GPUPlace to CUDAPlace (#6960)

Author: dzhwinter

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

@@ -47,33 +47,33 @@ 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,
         reinterpret_cast<const platform::CUDADeviceContext&>(ctx).stream());
   } 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);