Remove some custom_impl api (#45066)

* remove some custom_impl api and make them generated by yaml completely

* delete useless code

* fix adamw bug

* fix infermeta

* revert adamw

* polish code

* fix bug

paddle/phi/api/lib/CMakeLists.txt

@@ -337,7 +337,8 @@ add_custom_command(
     ${api_yaml_file} ${legacy_api_yaml_file} --wrapped_infermeta_header_path
     ${wrapped_infermeta_header_file} --wrapped_infermeta_source_path
     ${wrapped_infermeta_source_file}
-  DEPENDS ${api_yaml_file} ${wrapped_infermeta_gen_file} ${api_gen_base}
+  DEPENDS ${api_yaml_file} ${legacy_api_yaml_file} ${wrapped_infermeta_gen_file}
+          ${api_gen_base}
   VERBATIM)
 
 cc_library(

paddle/phi/api/lib/api_custom_impl.cc

@@ -198,416 +198,6 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, Tensor, Tensor> adamw_impl(
   return api_output;
 }
 
-Tensor conv2d_impl(const Tensor& input,
-                   const Tensor& filter,
-                   const std::vector<int>& strides,
-                   const std::vector<int>& paddings,
-                   const std::string& paddding_algorithm,
-                   int groups,
-                   const std::vector<int>& dilations,
-                   const std::string& data_format,
-                   bool use_addto,
-                   int workspace_size_MB,
-                   bool exhaustive_search) {
-  Backend kernel_backend = Backend::UNDEFINED;
-  DataLayout kernel_layout = DataLayout::UNDEFINED;
-  DataType kernel_data_type = DataType::UNDEFINED;
-
-  kernel_data_type = ParseDataType(input);
-
-  if (kernel_backend == Backend::UNDEFINED ||
-      kernel_layout == DataLayout::UNDEFINED ||
-      kernel_data_type == DataType::UNDEFINED) {
-    auto kernel_key_set = ParseKernelKeyByInputArgs(input, filter);
-    auto kernel_key = kernel_key_set.GetHighestPriorityKernelKey();
-    if (kernel_backend == Backend::UNDEFINED) {
-      kernel_backend = kernel_key.backend();
-    }
-    if (kernel_layout == DataLayout::UNDEFINED) {
-      kernel_layout = kernel_key.layout();
-    }
-    if (kernel_data_type == DataType::UNDEFINED) {
-      kernel_data_type = kernel_key.dtype();
-    }
-  }
-
-  VLOG(6) << "conv2d API kernel key: [" << kernel_backend << ", "
-          << kernel_layout << ", " << kernel_data_type << "]";
-  auto kernel_result = phi::KernelFactory::Instance().SelectKernelOrThrowError(
-      "conv2d", {kernel_backend, kernel_layout, kernel_data_type}, true);
-  const auto& kernel = kernel_result.kernel;
-  VLOG(6) << "conv2d API kernel: " << kernel;
-
-  auto* dev_ctx = GetDeviceContextByBackend(kernel_backend);
-
-  phi::TensorArgDef args0 = kernel.InputAt(0);
-  phi::TensorArgDef args1 = kernel.InputAt(1);
-  if (kernel_backend == Backend::GPU) {
-    args0.backend = Backend::GPU;
-    args1.backend = Backend::GPU;
-  }
-
-  auto input_input = PrepareData(input, args0, {});
-  auto input_filter = PrepareData(filter, args1, {});
-
-  Tensor api_output;
-  auto kernel_out = SetKernelOutput(kernel_backend, &api_output);
-  phi::MetaTensor meta_out(kernel_out);
-
-  phi::ConvInferMeta(MakeMetaTensor(*input_input),
-                     MakeMetaTensor(*input_filter),
-                     strides,
-                     paddings,
-                     paddding_algorithm,
-                     groups,
-                     dilations,
-                     data_format,
-                     use_addto,
-                     workspace_size_MB,
-                     exhaustive_search,
-                     &meta_out);
-
-  using kernel_signature = void (*)(const platform::DeviceContext&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const std::vector<int>&,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    int,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    bool,
-                                    int,
-                                    bool,
-                                    phi::DenseTensor*);
-  auto* kernel_fn = kernel.GetVariadicKernelFn<kernel_signature>();
-
-  {
-    (*kernel_fn)(*dev_ctx,
-                 *input_input,
-                 *input_filter,
-                 strides,
-                 paddings,
-                 paddding_algorithm,
-                 groups,
-                 dilations,
-                 data_format,
-                 use_addto,
-                 workspace_size_MB,
-                 exhaustive_search,
-                 kernel_out);
-  }
-
-  return api_output;
-}
-
-Tensor conv3d_impl(const Tensor& input,
-                   const Tensor& filter,
-                   const std::vector<int>& strides,
-                   const std::vector<int>& paddings,
-                   const std::string& paddding_algorithm,
-                   int groups,
-                   const std::vector<int>& dilations,
-                   const std::string& data_format,
-                   bool use_addto,
-                   int workspace_size_MB,
-                   bool exhaustive_search) {
-  Backend kernel_backend = Backend::UNDEFINED;
-  DataLayout kernel_layout = DataLayout::UNDEFINED;
-  DataType kernel_data_type = DataType::UNDEFINED;
-
-  kernel_data_type = ParseDataType(input);
-
-  if (kernel_backend == Backend::UNDEFINED ||
-      kernel_layout == DataLayout::UNDEFINED ||
-      kernel_data_type == DataType::UNDEFINED) {
-    auto kernel_key_set = ParseKernelKeyByInputArgs(input, filter);
-    auto kernel_key = kernel_key_set.GetHighestPriorityKernelKey();
-    if (kernel_backend == Backend::UNDEFINED) {
-      kernel_backend = kernel_key.backend();
-    }
-    if (kernel_layout == DataLayout::UNDEFINED) {
-      kernel_layout = kernel_key.layout();
-    }
-    if (kernel_data_type == DataType::UNDEFINED) {
-      kernel_data_type = kernel_key.dtype();
-    }
-  }
-
-  VLOG(6) << "conv3d API kernel key: [" << kernel_backend << ", "
-          << kernel_layout << ", " << kernel_data_type << "]";
-  auto kernel_result = phi::KernelFactory::Instance().SelectKernelOrThrowError(
-      "conv3d", {kernel_backend, kernel_layout, kernel_data_type}, true);
-  const auto& kernel = kernel_result.kernel;
-  VLOG(6) << "conv3d API kernel: " << kernel;
-
-  auto* dev_ctx = GetDeviceContextByBackend(kernel_backend);
-
-  phi::TensorArgDef args0 = kernel.InputAt(0);
-  phi::TensorArgDef args1 = kernel.InputAt(1);
-  if (kernel_backend == Backend::GPU) {
-    args0.backend = Backend::GPU;
-    args1.backend = Backend::GPU;
-  }
-
-  auto input_input = PrepareData(input, args0, {});
-  auto input_filter = PrepareData(filter, args1, {});
-
-  Tensor api_output;
-  auto kernel_out = SetKernelOutput(kernel_backend, &api_output);
-  phi::MetaTensor meta_out(kernel_out);
-
-  phi::ConvInferMeta(MakeMetaTensor(*input_input),
-                     MakeMetaTensor(*input_filter),
-                     strides,
-                     paddings,
-                     paddding_algorithm,
-                     groups,
-                     dilations,
-                     data_format,
-                     use_addto,
-                     workspace_size_MB,
-                     exhaustive_search,
-                     &meta_out);
-
-  using kernel_signature = void (*)(const platform::DeviceContext&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const std::vector<int>&,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    int,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    bool,
-                                    int,
-                                    bool,
-                                    phi::DenseTensor*);
-  auto* kernel_fn = kernel.GetVariadicKernelFn<kernel_signature>();
-
-  {
-    (*kernel_fn)(*dev_ctx,
-                 *input_input,
-                 *input_filter,
-                 strides,
-                 paddings,
-                 paddding_algorithm,
-                 groups,
-                 dilations,
-                 data_format,
-                 use_addto,
-                 workspace_size_MB,
-                 exhaustive_search,
-                 kernel_out);
-  }
-
-  return api_output;
-}
-
-void conv2d_grad_impl(const Tensor& input,
-                      const Tensor& filter,
-                      const Tensor& out_grad,
-                      const std::vector<int>& strides,
-                      const std::vector<int>& paddings,
-                      const std::string& paddding_algorithm,
-                      int groups,
-                      const std::vector<int>& dilations,
-                      const std::string& data_format,
-                      bool use_addto,
-                      int workspace_size_MB,
-                      bool exhaustive_search,
-                      Tensor* input_grad,
-                      Tensor* filter_grad) {
-  Backend kernel_backend = Backend::UNDEFINED;
-  DataLayout kernel_layout = DataLayout::UNDEFINED;
-  DataType kernel_data_type = DataType::UNDEFINED;
-
-  if (kernel_backend == Backend::UNDEFINED ||
-      kernel_layout == DataLayout::UNDEFINED ||
-      kernel_data_type == DataType::UNDEFINED) {
-    auto kernel_key_set = ParseKernelKeyByInputArgs(input, filter, out_grad);
-    auto kernel_key = kernel_key_set.GetHighestPriorityKernelKey();
-    if (kernel_backend == Backend::UNDEFINED) {
-      kernel_backend = kernel_key.backend();
-    }
-    if (kernel_layout == DataLayout::UNDEFINED) {
-      kernel_layout = kernel_key.layout();
-    }
-    if (kernel_data_type == DataType::UNDEFINED) {
-      kernel_data_type = kernel_key.dtype();
-    }
-  }
-
-  VLOG(6) << "conv2d_grad API kernel key: [" << kernel_backend << ", "
-          << kernel_layout << ", " << kernel_data_type << "]";
-  auto kernel_result = phi::KernelFactory::Instance().SelectKernelOrThrowError(
-      "conv2d_grad", {kernel_backend, kernel_layout, kernel_data_type}, true);
-  const auto& kernel = kernel_result.kernel;
-  VLOG(6) << "conv2d_grad API kernel: " << kernel;
-
-  auto* dev_ctx = GetDeviceContextByBackend(kernel_backend);
-
-  phi::TensorArgDef args0 = kernel.InputAt(0);
-  phi::TensorArgDef args1 = kernel.InputAt(1);
-  phi::TensorArgDef args2 = kernel.InputAt(2);
-  if (kernel_backend == Backend::GPU) {
-    args0.backend = Backend::GPU;
-    args1.backend = Backend::GPU;
-    args2.backend = Backend::GPU;
-  }
-
-  auto input_input = PrepareData(input, args0, {});
-  auto input_filter = PrepareData(filter, args1, {});
-  auto input_out_grad = PrepareData(out_grad, args2, {});
-
-  auto kernel_out_0 = SetKernelOutput(kernel_backend, input_grad);
-  auto kernel_out_1 = SetKernelOutput(kernel_backend, filter_grad);
-  phi::MetaTensor meta_out_0(kernel_out_0);
-  phi::MetaTensor meta_out_1(kernel_out_1);
-
-  phi::GeneralBinaryGradInferMeta(MakeMetaTensor(*input_input),
-                                  MakeMetaTensor(*input_filter),
-                                  kernel_out_0 ? &meta_out_0 : nullptr,
-                                  kernel_out_1 ? &meta_out_1 : nullptr);
-
-  using kernel_signature = void (*)(const platform::DeviceContext&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const std::vector<int>&,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    int,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    bool,
-                                    int,
-                                    bool,
-                                    phi::DenseTensor*,
-                                    phi::DenseTensor*);
-  auto* kernel_fn = kernel.GetVariadicKernelFn<kernel_signature>();
-
-  {
-    (*kernel_fn)(*dev_ctx,
-                 *input_input,
-                 *input_filter,
-                 *input_out_grad,
-                 strides,
-                 paddings,
-                 paddding_algorithm,
-                 groups,
-                 dilations,
-                 data_format,
-                 use_addto,
-                 workspace_size_MB,
-                 exhaustive_search,
-                 kernel_out_0,
-                 kernel_out_1);
-  }
-}
-
-void conv3d_grad_impl(const Tensor& input,
-                      const Tensor& filter,
-                      const Tensor& out_grad,
-                      const std::vector<int>& strides,
-                      const std::vector<int>& paddings,
-                      const std::string& paddding_algorithm,
-                      int groups,
-                      const std::vector<int>& dilations,
-                      const std::string& data_format,
-                      bool use_addto,
-                      int workspace_size_MB,
-                      bool exhaustive_search,
-                      Tensor* input_grad,
-                      Tensor* filter_grad) {
-  Backend kernel_backend = Backend::UNDEFINED;
-  DataLayout kernel_layout = DataLayout::UNDEFINED;
-  DataType kernel_data_type = DataType::UNDEFINED;
-
-  if (kernel_backend == Backend::UNDEFINED ||
-      kernel_layout == DataLayout::UNDEFINED ||
-      kernel_data_type == DataType::UNDEFINED) {
-    auto kernel_key_set = ParseKernelKeyByInputArgs(input, filter, out_grad);
-    auto kernel_key = kernel_key_set.GetHighestPriorityKernelKey();
-    if (kernel_backend == Backend::UNDEFINED) {
-      kernel_backend = kernel_key.backend();
-    }
-    if (kernel_layout == DataLayout::UNDEFINED) {
-      kernel_layout = kernel_key.layout();
-    }
-    if (kernel_data_type == DataType::UNDEFINED) {
-      kernel_data_type = kernel_key.dtype();
-    }
-  }
-
-  VLOG(6) << "conv3d_grad API kernel key: [" << kernel_backend << ", "
-          << kernel_layout << ", " << kernel_data_type << "]";
-  auto kernel_result = phi::KernelFactory::Instance().SelectKernelOrThrowError(
-      "conv3d_grad", {kernel_backend, kernel_layout, kernel_data_type}, true);
-  const auto& kernel = kernel_result.kernel;
-  VLOG(6) << "conv3d_grad API kernel: " << kernel;
-
-  auto* dev_ctx = GetDeviceContextByBackend(kernel_backend);
-
-  phi::TensorArgDef args0 = kernel.InputAt(0);
-  phi::TensorArgDef args1 = kernel.InputAt(1);
-  phi::TensorArgDef args2 = kernel.InputAt(2);
-  if (kernel_backend == Backend::GPU) {
-    args0.backend = Backend::GPU;
-    args1.backend = Backend::GPU;
-    args2.backend = Backend::GPU;
-  }
-
-  auto input_input = PrepareData(input, args0, {});
-  auto input_filter = PrepareData(filter, args1, {});
-  auto input_out_grad = PrepareData(out_grad, args2, {});
-
-  auto kernel_out_0 = SetKernelOutput(kernel_backend, input_grad);
-  auto kernel_out_1 = SetKernelOutput(kernel_backend, filter_grad);
-  phi::MetaTensor meta_out_0(kernel_out_0);
-  phi::MetaTensor meta_out_1(kernel_out_1);
-
-  phi::GeneralBinaryGradInferMeta(MakeMetaTensor(*input_input),
-                                  MakeMetaTensor(*input_filter),
-                                  kernel_out_0 ? &meta_out_0 : nullptr,
-                                  kernel_out_1 ? &meta_out_1 : nullptr);
-
-  using kernel_signature = void (*)(const platform::DeviceContext&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const phi::DenseTensor&,
-                                    const std::vector<int>&,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    int,
-                                    const std::vector<int>&,
-                                    const std::string&,
-                                    bool,
-                                    int,
-                                    bool,
-                                    phi::DenseTensor*,
-                                    phi::DenseTensor*);
-  auto* kernel_fn = kernel.GetVariadicKernelFn<kernel_signature>();
-
-  {
-    (*kernel_fn)(*dev_ctx,
-                 *input_input,
-                 *input_filter,
-                 *input_out_grad,
-                 strides,
-                 paddings,
-                 paddding_algorithm,
-                 groups,
-                 dilations,
-                 data_format,
-                 use_addto,
-                 workspace_size_MB,
-                 exhaustive_search,
-                 kernel_out_0,
-                 kernel_out_1);
-  }
-}
-
 Tensor copy_to_impl(const Tensor& x, Place place, bool blocking) {
   Tensor out;
   copy(x, place, blocking, &out);

paddle/phi/api/lib/api_custom_impl.h

@@ -66,30 +66,6 @@ std::tuple<Tensor, Tensor, Tensor, Tensor, Tensor, Tensor> batch_norm_impl(
     bool trainable_statistics,
     bool fuse_with_relu);
 
-Tensor conv2d_impl(const Tensor& input,
-                   const Tensor& filter,
-                   const std::vector<int>& strides,
-                   const std::vector<int>& paddings,
-                   const std::string& paddding_algorithm,
-                   int groups,
-                   const std::vector<int>& dilations,
-                   const std::string& data_format,
-                   bool use_addto,
-                   int workspace_size_MB,
-                   bool exhaustive_search);
-
-Tensor conv3d_impl(const Tensor& input,
-                   const Tensor& filter,
-                   const std::vector<int>& strides,
-                   const std::vector<int>& paddings,
-                   const std::string& paddding_algorithm,
-                   int groups,
-                   const std::vector<int>& dilations,
-                   const std::string& data_format,
-                   bool use_addto,
-                   int workspace_size_MB,
-                   bool exhaustive_search);
-
 Tensor copy_to_impl(const Tensor& x, Place place, bool blocking);
 
 Tensor embedding_impl(const Tensor& x,
@@ -116,36 +92,6 @@ std::tuple<Tensor, Tensor, Tensor> momentum_impl(
 
 ////////////////// Backward(grad) api impls //////////////////////
 
-void conv2d_grad_impl(const Tensor& input,
-                      const Tensor& filter,
-                      const Tensor& out_grad,
-                      const std::vector<int>& strides,
-                      const std::vector<int>& paddings,
-                      const std::string& paddding_algorithm,
-                      int groups,
-                      const std::vector<int>& dilations,
-                      const std::string& data_format,
-                      bool use_addto,
-                      int workspace_size_MB,
-                      bool exhaustive_search,
-                      Tensor* input_grad,
-                      Tensor* filter_grad);
-
-void conv3d_grad_impl(const Tensor& input,
-                      const Tensor& filter,
-                      const Tensor& out_grad,
-                      const std::vector<int>& strides,
-                      const std::vector<int>& paddings,
-                      const std::string& paddding_algorithm,
-                      int groups,
-                      const std::vector<int>& dilations,
-                      const std::string& data_format,
-                      bool use_addto,
-                      int workspace_size_MB,
-                      bool exhaustive_search,
-                      Tensor* input_grad,
-                      Tensor* filter_grad);
-
 void imag_grad_impl(const Tensor& out_grad, Tensor* x_grad);
 
 void embedding_grad_impl(const Tensor& x,

paddle/phi/api/yaml/legacy_api.yaml

@@ -513,7 +513,11 @@
 - api : conv2d
   args : (Tensor input, Tensor filter, int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search)
   output : Tensor
-  invoke : conv2d_impl(input, filter, strides, paddings, paddding_algorithm, groups, dilations, data_format, use_addto, workspace_size_MB, exhaustive_search)
+  infer_meta :
+    func : ConvInferMeta
+  kernel :
+    func : conv2d
+    use_gpudnn : true
   backward : conv2d_grad
 
 - api : conv2d_transpose
@@ -529,7 +533,11 @@
 - api : conv3d
   args : (Tensor input, Tensor filter, int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search)
   output : Tensor
-  invoke : conv3d_impl(input, filter, strides, paddings, paddding_algorithm, groups, dilations, data_format, use_addto, workspace_size_MB, exhaustive_search)
+  infer_meta :
+    func : ConvInferMeta
+  kernel :
+    func : conv3d
+    use_gpudnn : true
   backward : conv3d_grad
 
 - api : conv3d_transpose

paddle/phi/api/yaml/legacy_backward.yaml

@@ -438,7 +438,12 @@
   forward : conv2d (Tensor input, Tensor filter, int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search) -> Tensor(out)
   args : (Tensor input, Tensor filter, Tensor out_grad,  int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search)
   output : Tensor(input_grad), Tensor(filter_grad)
-  invoke : conv2d_grad_impl(input, filter, out_grad,  strides, paddings, paddding_algorithm, groups, dilations, data_format, use_addto, workspace_size_MB, exhaustive_search, input_grad, filter_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [input, filter]
+  kernel :
+    func : conv2d_grad
+    use_gpudnn : true
   backward : conv2d_grad_grad
 
 - backward_api : conv2d_grad_grad
@@ -478,7 +483,12 @@
   forward : conv3d (Tensor input, Tensor filter, int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search) -> Tensor(out)
   args : (Tensor input, Tensor filter, Tensor out_grad,  int[] strides, int[] paddings, str paddding_algorithm, int groups, int[] dilations, str data_format, bool use_addto, int workspace_size_MB, bool exhaustive_search)
   output : Tensor(input_grad), Tensor(filter_grad)
-  invoke : conv3d_grad_impl(input, filter, out_grad,  strides, paddings, paddding_algorithm, groups, dilations, data_format, use_addto, workspace_size_MB, exhaustive_search, input_grad, filter_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [input, filter]
+  kernel :
+    func : conv3d_grad
+    use_gpudnn : true
   backward : conv3d_grad_grad
 
 - backward_api : conv3d_grad_grad

paddle/phi/infermeta/binary.cc

@@ -2736,5 +2736,4 @@ void Unpool3dInferMeta(const MetaTensor& x,
 }  // namespace phi
 
 PD_REGISTER_INFER_META_FN(add_raw, phi::ElementwiseRawInferMeta);
-PD_REGISTER_INFER_META_FN(conv2d, phi::ConvInferMeta);
 PD_REGISTER_INFER_META_FN(conv2d_infer, phi::ConvInferInferMeta);