float>("epsilon"));
     const float momentum = ctx.Attr<float>("momentum");
     const bool is_test = ctx.Attr<bool>("is_test");
@@ -179,7 +179,7 @@ class BatchNormGradKernel<platform::CUDADeviceContext, T>
  public:
   void Compute(const framework::ExecutionContext &ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     double epsilon = static_cast<double>(ctx.Attr<float>("epsilon"));
     const std::string data_layout_str = ctx.Attr<std::string>("data_layout");
     const DataLayout data_layout =

paddle/operators/conv_cudnn_op.cu.cc

@@ -36,7 +36,7 @@ class CudnnConvOpKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     auto* input = ctx.Input<Tensor>("Input");
     auto* filter = ctx.Input<Tensor>("Filter");
     auto* output = ctx.Output<Tensor>("Output");
@@ -130,7 +130,7 @@ class CudnnConvOpKernel : public framework::OpKernel<T> {
         handle, cudnn_input_desc, cudnn_filter_desc, cudnn_conv_desc,
         cudnn_output_desc, algo, &workspace_size_in_bytes));
     // Allocate on GPU memory
-    platform::GPUPlace gpu = boost::get<platform::GPUPlace>(ctx.GetPlace());
+    platform::CUDAPlace gpu = boost::get<platform::CUDAPlace>(ctx.GetPlace());
     cudnn_workspace = paddle::memory::Alloc(gpu, workspace_size_in_bytes);
     // ------------------- cudnn conv forward ---------------------
     T alpha = 1.0f, beta = 0.0f;
@@ -151,7 +151,7 @@ class CudnnConvGradOpKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     auto input = ctx.Input<Tensor>("Input");
     auto filter = ctx.Input<Tensor>("Filter");
     auto output_grad = ctx.Input<Tensor>(framework::GradVarName("Output"));
@@ -277,7 +277,7 @@ class CudnnConvGradOpKernel : public framework::OpKernel<T> {
     // ------------------- cudnn conv workspace ---------------------
     // Already on GPU
     void* cudnn_workspace = nullptr;
-    platform::GPUPlace gpu = boost::get<platform::GPUPlace>(ctx.GetPlace());
+    platform::CUDAPlace gpu = boost::get<platform::CUDAPlace>(ctx.GetPlace());
     cudnn_workspace = paddle::memory::Alloc(gpu, workspace_size_in_bytes);
     // ------------------- cudnn conv backward data ---------------------
     T alpha = 1.0f, beta = 0.0f;

paddle/operators/conv_transpose_cudnn_op.cu.cc

@@ -35,7 +35,7 @@ class CudnnConvTransposeOpKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     auto* input = ctx.Input<Tensor>("Input");
     auto* filter = ctx.Input<Tensor>("Filter");
     auto* output = ctx.Output<Tensor>("Output");
@@ -100,7 +100,7 @@ class CudnnConvTransposeOpKernel : public framework::OpKernel<T> {
             cudnn_output_desc, algo, &workspace_size_in_bytes));
 
     // Allocate on GPU memory
-    platform::GPUPlace gpu = boost::get<platform::GPUPlace>(ctx.GetPlace());
+    platform::CUDAPlace gpu = boost::get<platform::CUDAPlace>(ctx.GetPlace());
     cudnn_workspace = paddle::memory::Alloc(gpu, workspace_size_in_bytes);
 
     // ------------------- cudnn conv transpose forward ---------------------
@@ -120,7 +120,7 @@ class CudnnConvTransposeGradOpKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
     auto input = ctx.Input<Tensor>("Input");
     auto filter = ctx.Input<Tensor>("Filter");
     auto output_grad = ctx.Input<Tensor>(framework::GradVarName("Output"));
@@ -201,7 +201,7 @@ class CudnnConvTransposeGradOpKernel : public framework::OpKernel<T> {
     // ------------------- cudnn conv workspace ---------------------
     // Already on GPU
     void* cudnn_workspace = nullptr;
-    platform::GPUPlace gpu = boost::get<platform::GPUPlace>(ctx.GetPlace());
+    platform::CUDAPlace gpu = boost::get<platform::CUDAPlace>(ctx.GetPlace());
     cudnn_workspace = paddle::memory::Alloc(gpu, workspace_size_in_bytes);
     // ------------------- cudnn conv backward data ---------------------
     // FIXME(typhoonzero): template type T may not be the same as cudnn call.

paddle/operators/detail/strided_memcpy.h

@@ -35,7 +35,7 @@ struct StridedMemcpyFunctor<T, 1> {
       memory::Copy(cpu_place, dst, cpu_place, src, sizeof(T) * dst_dim.head);
     } else {
 #ifdef PADDLE_WITH_CUDA
-      auto& gpu_place = boost::get<platform::GPUPlace>(place);
+      auto& gpu_place = boost::get<platform::CUDAPlace>(place);
       auto& cuda_ctx =
           reinterpret_cast<const platform::CUDADeviceContext&>(dev_ctx);
       memory::Copy(gpu_place, dst, gpu_place, src, sizeof(T) * dst_dim.head,

paddle/operators/linear_chain_crf_op.h

@@ -219,8 +219,8 @@ class LinearChainCRFOpKernel : public framework::OpKernel<T> {
     // operators runs on GPU device.
     auto copyTensor = [](const platform::DeviceContext& ctx, const Tensor& src,
                          Tensor* dst) {
-      dst->mutable_data<T>(platform::GPUPlace());
-      framework::CopyFrom(src, platform::GPUPlace(), ctx, dst);
+      dst->mutable_data<T>(platform::CUDAPlace());
+      framework::CopyFrom(src, platform::CUDAPlace(), ctx, dst);
     };
     copyTensor(ctx, emission_exps_src, emission_exps_dst);
     copyTensor(ctx, transition_exps_src, transition_exps_dst);
@@ -433,8 +433,8 @@ class LinearChainCRFGradOpKernel : public framework::OpKernel<T> {
     auto copyTensor = [](const platform::DeviceContext& ctx, const Tensor* src,
                          Tensor* dst) {
       if (src && dst) {
-        dst->mutable_data<T>(platform::GPUPlace());
-        framework::CopyFrom(*src, platform::GPUPlace(), ctx, dst);
+        dst->mutable_data<T>(platform::CUDAPlace());
+        framework::CopyFrom(*src, platform::CUDAPlace(), ctx, dst);
       }
     };
     copyTensor(ctx, emission_grad_src, emission_grad_dst);

paddle/operators/lookup_table_op.cu

@@ -101,7 +101,7 @@ class LookupTableGradCUDAKernel : public framework::OpKernel<T> {
       // copy GPU memory to CPU pinned memory
       framework::Vector<int64_t> new_rows;
       new_rows.resize(ids_dim[0]);
-      auto gpu_place = boost::get<platform::GPUPlace>(context.GetPlace());
+      auto gpu_place = boost::get<platform::CUDAPlace>(context.GetPlace());
 
       memory::Copy(platform::CPUPlace(), new_rows.data(), gpu_place, ids_data,
                    ids_dim[0] * sizeof(int64_t), stream);

paddle/operators/lstm_unit_op.cu

@@ -98,7 +98,7 @@ class LstmUnitOpCUDAKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
 
     auto* x_tensor = ctx.Input<framework::Tensor>("X");
     auto* c_prev_tensor = ctx.Input<framework::Tensor>("C_prev");
@@ -129,7 +129,7 @@ class LstmUnitGradOpCUDAKernel : public framework::OpKernel<T> {
  public:
   void Compute(const framework::ExecutionContext& ctx) const override {
     PADDLE_ENFORCE(platform::is_gpu_place(ctx.GetPlace()),
-                   "It must use GPUPlace.");
+                   "It must use CUDAPlace.");
 
     auto x_tensor = ctx.Input<Tensor>("X");
     auto c_prev_tensor = ctx.Input<Tensor>("C_prev");

paddle/operators/math/im2col_test.cc

@@ -159,6 +159,7 @@ void testIm2col() {
 TEST(math, im2col) {
   testIm2col<paddle::platform::CPUDeviceContext, paddle::platform::CPUPlace>();
 #ifdef PADDLE_WITH_CUDA
-  testIm2col<paddle::platform::CUDADeviceContext, paddle::platform::GPUPlace>();
+  testIm2col<paddle::platform::CUDADeviceContext,
+             paddle::platform::CUDAPlace>();
 #endif
 }

paddle/operators/math/math_function.cu

@@ -105,7 +105,7 @@ void matmul<platform::CUDADeviceContext, float>(
   PADDLE_ENFORCE(platform::is_gpu_place(matrix_a.place()) &&
                      platform::is_gpu_place(matrix_b.place()) &&
                      platform::is_gpu_place(matrix_out->place()),
-                 "Matrix must all be in GPUPlace");
+                 "Matrix must all be in CUDAPlace");
 
   int M = dim_out[0];
   int N = dim_out[1];
@@ -134,7 +134,7 @@ void matmul<platform::CUDADeviceContext, double>(
   PADDLE_ENFORCE(platform::is_gpu_place(matrix_a.place()) &&
                      platform::is_gpu_place(matrix_b.place()) &&
                      platform::is_gpu_place(matrix_out->place()),
-                 "Matrix must all be in GPUPlace");
+                 "Matrix must all be in CUDAPlace");
 
   int M = dim_out[0];
   int N = dim_out[1];
@@ -266,7 +266,7 @@ struct TensorSetConstantGPU {
 };
 
 template <>
-void set_constant_with_place<platform::GPUPlace>(
+void set_constant_with_place<platform::CUDAPlace>(
     const platform::DeviceContext& context, framework::Tensor* tensor,
     float value) {
   framework::VisitDataType(framework::ToDataType(tensor->type()),
@@ -277,7 +277,7 @@ template <>
 void set_constant_with_place<platform::CUDNNPlace>(
     const platform::DeviceContext& context, framework::Tensor* tensor,
     float value) {
-  set_constant_with_place<platform::GPUPlace>(context, tensor, value);
+  set_constant_with_place<platform::CUDAPlace>(context, tensor, value);
 }
 
 template struct RowwiseAdd<platform::CUDADeviceContext, float>;

paddle/operators/math/math_function_test.cu

@@ -13,7 +13,7 @@ TEST(math_function, notrans_mul_trans) {
   float arr[6] = {0, 1, 2, 3, 4, 5};
   memcpy(input1_ptr, arr, 6 * sizeof(float));
 
-  auto* gpu_place = new paddle::platform::GPUPlace(0);
+  auto* gpu_place = new paddle::platform::CUDAPlace(0);
   paddle::platform::CUDADeviceContext context(*gpu_place);
 
   paddle::framework::CopyFrom(input1, *gpu_place, context, &input1_gpu);
@@ -47,7 +47,7 @@ TEST(math_function, trans_mul_notrans) {
   float arr[6] = {0, 1, 2, 3, 4, 5};
   memcpy(input1_ptr, arr, 6 * sizeof(float));
 
-  auto* gpu_place = new paddle::platform::GPUPlace(0);
+  auto* gpu_place = new paddle::platform::CUDAPlace(0);
   paddle::platform::CUDADeviceContext context(*gpu_place);
 
   paddle::framework::CopyFrom(input1, *gpu_place, context, &input1_gpu);
@@ -96,7 +96,7 @@ TEST(math_function, gemm_notrans_cublas) {
   float arr3[8] = {0, 1, 2, 3, 4, 5, 6, 7};
   memcpy(input3_ptr, arr3, 8 * sizeof(float));
 
-  auto* gpu_place = new paddle::platform::GPUPlace(0);
+  auto* gpu_place = new paddle::platform::CUDAPlace(0);
   paddle::platform::CUDADeviceContext context(*gpu_place);
 
   paddle::framework::CopyFrom(input1, *gpu_place, context, &input1_gpu);
@@ -151,7 +151,7 @@ TEST(math_function, gemm_trans_cublas) {
   float arr3[8] = {0, 1, 2, 3, 4, 5, 6, 7};
   memcpy(input3_ptr, arr3, 8 * sizeof(float));
 
-  auto* gpu_place = new paddle::platform::GPUPlace(0);
+  auto* gpu_place = new paddle::platform::CUDAPlace(0);
   paddle::platform::CUDADeviceContext context(*gpu_place);
 
   paddle::framework::CopyFrom(input1, *gpu_place, context, &input1_gpu);
@@ -189,7 +189,7 @@ void GemvTest(int m, int n, bool trans) {
   T* data_b = vec_b.mutable_data<T>({trans ? m : n}, *cpu_place);
   T* data_c = vec_c.mutable_data<T>({trans ? n : m}, *cpu_place);
 
-  auto* gpu_place = new paddle::platform::GPUPlace(0);
+  auto* gpu_place = new paddle::platform::CUDAPlace(0);
   paddle::framework::Tensor g_mat_a;
   paddle::framework::Tensor g_vec_b;
   paddle::framework::Tensor g_vec_c;