diff --git a/paddle/fluid/framework/infershape_utils.cc b/paddle/fluid/framework/infershape_utils.cc
index fe4ee561c77d60ac5548f7e1951e681dafbfb48c..ea77f352dc95228b7e8a8988793ebfe8133b3024 100644
--- a/paddle/fluid/framework/infershape_utils.cc
+++ b/paddle/fluid/framework/infershape_utils.cc
@@ -407,6 +407,8 @@ void CompatMetaTensor::share_dims(const MetaTensor& meta_tensor) {
           static_cast<const CompatMetaTensor&>(meta_tensor).GetSelectedRows();
       selected_rows->set_rows(input_selected_rows.rows());
       selected_rows->set_height(input_selected_rows.height());
+      phi::DenseTensorUtils::GetMutableMeta(selected_rows->mutable_value())
+          ->dims = input_selected_rows.value().dims();
     }
   }
 }
diff --git a/paddle/fluid/operators/activation_op.cc b/paddle/fluid/operators/activation_op.cc
index 8c46bc01079aded7c7c5a47d21831aa66d7ddd63..908ddf382a9f785dce662f7aede96faf3e38d252 100644
--- a/paddle/fluid/operators/activation_op.cc
+++ b/paddle/fluid/operators/activation_op.cc
@@ -139,132 +139,6 @@ class ActivationOpGrad : public framework::OperatorWithKernel {
   }
 };
 
-UNUSED constexpr char SigmoidDoc[] = R"DOC(
-Sigmoid Activation
-
-$$out = \frac{1}{1 + e^{-x}}$$
-
-)DOC";
-
-UNUSED constexpr char ReluDoc[] = R"DOC(
-Relu Activation Operator.
-
-$$out = \max(x, 0)$$
-
-)DOC";
-
-UNUSED constexpr char TanhShrinkDoc[] = R"DOC(
-TanhShrink Activation Operator.
-
-$$out = x - \\frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}$$
-
-)DOC";
-
-UNUSED constexpr char SqrtDoc[] = R"DOC(
-Sqrt Activation Operator.
-
-$$out=\\sqrt{x}=x^{1/2}$$
-
-**Note**:
-  input value must be greater than or equal to zero.
-
-)DOC";
-
-UNUSED constexpr char RsqrtDoc[] = R"DOC(
-Rsqrt Activation Operator.
-
-Please make sure input is legal in case of numeric errors.
-
-$$out = \\frac{1}{\\sqrt{x}}$$
-
-)DOC";
-
-UNUSED constexpr char LogDoc[] = R"DOC(
-Log Activation Operator.
-
-$$out = \ln(x)$$
-
-Natural logarithm of x.
-
-)DOC";
-
-UNUSED constexpr char SquareDoc[] = R"DOC(
-The OP square each elements of the inputs.
-
-$$out = x^2$$
-
-)DOC";
-
-UNUSED constexpr char SoftsignDoc[] = R"DOC(
-Softsign Activation Operator.
-
-$$out = \\frac{x}{1 + \|x\|}$$
-
-)DOC";
-
-class LeakyReluOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X",
-             "A LoDTensor or Tensor representing preactivation values. Must be "
-             "one of the following types: float32, float64.");
-    AddOutput(
-        "Out",
-        "A LoDTensor or Tensor with the same type and size as that of x.");
-    AddAttr<float>("alpha", "Slope of the activation function at x < 0.")
-        .SetDefault(0.02f);
-    AddComment(R"DOC(
-LeakyRelu Activation Operator.
-
-$$out = \max(x, \alpha * x)$$
-
-)DOC");
-  }
-};
-
-class SoftplusOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X",
-             "Input of Softplus operator, an N-D Tensor, with data type "
-             "float32, float64 or float16.");
-    AddOutput(
-        "Out",
-        "Output of Softplus operator, a Tensor with shape same as input.");
-    AddAttr<float>("beta", "The value of beta for Softplus.").SetDefault(1.0f);
-    AddAttr<float>("threshold", "The value of threshold for Softplus.")
-        .SetDefault(20.0f);
-    AddComment(R"DOC(
-:strong:`Softplus Activation Operator`
-
-..  math::
-    out = \frac{1}{\beta} * \log(1 + \exp(\beta * x)) \\
-    \text{For numerical stability, the implementation reverts to the linear function when :}\,x \times \beta > threshold.
-
-)DOC");
-  }
-};
-
-class SoftShrinkOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X", "Input of Softshrink operator");
-    AddOutput("Out", "Output of Softshrink operator");
-    AddAttr<float>("lambda", "non-negative offset").SetDefault(0.5f);
-    AddComment(R"DOC(
-:strong:`Softshrink Activation Operator`
-
-..  math::
-    out = \begin{cases}
-         x - \lambda, \text{if } x > \lambda \\
-         x + \lambda, \text{if } x < -\lambda \\
-         0,  \text{otherwise}
-         \end{cases}
-
-)DOC");
-  }
-};
-
 class BReluOpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
@@ -303,66 +177,6 @@ $$out = \ln(1 + \exp(\max(\min(x, threshold), -threshold)))$$
   }
 };
 
-class ELUOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X",
-             "The input is a multi-dimensional Tensor. The data type is "
-             "float32 or float64.");
-    AddOutput("Out",
-              "The output is a multi-dimensional Tensor which has same "
-              "dimension and data type as the ``x``.");
-    AddAttr<float>("alpha", "The alpha value of ELU").SetDefault(1.0f);
-    AddComment(R"DOC(
-ELU Activation Operator.
-
-Applies the following element-wise computation on the input according to
-https://arxiv.org/abs/1511.07289.
-
-$$out = \max(0, x) + \min(0, \alpha * (e^x - 1))$$
-
-)DOC");
-  }
-};
-
-template <typename T>
-class ELUGradOpMaker : public framework::SingleGradOpMaker<T> {
- public:
-  using framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("elu_grad");
-    op->SetInput(framework::GradVarName("Out"), this->OutputGrad("Out"));
-    op->SetInput("Out", this->Output("Out"));
-    op->SetInput("X", this->Input("X"));
-    op->SetOutput(framework::GradVarName("X"), this->InputGrad("X"));
-    op->SetAttrMap(this->Attrs());
-  }
-};
-
-class CELUOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X",
-             "The input is a multi-dimensional Tensor. The data type is "
-             "float32 or float64.");
-    AddOutput("Out",
-              "The output is a multi-dimensional Tensor which has same "
-              "dimension and data type as the ``x``.");
-    AddAttr<float>("alpha", "The alpha value of CELU").SetDefault(1.0f);
-    AddComment(R"DOC(
-CELU Activation Operator.
-
-Applies the following element-wise computation on the input according to
-https://arxiv.org/abs/1704.07483.
-
-$$out = \max(0, x) + \min(0, \alpha * (e^(x/\alpha) - 1))$$
-
-)DOC");
-  }
-};
-
 class Relu6OpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
@@ -424,27 +238,6 @@ $$out = b * \\frac{e^{a * x} - e^{-a * x}}{e^{a * x} + e^{-a * x}}$$
   }
 };
 
-class ThresholdedReluOpMaker : public framework::OpProtoAndCheckerMaker {
- public:
-  void Make() override {
-    AddInput("X", "Input of ThresholdedRelu operator");
-    AddOutput("Out", "Output of ThresholdedRelu operator");
-    AddAttr<float>("threshold",
-                   "The threshold location of activation. [default 1.0].")
-        .SetDefault(1.0f);
-    AddComment(R"DOC(
-:strong:`ThresholdedRelu activation operator`
-
-..  math::
-
-    out = \begin{cases}
-             x,  \text{if } x > threshold \\
-             0,  \text{otherwise}
-          \end{cases}
-)DOC");
-  }
-};
-
 class SwishOpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
@@ -512,15 +305,6 @@ It is recommended to use the defaults for this activation.
   }
 };
 
-REGISTER_ACTIVATION_OP_MAKER(Sigmoid, SigmoidDoc);
-REGISTER_ACTIVATION_OP_MAKER(Relu, ReluDoc);
-REGISTER_ACTIVATION_OP_MAKER(TanhShrink, TanhShrinkDoc);
-REGISTER_ACTIVATION_OP_MAKER(Sqrt, SqrtDoc);
-REGISTER_ACTIVATION_OP_MAKER(Rsqrt, RsqrtDoc);
-REGISTER_ACTIVATION_OP_MAKER(Log, LogDoc);
-REGISTER_ACTIVATION_OP_MAKER(Square, SquareDoc);
-REGISTER_ACTIVATION_OP_MAKER(Softsign, SoftsignDoc);
-
 template <ActBwdOpFwdDeps kDepValue>
 class ActivationOpDoubleGrad : public framework::OperatorWithKernel {
  public:
@@ -632,229 +416,6 @@ class ActivationOpTripleGrad : public framework::OperatorWithKernel {
   }
 };
 
-template <typename T>
-class SigmoidDoubleGradMaker
-    : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("sigmoid_grad_grad");
-    // input1: Out
-    op->SetInput("Out", this->Input("Out"));
-    // input2: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetInput("DOut", this->Input(framework::GradVarName("Out")));
-    op->SetAttrMap(this->Attrs());
-    // output: ddy
-    op->SetOutput("DOutNew", this->InputGrad("Out"));
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-template <typename T>
-class SigmoidTripleGradMaker
-    : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("sigmoid_triple_grad");
-    // Out, DDX, DOut, D_DDOut, D_DOut_New   // input
-    // D_OutNew, D_DOut, D_DDx               // output
-    // input1: Out
-    op->SetInput("Out", this->Input("Out"));
-    // input2: ddx
-    op->SetInput("DDX", this->Input("DDX"));
-    // input3: dout
-    op->SetInput("DOut", this->Input("DOut"));
-    // input4: d_ddout
-    op->SetInput("D_DDOut", this->OutputGrad("DDOut"));
-    // input5: d_dout_new
-    op->SetInput("D_DOut_New", this->OutputGrad("DOutNew"));
-    op->SetAttrMap(this->Attrs());
-
-    // output: d_dOut, d_OutNew, d_ddx
-    op->SetOutput("D_OutNew", this->InputGrad("Out"));
-    op->SetOutput("D_DOut", this->InputGrad("DOut"));
-    op->SetOutput("D_DDx", this->InputGrad("DDX"));
-  }
-};
-
-// ReluGrad: dx = dy if y >= 0 else 0
-// ReluGradGrad: ddy = ddx if y >= 0 else 0
-template <typename T>
-class ReluDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("relu_grad_grad");
-    // input1: Out
-    op->SetInput("Out", this->Input("Out"));
-    // input2: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-    // output: ddy
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// leaky_relu Grad: dx=dy if x>=0 else alpha * dy
-// leaky_relu GradGrad: ddy=ddx if x>=0 else alpha * ddx
-template <typename T>
-class LeakyReluDoubleGradMaker
-    : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("leaky_relu_grad_grad");
-    // input1: X
-    op->SetInput("X", this->Input("X"));
-    // X@GRAD@GRAD: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-    // Out@GRAD@GRAD: ddy
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// elu grad: dx=dy if y>0 else alpha*dy*x.exp()
-// elu gradgrad: ddx=ddy if y>0 else alpha*ddy*x.exp()
-template <typename T>
-class ELUDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("elu_grad_grad");
-
-    op->SetInput("X", this->Input("X"));
-    op->SetInput("DOut", this->Input(framework::GradVarName("Out")));
-    // X@GRAD@GRAD: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-
-    // Out@GRAD@GRAD: ddy
-    op->SetOutput("DX", this->InputGrad("X"));
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// celu grad: dx=dy if y>0 else dy*(x/alpha).exp()
-// celu gradgrad: ddx=ddy if y>0 else ddy*(x/alpha).exp()/alpha
-template <typename T>
-class CELUDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("celu_grad_grad");
-
-    op->SetInput("X", this->Input("X"));
-    op->SetInput("DOut", this->Input(framework::GradVarName("Out")));
-    // X@GRAD@GRAD: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-
-    // Out@GRAD@GRAD: ddy
-    op->SetOutput("DX", this->InputGrad("X"));
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// sqrt Grad: dx = 0.5 * dy / y
-// sqrt GradGrad: ddy = 0.5 * ddx / y, dy = -1 * dx * ddx
-template <typename T>
-class SqrtDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("sqrt_grad_grad");
-    op->SetInput("Out", this->Input("Out"));
-    op->SetInput("DX", this->Output(framework::GradVarName("X")));
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-    op->SetOutput("DOut", this->InputGrad("Out"));
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// rsqrt Grad: dx = -0.5 * dy * y * y * y
-// rsqrt GradGrad: ddy = -0.5 * ddx * y * y * y, dy = (3/y) * ddx
-template <typename T>
-class RsqrtDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("rsqrt_grad_grad");
-    op->SetInput("Out", this->Input("Out"));
-    op->SetInput("DX", this->Output(framework::GradVarName("X")));
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetAttrMap(this->Attrs());
-    op->SetOutput("DOut", this->InputGrad("Out"));
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// square Grad: dx=2x*dy
-// square GradGrad: ddy=2x*ddx, dx=2dy*ddx
-template <typename T>
-class SquareDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("square_grad_grad");
-    op->SetInput("X", this->Input("X"));
-    // Out@GRAD: dy
-    op->SetInput("DOut", this->Input(framework::GradVarName("Out")));
-    // X@GRAD@GRAD: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-
-    op->SetAttrMap(this->Attrs());
-
-    // X@GRAD: dx
-    op->SetOutput("DX", this->InputGrad("X"));
-    // Out@GRAD@GRAD: ddy
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
-// log Grad: dx = dout / x
-// log Grad Grad: ddout = ddx / x; dx = -(dout / x) * (ddx / x)
-template <typename T>
-class LogDoubleGradMaker : public ::paddle::framework::SingleGradOpMaker<T> {
- public:
-  using ::paddle::framework::SingleGradOpMaker<T>::SingleGradOpMaker;
-
- protected:
-  void Apply(GradOpPtr<T> op) const override {
-    op->SetType("log_grad_grad");
-    op->SetInput("X", this->Input("X"));
-    // X@GRAD@GRAD: ddx
-    op->SetInput("DDX", this->OutputGrad(framework::GradVarName("X")));
-    op->SetInput("DOut", this->Input(framework::GradVarName("Out")));
-    op->SetAttrMap(this->Attrs());
-    // X@GRAD: dx
-    op->SetOutput("DX", this->InputGrad("X"));
-    // Out@GRAD@GRAD: ddy
-    op->SetOutput("DDOut", this->InputGrad(framework::GradVarName("Out")));
-  }
-};
-
 DECLARE_INPLACE_OP_INFERER(ActivationGradOpInplaceInferer,
                            {framework::GradVarName("Out"),  // dout
                             framework::GradVarName("X")});  // dx
@@ -971,27 +532,7 @@ FOR_EACH_ACTIVATION_OP(REGISTER_ACTIVATION_OP);
 FOR_EACH_ACTIVATION_OP(REGISTER_ACTIVATION_CPU_KERNEL);
 
 REGISTER_ACTIVATION_OP(brelu, BRelu, BReluFunctor, BReluGradFunctor);
-REGISTER_ACTIVATION_OP(thresholded_relu,
-                       ThresholdedRelu,
-                       ThresholdedReluFunctor,
-                       ThresholdedReluGradFunctor);
 REGISTER_ACTIVATION_OP(relu6, Relu6, Relu6Functor, Relu6GradFunctor);
-REGISTER_ACTIVATION_OP(softshrink,
-                       SoftShrink,
-                       SoftShrinkFunctor,
-                       SoftShrinkGradFunctor);
-REGISTER_ACTIVATION_OP(tanh_shrink,
-                       TanhShrink,
-                       TanhShrinkFunctor,
-                       TanhShrinkGradFunctor);
-REGISTER_ACTIVATION_OP(softsign,
-                       Softsign,
-                       SoftsignFunctor,
-                       SoftsignGradFunctor);
-REGISTER_ACTIVATION_OP(softplus,
-                       Softplus,
-                       SoftplusFunctor,
-                       SoftplusGradFunctor);
 REGISTER_ACTIVATION_OP(mish, Mish, MishFunctor, MishGradFunctor);
 REGISTER_ACTIVATION_OP(stanh, STanh, STanhFunctor, STanhGradFunctor);
 REGISTER_ACTIVATION_OP(hard_swish,
@@ -1000,205 +541,6 @@ REGISTER_ACTIVATION_OP(hard_swish,
                        HardSwishGradFunctor);
 REGISTER_ACTIVATION_OP(swish, Swish, SwishFunctor, SwishGradFunctor);
 
-/* ==========================    sigmoid register  =============================
- */
-// 1. Register Sigmoid Operator
-REGISTER_OPERATOR(
-    sigmoid,
-    ops::ActivationOp,
-    ops::SigmoidOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::SigmoidGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::SigmoidGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    std::conditional<ops::CanInplaceAct<ops::SigmoidGradFunctor<float>>(),
-                     ops::ActFwdInplaceInferer,
-                     void>::type);
-
-// 2. Register Sigmoid Grad Operator
-REGISTER_OPERATOR(sigmoid_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::SigmoidDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::SigmoidDoubleGradMaker<paddle::imperative::OpBase>);
-
-// 3. Register Sigmoid DoubleGrad Operator
-REGISTER_OPERATOR(
-    sigmoid_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::SigmoidGradGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer,
-    ops::SigmoidTripleGradMaker<paddle::framework::OpDesc>,
-    ops::SigmoidTripleGradMaker<paddle::imperative::OpBase>);
-
-// 4. Register Sigmoid TripleGrad Operator
-REGISTER_OPERATOR(sigmoid_triple_grad,
-                  ops::ActivationOpTripleGrad<
-                      ops::SigmoidTripleGradFunctor<float>::FwdDeps()>,
-                  ops::ActivationTripleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ==========================    relu register  ============================= */
-REGISTER_OPERATOR(
-    relu,
-    ops::ActivationOp,
-    ops::ReluOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::ReluGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::ReluGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(relu_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::ReluDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::ReluDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    relu_grad_grad,
-    ops::ActivationOpDoubleGrad2<ops::ReluGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ======================== leaky relu register  ============================ */
-REGISTER_OPERATOR(
-    leaky_relu,
-    ops::ActivationOp,
-    ops::LeakyReluOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::LeakyReluGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::LeakyReluGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(leaky_relu_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::LeakyReluDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::LeakyReluDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    leaky_relu_grad_grad,
-    ops::ActivationOpDoubleGrad2<ops::LeakyReluGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ========================    elu  register     ============================ */
-REGISTER_OPERATOR(elu,
-                  ops::ActivationOp,
-                  ops::ELUOpMaker,
-                  ops::ActivationOpInferVarType,
-                  ops::ELUGradOpMaker<paddle::framework::OpDesc>,
-                  ops::ELUGradOpMaker<paddle::imperative::OpBase>,
-                  ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(elu_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::ELUDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::ELUDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    elu_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::ELUGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ========================    celu  register     ============================
- */
-REGISTER_OPERATOR(
-    celu,
-    ops::ActivationOp,
-    ops::CELUOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::CELUGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::CELUGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(celu_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::CELUDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::CELUDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    celu_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::CELUGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ===========================   sqrt register  ============================= */
-REGISTER_OPERATOR(
-    sqrt,
-    ops::ActivationOp,
-    ops::SqrtOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::SqrtGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::SqrtGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(sqrt_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::SqrtDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::SqrtDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    sqrt_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::SqrtGradGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ===========================   rsqrt register  =============================
- */
-REGISTER_OPERATOR(
-    rsqrt,
-    ops::ActivationOp,
-    ops::RsqrtOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::RsqrtGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::RsqrtGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(rsqrt_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::RsqrtDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::RsqrtDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    rsqrt_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::RsqrtGradGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
-/* ==========================   square register  ============================ */
-REGISTER_OPERATOR(
-    square,
-    ops::ActivationOp,
-    ops::SquareOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::SquareGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::SquareGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(square_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::SquareDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::SquareDoubleGradMaker<paddle::imperative::OpBase>);
-REGISTER_OPERATOR(
-    square_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::SquareGradGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
-/* ========================================================================== */
-
 /* ==========================   pow register  ============================ */
 
 REGISTER_OPERATOR(
@@ -1216,28 +558,6 @@ REGISTER_OPERATOR(pow_grad,
                   ops::ActivationGradOpInplaceInferer);
 /* ========================================================================== */
 
-/* ==========================  Log register ==================================*/
-REGISTER_OPERATOR(
-    log,
-    ops::ActivationOp,
-    ops::LogOpMaker,
-    ops::ActivationOpInferVarType,
-    ops::ActivationGradOpMaker<ops::LogGradFunctor<float>::FwdDeps(),
-                               paddle::framework::OpDesc>,
-    ops::ActivationGradOpMaker<ops::LogGradFunctor<float>::FwdDeps(),
-                               paddle::imperative::OpBase>,
-    ops::ActFwdInplaceInferer);
-REGISTER_OPERATOR(log_grad,
-                  ops::ActivationOpGrad,
-                  ops::ActivationGradOpInplaceInferer,
-                  ops::LogDoubleGradMaker<paddle::framework::OpDesc>,
-                  ops::LogDoubleGradMaker<paddle::imperative::OpBase>);
-
-REGISTER_OPERATOR(
-    log_grad_grad,
-    ops::ActivationOpDoubleGrad<ops::LogGradGradFunctor<float>::FwdDeps()>,
-    ops::ActivationDoubleGradOpInplaceInferer);
-
 /* ==========================  register checkpoint ===========================*/
 REGISTER_OP_VERSION(leaky_relu)
     .AddCheckpoint(
diff --git a/paddle/fluid/operators/activation_op.h b/paddle/fluid/operators/activation_op.h
index 94d5fcca508f9dd8a5dc3a415f288ccc9f00d3d3..a4720905ad54ad4ea9039742e669361e32a43183 100644
--- a/paddle/fluid/operators/activation_op.h
+++ b/paddle/fluid/operators/activation_op.h
@@ -266,57 +266,19 @@ using BReluFunctor = phi::funcs::HardTanhFunctor<T>;
 template <typename T>
 using BReluGradFunctor = phi::funcs::HardTanhGradFunctor<T>;
 
-USE_PHI_FUNCTOR(Cos)
-USE_PHI_FUNCTOR(Tan)
-USE_PHI_FUNCTOR(Acos)
-USE_PHI_FUNCTOR(Sin)
-USE_PHI_FUNCTOR(Asin)
-USE_PHI_FUNCTOR(Atan)
-USE_PHI_FUNCTOR(Sinh)
-USE_PHI_FUNCTOR(Cosh)
-USE_PHI_FUNCTOR(Asinh)
-USE_PHI_FUNCTOR(Acosh)
-USE_PHI_FUNCTOR(Atanh)
 USE_PHI_FUNCTOR(Tanh)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Tanh)
-USE_PHI_TRIPLE_GRAD_FUNCTOR(Tanh)
-USE_PHI_FUNCTOR(ThresholdedRelu)
 USE_PHI_FUNCTOR(Relu6)
 USE_PHI_FUNCTOR(LeakyRelu)
 USE_PHI_DOUBLE_GRAD_FUNCTOR(LeakyRelu)
 USE_PHI_FUNCTOR(HardShrink)
-USE_PHI_FUNCTOR(SoftShrink)
-USE_PHI_FUNCTOR(TanhShrink)
-USE_PHI_FUNCTOR(Silu)
 USE_PHI_FUNCTOR(ELU)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(ELU)
-USE_PHI_FUNCTOR(Softsign)
 USE_PHI_FUNCTOR(Sigmoid)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Sigmoid)
-USE_PHI_TRIPLE_GRAD_FUNCTOR(Sigmoid)
-USE_PHI_FUNCTOR(LogSigmoid)
 USE_PHI_FUNCTOR(HardSigmoid)
-USE_PHI_FUNCTOR(Log)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Log)
-USE_PHI_FUNCTOR(Log2)
-USE_PHI_FUNCTOR(Log10)
-USE_PHI_FUNCTOR(Log1p)
 USE_PHI_FUNCTOR(Swish)
 USE_PHI_FUNCTOR(HardSwish)
 USE_PHI_FUNCTOR(Pow)
-USE_PHI_FUNCTOR(Expm1)
 USE_PHI_FUNCTOR(Mish)
 USE_PHI_FUNCTOR(STanh)
-USE_PHI_FUNCTOR(Reciprocal)
-USE_PHI_FUNCTOR(Square)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Square)
-USE_PHI_FUNCTOR(Sqrt)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Sqrt)
-USE_PHI_FUNCTOR(Rsqrt)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(Rsqrt)
-USE_PHI_FUNCTOR(Softplus)
-USE_PHI_FUNCTOR(CELU)
-USE_PHI_DOUBLE_GRAD_FUNCTOR(CELU)
 
 template <typename T>
 using ELUGradNegativeAlphaFunctor = phi::funcs::ELUGradNegativeAlphaFunctor<T>;
@@ -386,40 +348,6 @@ struct SoftReluGradFunctor : public BaseActivationFunctor<T> {
   }
 };
 
-template <typename DeviceContext, typename T>
-class ELUGradKernel : public framework::OpKernel<T> {
- public:
-  void Compute(const framework::ExecutionContext& context) const override {
-    auto* X = context.Input<phi::DenseTensor>("X");
-    auto* Out = context.Input<phi::DenseTensor>("Out");
-    auto* dOut = context.Input<phi::DenseTensor>(framework::GradVarName("Out"));
-    auto* dX = context.Output<phi::DenseTensor>(framework::GradVarName("X"));
-    const float alpha = context.Attr<float>("alpha");
-    dX->mutable_data<T>(context.GetPlace());
-
-    auto x = framework::EigenVector<T>::Flatten(
-        GET_DATA_SAFELY(X, "Input", "X", "elu_grad"));
-    auto out = framework::EigenVector<T>::Flatten(
-        GET_DATA_SAFELY(Out, "Input", "Out", "elu_grad"));
-    auto dout = framework::EigenVector<T>::Flatten(
-        GET_DATA_SAFELY(dOut, "Input", "dOut", "elu_grad"));
-    auto dx = framework::EigenVector<T>::Flatten(
-        GET_DATA_SAFELY(dX, "Output", "dX", "elu_grad"));
-    auto* place =
-        context.template device_context<DeviceContext>().eigen_device();
-
-    if (alpha > 0) {
-      ELUGradFunctor<T> functor;
-      functor.alpha = alpha;
-      functor(*place, x, out, dout, dx);
-    } else {
-      ELUGradNegativeAlphaFunctor<T> functor;
-      functor.alpha = alpha;
-      functor(*place, x, out, dout, dx);
-    }
-  }
-};
-
 template <typename T>
 struct AbsGradGradFunctor : public BaseActivationFunctor<T> {
   template <typename Device>
diff --git a/paddle/fluid/operators/mkldnn/nhwc_op_tests.cmake b/paddle/fluid/operators/mkldnn/nhwc_op_tests.cmake
index 4f88b091c02ae8a80168dfd6051868a85a2f031b..74c7e1334cfe790ad4230d440468177a4ed6b668 100644
--- a/paddle/fluid/operators/mkldnn/nhwc_op_tests.cmake
+++ b/paddle/fluid/operators/mkldnn/nhwc_op_tests.cmake
@@ -8,6 +8,7 @@ cc_test_old(
   shape_op
   crop_op
   activation_op
+  generated_op
   pooling
   transpose_op
   scope
diff --git a/paddle/phi/api/yaml/backward.yaml b/paddle/phi/api/yaml/backward.yaml
index 35cf2c66fd2f3116342290e18c2fe4ac0a9a7dac..7aee6e9f89180ab2dd69f14ea6de3fb24345bbc3 100644
--- a/paddle/phi/api/yaml/backward.yaml
+++ b/paddle/phi/api/yaml/backward.yaml
@@ -117,6 +117,29 @@
     func : ceil_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : celu_double_grad
+  forward : celu_grad(Tensor x, Tensor grad_out, float alpha) -> Tensor(grad_x)
+  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad, float alpha)
+  output : Tensor(x_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [x, x]
+  kernel :
+    func : celu_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : celu_grad
+  forward : celu(Tensor x, float alpha) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad, float alpha)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param: [x]
+  kernel :
+    func : celu_grad
+  backward : celu_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : cholesky_grad
   forward : cholesky (Tensor x, bool upper) -> Tensor(out)
   args : (Tensor out, Tensor out_grad, bool upper)
@@ -236,6 +259,29 @@
     func : dot_grad
     data_type : out_grad
 
+- backward_op : elu_double_grad
+  forward : elu_grad (Tensor x, Tensor out, Tensor grad_out, float alpha)-> Tensor(grad_x)
+  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad, float alpha)
+  output : Tensor(x_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [x, x]
+  kernel :
+    func : elu_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : elu_grad
+  forward : elu (Tensor x, float alpha) -> Tensor(out)
+  args : (Tensor x, Tensor out, Tensor out_grad, float alpha)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : elu_grad
+  backward : elu_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : erf_grad
   forward : erf (Tensor x) -> Tensor(out)
   args : (Tensor x, Tensor out_grad)
@@ -350,6 +396,29 @@
     func : hard_sigmoid_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : leaky_relu_double_grad
+  forward : leaky_relu_grad (Tensor x, Tensor grad_out, float negative_slope) -> Tensor(grad_x)
+  args : (Tensor x, Tensor grad_x_grad, float negative_slope)
+  output : Tensor(grad_out_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [grad_x_grad]
+  kernel :
+    func : leaky_relu_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : leaky_relu_grad
+  forward : leaky_relu (Tensor x, float negative_slope) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad, float negative_slope)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : leaky_relu_grad
+  backward : leaky_relu_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : lgamma_grad
   forward : lgamma(Tensor x) -> Tensor(out)
   args : (Tensor x, Tensor out_grad)
@@ -393,6 +462,29 @@
     func : log2_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : log_double_grad
+  forward : log_grad (Tensor x, Tensor grad_out) -> Tensor(grad_x)
+  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad)
+  output : Tensor(x_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [x, x]
+  kernel :
+    func : log_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : log_grad
+  forward : log (Tensor x) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : log_grad
+  backward : log_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : logit_grad
   forward : logit (Tensor x, float eps = 1e-6f) -> Tensor(out)
   args : (Tensor x, Tensor out_grad, float eps)
@@ -445,6 +537,29 @@
     func : reciprocal_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : relu_double_grad
+  forward : relu_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
+  args : (Tensor out, Tensor grad_x_grad)
+  output : Tensor(grad_out_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [out]
+  kernel :
+    func : relu_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : relu_grad
+  forward : relu (Tensor x) -> Tensor(out)
+  args : (Tensor out, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [out]
+  kernel :
+    func : relu_grad
+  backward: relu_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : round_grad
   forward : round(Tensor x) -> Tensor(out)
   args : (Tensor out_grad)
@@ -456,6 +571,29 @@
     func : round_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : rsqrt_double_grad
+  forward : rsqrt_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
+  args : (Tensor out, Tensor grad_x, Tensor grad_x_grad)
+  output : Tensor(out_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [out, out]
+  kernel :
+    func : rsqrt_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : rsqrt_grad
+  forward : rsqrt (Tensor x) -> Tensor(out)
+  args : (Tensor out, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [out]
+  kernel :
+    func : rsqrt_grad
+  backward : rsqrt_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : send_uv_grad
   forward : send_uv (Tensor x, Tensor y, Tensor src_index, Tensor dst_index, str message_op = "ADD") -> Tensor(out)
   args: (Tensor x, Tensor y, Tensor src_index, Tensor dst_index, Tensor out_grad, str message_op = "ADD")
@@ -467,6 +605,42 @@
     func : send_uv_grad
     data_type : x
 
+- backward_op : sigmoid_double_grad
+  forward : sigmoid_grad (Tensor out, Tensor fwd_grad_out) -> Tensor(grad_x)
+  args : (Tensor out, Tensor fwd_grad_out, Tensor grad_x_grad)
+  output : Tensor(out_grad), Tensor(fwd_grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [out, fwd_grad_out]
+  kernel :
+    func : sigmoid_double_grad
+  backward : sigmoid_triple_grad
+  inplace : (grad_x_grad -> fwd_grad_out_grad)
+
+- backward_op : sigmoid_grad
+  forward : sigmoid (Tensor x) -> Tensor(out)
+  args : (Tensor out, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [out]
+  kernel :
+    func : sigmoid_grad
+  backward : sigmoid_double_grad
+  inplace : (out_grad -> x_grad)
+
+- backward_op : sigmoid_triple_grad
+  forward : sigmoid_double_grad (Tensor out, Tensor fwd_grad_out, Tensor grad_grad_x) -> Tensor(grad_out), Tensor(grad_grad_out)
+  args : (Tensor out, Tensor fwd_grad_out, Tensor grad_grad_x, Tensor grad_out_grad, Tensor grad_grad_out_grad)
+  output : Tensor(out_grad), Tensor(fwd_grad_out_grad), Tensor(grad_grad_x_grad)
+  infer_meta :
+    func : GeneralTernaryGradInferMeta
+    param : [out, fwd_grad_out, grad_grad_x]
+  kernel :
+    func : sigmoid_triple_grad
+  optional : grad_grad_out_grad
+  inplace : (grad_grad_x -> fwd_grad_out_grad)
+
 - backward_op : silu_grad
   forward : silu (Tensor x) -> Tensor(out)
   args : (Tensor x, Tensor out_grad)
@@ -512,6 +686,39 @@
     func : sinh_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : softplus_grad
+  forward : softplus (Tensor x, float beta, float threshold) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad, float beta, float threshold)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softplus_grad
+  inplace : (out_grad -> x_grad)
+
+- backward_op : softshrink_grad
+  forward : softshrink (Tensor x, float threshold) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad, float threshold)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softshrink_grad
+  inplace : (out_grad -> x_grad)
+
+- backward_op : softsign_grad
+  forward : softsign (Tensor x) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softsign_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : solve_grad
   forward : solve (Tensor x, Tensor y) -> Tensor(out)
   args : (Tensor x, Tensor y, Tensor out, Tensor out_grad)
@@ -522,6 +729,52 @@
   kernel :
     func : solve_grad
 
+- backward_op : sqrt_double_grad
+  forward : sqrt_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
+  args : (Tensor out, Tensor grad_x, Tensor grad_x_grad)
+  output : Tensor(out_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [out, out]
+  kernel :
+    func : sqrt_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : sqrt_grad
+  forward : sqrt (Tensor x) -> Tensor(out)
+  args : (Tensor out, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [out]
+  kernel :
+    func : sqrt_grad
+  backward : sqrt_double_grad
+  inplace : (out_grad -> x_grad)
+
+- backward_op : square_double_grad
+  forward : square_grad (Tensor x, Tensor grad_out) -> Tensor(grad_x)
+  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad)
+  output : Tensor(x_grad), Tensor(grad_out_grad)
+  infer_meta :
+    func : GeneralBinaryGradInferMeta
+    param : [x, x]
+  kernel :
+    func : square_double_grad
+  inplace : (grad_x_grad -> grad_out_grad)
+
+- backward_op : square_grad
+  forward : square (Tensor x) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : square_grad
+  backward : square_double_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : tan_grad
   forward : tan (Tensor x) -> Tensor(out)
   args : (Tensor x, Tensor out_grad)
@@ -557,6 +810,17 @@
   backward : tanh_double_grad
   inplace : (out_grad -> x_grad)
 
+- backward_op : tanh_shrink_grad
+  forward : tanh_shrink (Tensor x) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : tanh_shrink_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : tanh_triple_grad
   forward : tanh_double_grad (Tensor out, Tensor grad_out_forward, Tensor grad_x_grad_forward) -> Tensor(grad_out_new), Tensor(grad_out_grad)
   args : (Tensor out, Tensor grad_out_forward, Tensor grad_x_grad_forward, Tensor grad_out_new_grad, Tensor grad_out_grad_grad)
@@ -568,6 +832,17 @@
     func : tanh_triple_grad
   inplace : (grad_x_grad_forward -> grad_out_forward_grad)
 
+- backward_op : thresholded_relu_grad
+  forward : thresholded_relu (Tensor x, float threshold) -> Tensor(out)
+  args : (Tensor x, Tensor out_grad, float threshold)
+  output : Tensor(x_grad)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : thresholded_relu_grad
+  inplace : (out_grad -> x_grad)
+
 - backward_op : trace_grad
   forward : trace (Tensor x, int offset, int axis1, int axis2) -> Tensor(out)
   args : (Tensor x, Tensor out_grad, int offset, int axis1, int axis2)
diff --git a/paddle/phi/api/yaml/generator/generate_op.py b/paddle/phi/api/yaml/generator/generate_op.py
index 777b5283743fd06ba3ca3db8f5ca19658b1a2aac..8a6e503f8f690b74462bfada6bec6e5581506aa4 100644
--- a/paddle/phi/api/yaml/generator/generate_op.py
+++ b/paddle/phi/api/yaml/generator/generate_op.py
@@ -75,6 +75,11 @@ def replace_compat_name(api_op_map, forward_api_dict, backward_api_dict):
         else:
             return names[0].strip(), names[1].split(')')[0].strip()
 
+    def update_api_attr_name(attrs, attrs_alias_map):
+        for attr_item in attrs:
+            if attr_item['name'] in attrs_alias_map:
+                attr_item['name'] = attrs_alias_map[attr_item['name']]
+
     for api_args in api_op_map:
         api_name, op_name = get_api_and_op_name(api_args['op'])
         if api_name not in forward_api_dict:
@@ -99,6 +104,13 @@ def replace_compat_name(api_op_map, forward_api_dict, backward_api_dict):
                 double_grad_item = backward_api_dict[double_grad_api_name]
                 backward_api_item['backward'] = double_grad_op_name
                 double_grad_item['op_name'] = double_grad_op_name
+                if 'attrs' in api_args:
+                    update_api_attr_name(
+                        double_grad_item['attrs'], api_args['attrs']
+                    )
+                    update_api_attr_name(
+                        double_grad_item['forward']['attrs'], api_args['attrs']
+                    )
 
                 # for triple grad
                 if len(backward_op_list) > 2:
@@ -109,6 +121,14 @@ def replace_compat_name(api_op_map, forward_api_dict, backward_api_dict):
                     triple_grad_item = backward_api_dict[triple_grad_api_name]
                     double_grad_item['backward'] = triple_grad_op_name
                     triple_grad_item['op_name'] = triple_grad_op_name
+                    if 'attrs' in api_args:
+                        update_api_attr_name(
+                            triple_grad_item['attrs'], api_args['attrs']
+                        )
+                        update_api_attr_name(
+                            triple_grad_item['forward']['attrs'],
+                            api_args['attrs'],
+                        )
 
         key_set = ['inputs', 'attrs', 'outputs']
         args_map = {}
diff --git a/paddle/phi/api/yaml/generator/templates/operator_utils.c.j2 b/paddle/phi/api/yaml/generator/templates/operator_utils.c.j2
index 502266ce7a994694a7c412a7a3a800fc79f688fb..0c86bb5d416eb03c5403cafa48c5daebc6545e93 100644
--- a/paddle/phi/api/yaml/generator/templates/operator_utils.c.j2
+++ b/paddle/phi/api/yaml/generator/templates/operator_utils.c.j2
@@ -459,7 +459,7 @@ class {{name | to_pascal_case}}OpMaker : public framework::SingleGradOpMaker<T>
 Input({{name_in_forward_orig | to_opmaker_name}})
   {%- elif name in output_names %}
     {% set name_in_forward_orig = output_orig_names[output_names.index(name)]%}
-Output({{name | to_opmaker_name}})
+Output({{name_in_forward_orig | to_opmaker_name}})
   {%- elif name.endswith("_grad") %}{# output grad#}
     {% set name_in_forward = name[:-5] %}
     {% if name_in_forward in output_names %}
diff --git a/paddle/phi/api/yaml/legacy_backward.yaml b/paddle/phi/api/yaml/legacy_backward.yaml
index c4b16f73101e184f3ffdf4466934e6685a92405f..62f69ed3a3bfe1416cc2b298b9bed2da0e68ecc3 100755
--- a/paddle/phi/api/yaml/legacy_backward.yaml
+++ b/paddle/phi/api/yaml/legacy_backward.yaml
@@ -217,29 +217,6 @@
   invoke : cast (out_grad, x.dtype())
   no_need_buffer : x
 
-- backward_op : celu_double_grad
-  forward : celu_grad(Tensor x, Tensor grad_out, float alpha) -> Tensor(grad_x)
-  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad, float alpha)
-  output : Tensor(x_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [x, x]
-  kernel :
-    func : celu_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : celu_grad
-  forward : celu(Tensor x, float alpha) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad, float alpha)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param: [x]
-  kernel :
-    func : celu_grad
-  backward : celu_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : clip_double_grad
   forward : clip_grad (Tensor x, Tensor grad_out, Scalar min = 0., Scalar max = 0.) -> Tensor(grad_x)
   args : (Tensor x, Tensor grad_x_grad, Scalar min = 0., Scalar max = 0.)
@@ -552,29 +529,6 @@
   kernel :
     func : elementwise_pow_grad
 
-- backward_op : elu_double_grad
-  forward : elu_grad (Tensor x, Tensor out, Tensor grad_out, float alpha)-> Tensor(grad_x)
-  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad, float alpha)
-  output : Tensor(x_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [x, x]
-  kernel :
-    func : elu_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : elu_grad
-  forward : elu (Tensor x, float alpha) -> Tensor(out)
-  args : (Tensor x, Tensor out, Tensor out_grad, float alpha)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : elu_grad
-  backward : elu_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : embedding_grad
   forward : embedding (Tensor x, Tensor weight, int64_t padding_idx=-1, bool sparse=false) -> Tensor(out)
   args : (Tensor x, Tensor weight, Tensor out_grad, int64_t padding_idx=-1, bool sparse=false)
@@ -940,29 +894,6 @@
   no_need_buffer : bias
   optional : scale, bias
 
-- backward_op : leaky_relu_double_grad
-  forward : leaky_relu_grad (Tensor x, Tensor grad_out, float negative_slope) -> Tensor(grad_x)
-  args : (Tensor x, Tensor grad_x_grad, float negative_slope)
-  output : Tensor(grad_out_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [grad_x_grad]
-  kernel :
-    func : leaky_relu_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : leaky_relu_grad
-  forward : leaky_relu (Tensor x, float negative_slope) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad, float negative_slope)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : leaky_relu_grad
-  backward : leaky_relu_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : lerp_grad
   forward : lerp (Tensor x, Tensor y, Tensor weight) -> Tensor(out)
   args : (Tensor x, Tensor y, Tensor weight, Tensor out, Tensor out_grad)
@@ -985,29 +916,6 @@
     func : linear_interp_grad
     data_type : output_grad
 
-- backward_op : log_double_grad
-  forward : log_grad (Tensor x, Tensor grad_out) -> Tensor(grad_x)
-  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad)
-  output : Tensor(x_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [x, x]
-  kernel :
-    func : log_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : log_grad
-  forward : log (Tensor x) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : log_grad
-  backward : log_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : log_loss_grad
   forward : log_loss (Tensor input, Tensor label, float epsilon) -> Tensor(out)
   args : (Tensor input, Tensor label, Tensor out_grad, float epsilon)
@@ -1537,29 +1445,6 @@
     func : relu6_grad
   inplace : (out_grad -> x_grad)
 
-- backward_op : relu_double_grad
-  forward : relu_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
-  args : (Tensor out, Tensor grad_x_grad)
-  output : Tensor(grad_out_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [out]
-  kernel :
-    func : relu_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : relu_grad
-  forward : relu (Tensor x) -> Tensor(out)
-  args : (Tensor out, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [out]
-  kernel :
-    func : relu_grad
-  backward: relu_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : renorm_grad
   forward : renorm (Tensor x, float p, int axis, float max_norm) -> Tensor(out)
   args : (Tensor x, Tensor out_grad, float p, int axis, float max_norm)
@@ -1683,29 +1568,6 @@
     data_type : x
   no_need_buffer : x
 
-- backward_op : rsqrt_double_grad
-  forward : rsqrt_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
-  args : (Tensor out, Tensor grad_x, Tensor grad_x_grad)
-  output : Tensor(out_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [out, out]
-  kernel :
-    func : rsqrt_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : rsqrt_grad
-  forward : rsqrt (Tensor x) -> Tensor(out)
-  args : (Tensor out, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [out]
-  kernel :
-    func : rsqrt_grad
-  backward : rsqrt_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : scale_grad
   forward : scale (Tensor x, Scalar scale, float bias, bool bias_after_scale) -> Tensor(out)
   args : (Tensor out_grad, Scalar scale=1.0, bool bias_after_scale=true)
@@ -1791,42 +1653,6 @@
     func : sigmoid_cross_entropy_with_logits_grad
   inplace : (out_grad -> x_grad)
 
-- backward_op : sigmoid_double_grad
-  forward : sigmoid_grad (Tensor out, Tensor fwd_grad_out) -> Tensor(grad_x)
-  args : (Tensor out, Tensor fwd_grad_out, Tensor grad_x_grad)
-  output : Tensor(out_grad), Tensor(fwd_grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [out, fwd_grad_out]
-  kernel :
-    func : sigmoid_double_grad
-  backward : sigmoid_triple_grad
-  inplace : (grad_x_grad -> fwd_grad_out_grad)
-
-- backward_op : sigmoid_grad
-  forward : sigmoid (Tensor x) -> Tensor(out)
-  args : (Tensor out, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [out]
-  kernel :
-    func : sigmoid_grad
-  backward : sigmoid_double_grad
-  inplace : (out_grad -> x_grad)
-
-- backward_op : sigmoid_triple_grad
-  forward : sigmoid_double_grad (Tensor out, Tensor fwd_grad_out, Tensor grad_grad_x) -> Tensor(grad_out), Tensor(grad_grad_out)
-  args : (Tensor out, Tensor fwd_grad_out, Tensor grad_grad_x, Tensor grad_out_grad, Tensor grad_grad_out_grad)
-  output : Tensor(out_grad), Tensor(fwd_grad_out_grad), Tensor(grad_grad_x_grad)
-  infer_meta :
-    func : GeneralTernaryGradInferMeta
-    param : [out, fwd_grad_out, grad_grad_x]
-  kernel :
-    func : sigmoid_triple_grad
-  optional : grad_grad_out_grad
-  inplace : (grad_grad_x -> fwd_grad_out_grad)
-
 - backward_op : sign_grad
   forward : sign (Tensor x) -> Tensor(out)
   args : (Tensor out_grad)
@@ -1872,39 +1698,6 @@
     func : softmax_grad
     use_gpudnn : true
 
-- backward_op : softplus_grad
-  forward : softplus (Tensor x, float beta, float threshold) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad, float beta, float threshold)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : softplus_grad
-  inplace : (out_grad -> x_grad)
-
-- backward_op : softshrink_grad
-  forward : softshrink (Tensor x, float threshold) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad, float threshold)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : soft_shrink_grad
-  inplace : (out_grad -> x_grad)
-
-- backward_op : softsign_grad
-  forward : softsign (Tensor x) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : softsign_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : spectral_norm_grad
   forward : spectral_norm (Tensor weight, Tensor u, Tensor v, int dim, int power_iters, float eps) -> Tensor(out)
   args : (Tensor weight, Tensor u, Tensor v, Tensor out_grad, int dim, int power_iters, float eps)
@@ -1927,52 +1720,6 @@
   output : Tensor(x_grad)
   invoke : concat( out_grad, axis)
 
-- backward_op : sqrt_double_grad
-  forward : sqrt_grad (Tensor out, Tensor grad_out) -> Tensor(grad_x)
-  args : (Tensor out, Tensor grad_x, Tensor grad_x_grad)
-  output : Tensor(out_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [out, out]
-  kernel :
-    func : sqrt_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : sqrt_grad
-  forward : sqrt (Tensor x) -> Tensor(out)
-  args : (Tensor out, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [out]
-  kernel :
-    func : sqrt_grad
-  backward : sqrt_double_grad
-  inplace : (out_grad -> x_grad)
-
-- backward_op : square_double_grad
-  forward : square_grad (Tensor x, Tensor grad_out) -> Tensor(grad_x)
-  args : (Tensor x, Tensor grad_out, Tensor grad_x_grad)
-  output : Tensor(x_grad), Tensor(grad_out_grad)
-  infer_meta :
-    func : GeneralBinaryGradInferMeta
-    param : [x, x]
-  kernel :
-    func : square_double_grad
-  inplace : (grad_x_grad -> grad_out_grad)
-
-- backward_op : square_grad
-  forward : square (Tensor x) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : square_grad
-  backward : square_double_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : squared_l2_norm_grad
   forward : squared_l2_norm(Tensor x) -> Tensor(out)
   args : (Tensor x, Tensor out_grad)
@@ -2112,17 +1859,6 @@
   kernel :
     func : take_along_axis_grad
 
-- backward_op : tanh_shrink_grad
-  forward : tanh_shrink (Tensor x) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : tanh_shrink_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : temporal_shift_grad
   forward : temporal_shift(Tensor x, int seg_num, float shift_ratio, str data_format_str) -> Tensor(out)
   args : (Tensor out_grad, int seg_num, float shift_ratio, str data_format_str)
@@ -2133,17 +1869,6 @@
   kernel :
     func : temporal_shift_grad
 
-- backward_op : thresholded_relu_grad
-  forward : thresholded_relu (Tensor x, float threshold) -> Tensor(out)
-  args : (Tensor x, Tensor out_grad, float threshold)
-  output : Tensor(x_grad)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : thresholded_relu_grad
-  inplace : (out_grad -> x_grad)
-
 - backward_op : tile_double_grad
   forward : tile_grad (Tensor x, Tensor grad_out, IntArray repeat_times) -> Tensor(grad_x)
   args : (Tensor grad_x_grad, IntArray repeat_times)
diff --git a/paddle/phi/api/yaml/legacy_ops.yaml b/paddle/phi/api/yaml/legacy_ops.yaml
index 0f118add06abb77ce9326fa216a0ae961e079bd4..be74f516685201dbca75e396e7f3f0f1afbe7caa 100755
--- a/paddle/phi/api/yaml/legacy_ops.yaml
+++ b/paddle/phi/api/yaml/legacy_ops.yaml
@@ -357,16 +357,6 @@
     data_type : x
   backward : cast_grad
 
-- op : celu
-  args : (Tensor x, float alpha)
-  output : Tensor(out)
-  infer_meta :
-    func : UnchangedInferMeta
-    param: [x]
-  kernel :
-    func : celu
-  backward : celu_grad
-
 - op : check_finite_and_unscale_
   args : (Tensor[] x, Tensor scale, Tensor input_found_infinite)
   output : Tensor[](out){x.size()}, Tensor(output_found_infinite)
@@ -664,17 +654,6 @@
     func : elementwise_pow
   backward : elementwise_pow_grad
 
-- op : elu
-  args : (Tensor x, float alpha)
-  output : Tensor(out)
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : elu
-  inplace : (x -> out)
-  backward : elu_grad
-
 - op : embedding
   args : (Tensor x, Tensor weight, int64_t padding_idx=-1, bool sparse=false)
   output : Tensor
@@ -1241,16 +1220,6 @@
   backward : layer_norm_grad
   optional : scale, bias
 
-- op : leaky_relu
-  args : (Tensor x, float negative_slope)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : leaky_relu
-  backward : leaky_relu_grad
-
 - op : lerp
   args : (Tensor x, Tensor y, Tensor weight)
   output : Tensor(out)
@@ -1300,15 +1269,6 @@
     data_type : dtype
     backend : place
 
-- op : log
-  args : (Tensor x)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : log
-  backward: log_grad
-
 - op : log_loss
   args : (Tensor input, Tensor label, float epsilon)
   output : Tensor
@@ -1910,16 +1870,6 @@
     func : real
   backward : real_grad
 
-- op : relu
-  args : (Tensor x)
-  output : Tensor(out)
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : relu
-  inplace : (x -> out)
-  backward : relu_grad
-
 - op : relu6
   args : (Tensor x, float threshold)
   output : Tensor
@@ -2032,16 +1982,6 @@
     func : roll
   backward : roll_grad
 
-- op : rsqrt
-  args : (Tensor x)
-  output : Tensor(out)
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : rsqrt
-  inplace : (x -> out)
-  backward : rsqrt_grad
-
 - op : scale
   args : (Tensor x, Scalar scale, float bias, bool bias_after_scale)
   output : Tensor(out)
@@ -2160,15 +2100,6 @@
   kernel :
     func : shard_index
 
-- op : sigmoid
-  args : (Tensor x)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : sigmoid
-  backward : sigmoid_grad
-
 - op : sigmoid_cross_entropy_with_logits
   args : (Tensor x, Tensor label, bool normalize, int ignore_index)
   output : Tensor
@@ -2216,36 +2147,6 @@
   inplace : (x -> out)
   backward : softmax_grad
 
-- op : softplus
-  args : (Tensor x, float beta, float threshold)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : softplus
-  backward : softplus_grad
-
-- op : softshrink
-  args : (Tensor x, float threshold)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : soft_shrink
-  backward : softshrink_grad
-
-- op : softsign
-  args : (Tensor x)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : softsign
-  backward : softsign_grad
-
 - op : spectral_norm
   args : (Tensor weight, Tensor u, Tensor v, int dim, int power_iters, float eps)
   output : Tensor
@@ -2274,25 +2175,6 @@
     func : split_with_num
   backward : split_with_num_grad
 
-- op : sqrt
-  args : (Tensor x)
-  output : Tensor(out)
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : sqrt
-  inplace : (x -> out)
-  backward : sqrt_grad
-
-- op : square
-  args : (Tensor x)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : square
-  backward : square_grad
-
 - op : squared_l2_norm
   args : (Tensor x)
   output : Tensor
@@ -2394,15 +2276,6 @@
     data_type : arr
   backward : take_along_axis_grad
 
-- op : tanh_shrink
-  args : (Tensor x)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-  kernel :
-    func : tanh_shrink
-  backward : tanh_shrink_grad
-
 - op : temporal_shift
   args : (Tensor x, int seg_num, float shift_ratio, str data_format_str)
   output : Tensor
@@ -2412,16 +2285,6 @@
     func : temporal_shift
   backward : temporal_shift_grad
 
-- op : thresholded_relu
-  args : (Tensor x, float threshold)
-  output : Tensor
-  infer_meta :
-    func : UnchangedInferMeta
-    param : [x]
-  kernel :
-    func : thresholded_relu
-  backward : thresholded_relu_grad
-
 - op : tile
   args : (Tensor x, IntArray repeat_times)
   output : Tensor
diff --git a/paddle/phi/api/yaml/op_compat.yaml b/paddle/phi/api/yaml/op_compat.yaml
index 4dad61d58e3467792407024a068be04264d0e7bf..a67d4721c17564307bcf584052909836c11ad0eb 100644
--- a/paddle/phi/api/yaml/op_compat.yaml
+++ b/paddle/phi/api/yaml/op_compat.yaml
@@ -131,6 +131,13 @@
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
+- op : celu
+  backward : celu_grad, celu_double_grad(celu_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
+
 - op : cholesky
   inputs :
     x : X
@@ -316,7 +323,11 @@
              bool use_quantizer = false, float Scale_x = 1.0f, float Scale_y = 1.0f, float Scale_out = 1.0f]
 
 - op : elu
-  backward : elu_grad
+  backward : elu_grad, elu_double_grad (elu_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false]
 
@@ -504,7 +515,13 @@
     attrs : [bool use_mkldnn = false, str mkldnn_data_type = "float32", bool is_test = false]
 
 - op : leaky_relu
-  backward : leaky_relu_grad
+  backward : leaky_relu_grad, leaky_relu_double_grad (leaky_relu_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
+  attrs:
+    negative_slope : alpha
   extra :
     attrs : [bool use_mkldnn = false]
 
@@ -520,7 +537,11 @@
     attrs : [bool use_mkldnn = false]
 
 - op : log
-  backward : log_grad
+  backward : log_grad, log_double_grad (log_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -725,7 +746,11 @@
     attrs : [bool use_mkldnn = false]
 
 - op : relu
-  backward : relu_grad
+  backward : relu_grad, relu_double_grad (relu_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -754,7 +779,11 @@
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
 - op : rsqrt
-  backward : rsqrt_grad
+  backward : rsqrt_grad, rsqrt_double_grad (rsqrt_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -784,7 +813,11 @@
     attrs : [bool use_mkldnn = false]
 
 - op : sigmoid
-  backward : sigmoid_grad
+  backward : sigmoid_grad, sigmoid_double_grad (sigmoid_grad_grad), sigmoid_triple_grad
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -827,12 +860,29 @@
 
 - op : softplus
   backward : softplus_grad
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false, str fuse_activation_type = "", float fuse_activation_alpha = 0.0f,
              float fuse_activation_beta = 0.0f, float fuse_activation_scale = 1.0f]
 
+- op : softshrink
+  backward : softshrink_grad
+  inputs :
+    x : X
+  outputs :
+    out : Out
+  attrs :
+    threshold : lambda
+
 - op : softsign
   backward : softsign_grad
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -843,12 +893,20 @@
     out : Out
 
 - op : sqrt
-  backward : sqrt_grad
+  backward : sqrt_grad, sqrt_double_grad (sqrt_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
 - op : square
-  backward : square_grad
+  backward : square_grad, square_double_grad (square_grad_grad)
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
@@ -903,9 +961,19 @@
 
 - op : tanh_shrink
   backward : tanh_shrink_grad
+  inputs :
+    x : X
+  outputs :
+    out : Out
   extra :
     attrs : [bool use_mkldnn = false, bool use_cudnn = false]
 
+- op : thresholded_relu
+  inputs :
+    x : X
+  outputs :
+    out : Out
+
 - op : trace
   inputs :
     x : Input
diff --git a/paddle/phi/api/yaml/ops.yaml b/paddle/phi/api/yaml/ops.yaml
index 78eb97984013eeb4da149ff110763105af0dba31..efe1265e7d74eb695068715afbebe107015c8ae1 100644
--- a/paddle/phi/api/yaml/ops.yaml
+++ b/paddle/phi/api/yaml/ops.yaml
@@ -106,6 +106,16 @@
   inplace : (x -> out)
   backward : ceil_grad
 
+- op : celu
+  args : (Tensor x, float alpha = 1.0)
+  output : Tensor(out)
+  infer_meta :
+    func : UnchangedInferMeta
+    param: [x]
+  kernel :
+    func : celu
+  backward : celu_grad
+
 - op : cholesky
   args : (Tensor x, bool upper=false)
   output : Tensor
@@ -207,6 +217,17 @@
     data_type : x
   backward : dot_grad
 
+- op : elu
+  args : (Tensor x, float alpha = 1.0f)
+  output : Tensor(out)
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : elu
+  inplace : (x -> out)
+  backward : elu_grad
+
 - op : erf
   args : (Tensor x)
   output : Tensor
@@ -312,6 +333,16 @@
     func : hard_sigmoid
   backward : hardsigmoid_grad
 
+- op : leaky_relu
+  args : (Tensor x, float negative_slope = 0.02f)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : leaky_relu
+  backward : leaky_relu_grad
+
 - op : lgamma
   args : (Tensor x)
   output : Tensor(out)
@@ -321,6 +352,15 @@
     func : lgamma
   backward : lgamma_grad
 
+- op : log
+  args : (Tensor x)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : log
+  backward: log_grad
+
 - op : log10
   args : (Tensor x)
   output : Tensor
@@ -395,6 +435,16 @@
   inplace : (x -> out)
   backward : reciprocal_grad
 
+- op : relu
+  args : (Tensor x)
+  output : Tensor(out)
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : relu
+  inplace : (x -> out)
+  backward : relu_grad
+
 - op : round
   args : (Tensor x)
   output : Tensor(out)
@@ -405,6 +455,16 @@
   inplace : (x -> out)
   backward : round_grad
 
+- op : rsqrt
+  args : (Tensor x)
+  output : Tensor(out)
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : rsqrt
+  inplace : (x -> out)
+  backward : rsqrt_grad
+
 - op : send_uv
   args : (Tensor x, Tensor y, Tensor src_index, Tensor dst_index, str message_op = "ADD")
   output : Tensor(out)
@@ -415,6 +475,15 @@
     data_type : x
   backward : send_uv_grad
 
+- op : sigmoid
+  args : (Tensor x)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : sigmoid
+  backward : sigmoid_grad
+
 - op : silu
   args : (Tensor x)
   output : Tensor
@@ -442,6 +511,36 @@
     func : sinh
   backward : sinh_grad
 
+- op : softplus
+  args : (Tensor x, float beta = 1.0, float threshold = 20.0f)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softplus
+  backward : softplus_grad
+
+- op : softshrink
+  args : (Tensor x, float threshold = 0.5)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softshrink
+  backward : softshrink_grad
+
+- op : softsign
+  args : (Tensor x)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : softsign
+  backward : softsign_grad
+
 - op : solve
   args : (Tensor x, Tensor y)
   output : Tensor
@@ -452,6 +551,27 @@
     data_type : x
   backward : solve_grad
 
+- op : sqrt
+  args : (Tensor x)
+  output : Tensor(out)
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : sqrt {dense -> dense},
+           sqrt_sr {selected_rows -> selected_rows}
+  inplace : (x -> out)
+  backward : sqrt_grad
+
+- op : square
+  args : (Tensor x)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : square {dense -> dense},
+           square_sr {selected_rows -> selected_rows}
+  backward : square_grad
+
 - op : tan
   args : (Tensor x)
   output : Tensor
@@ -471,6 +591,25 @@
   inplace : (x -> out)
   backward : tanh_grad
 
+- op : tanh_shrink
+  args : (Tensor x)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+  kernel :
+    func : tanh_shrink
+  backward : tanh_shrink_grad
+
+- op : thresholded_relu
+  args : (Tensor x, float threshold = 1.0)
+  output : Tensor
+  infer_meta :
+    func : UnchangedInferMeta
+    param : [x]
+  kernel :
+    func : thresholded_relu
+  backward : thresholded_relu_grad
+
 - op : trace
   args : (Tensor x, int offset = 0, int axis1 = 0, int axis2 = 1)
   output : Tensor
diff --git a/paddle/phi/kernels/cpu/activation_grad_kernel.cc b/paddle/phi/kernels/cpu/activation_grad_kernel.cc
index f8602fff21f67e8b074854ef7bf38332a13ab378..ff3136e8ff097fe0924ef50742aae60464cccbab 100644
--- a/paddle/phi/kernels/cpu/activation_grad_kernel.cc
+++ b/paddle/phi/kernels/cpu/activation_grad_kernel.cc
@@ -268,7 +268,7 @@ PD_REGISTER_ACTIVATION_GRAD_KERNEL(leaky_relu_grad, LeakyReluGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(thresholded_relu_grad,
                                    ThresholdedReluGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(relu6_grad, Relu6GradKernel)
-PD_REGISTER_ACTIVATION_GRAD_KERNEL(soft_shrink_grad, SoftShrinkGradKernel)
+PD_REGISTER_ACTIVATION_GRAD_KERNEL(softshrink_grad, SoftShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(hard_shrink_grad, HardShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(tanh_shrink_grad, TanhShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(elu_grad, EluGradKernel)
diff --git a/paddle/phi/kernels/cpu/activation_kernel.cc b/paddle/phi/kernels/cpu/activation_kernel.cc
index 4cbe46bd6658f3eccb0c7b7c6b0a67fc5b8fb0db..f5ff006b3acf509149680e69429c4217852e8a42 100644
--- a/paddle/phi/kernels/cpu/activation_kernel.cc
+++ b/paddle/phi/kernels/cpu/activation_kernel.cc
@@ -151,7 +151,7 @@ PD_REGISTER_ACTIVATION_KERNEL(leaky_relu, LeakyReluKernel)
 PD_REGISTER_ACTIVATION_KERNEL(thresholded_relu, ThresholdedReluKernel)
 PD_REGISTER_ACTIVATION_KERNEL(relu6, Relu6Kernel)
 PD_REGISTER_ACTIVATION_KERNEL(hard_shrink, HardShrinkKernel)
-PD_REGISTER_ACTIVATION_KERNEL(soft_shrink, SoftShrinkKernel)
+PD_REGISTER_ACTIVATION_KERNEL(softshrink, SoftShrinkKernel)
 PD_REGISTER_ACTIVATION_KERNEL(tanh_shrink, TanhShrinkKernel)
 PD_REGISTER_ACTIVATION_KERNEL(elu, EluKernel)
 PD_REGISTER_ACTIVATION_KERNEL(silu, SiluKernel)
diff --git a/paddle/phi/kernels/gpu/activation_grad_kernel.cu b/paddle/phi/kernels/gpu/activation_grad_kernel.cu
index f6764465bfa6aa86e0f1612617c01026c7f7a29f..bfa7b28b7614f661dbe95a29d1924f3a4eccf5f7 100644
--- a/paddle/phi/kernels/gpu/activation_grad_kernel.cu
+++ b/paddle/phi/kernels/gpu/activation_grad_kernel.cu
@@ -373,7 +373,7 @@ PD_REGISTER_KERNEL(exp_grad,
                    int64_t,
                    phi::dtype::float16) {}
 
-PD_REGISTER_ACTIVATION_GRAD_KERNEL(soft_shrink_grad, SoftShrinkGradKernel)
+PD_REGISTER_ACTIVATION_GRAD_KERNEL(softshrink_grad, SoftShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(hard_shrink_grad, HardShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(tanh_shrink_grad, TanhShrinkGradKernel)
 PD_REGISTER_ACTIVATION_GRAD_KERNEL(silu_grad, SiluGradKernel)
diff --git a/paddle/phi/kernels/gpu/activation_kernel.cu b/paddle/phi/kernels/gpu/activation_kernel.cu
index e22c477d852cb247ab826810ad30feddb869608b..fd4cdf9c0df58c926f14f11478dfbfb08a40748a 100644
--- a/paddle/phi/kernels/gpu/activation_kernel.cu
+++ b/paddle/phi/kernels/gpu/activation_kernel.cu
@@ -242,7 +242,7 @@ PD_REGISTER_KERNEL(square,
                    phi::dtype::bfloat16) {}
 
 PD_REGISTER_ACTIVATION_KERNEL(hard_shrink, HardShrinkKernel)
-PD_REGISTER_ACTIVATION_KERNEL(soft_shrink, SoftShrinkKernel)
+PD_REGISTER_ACTIVATION_KERNEL(softshrink, SoftShrinkKernel)
 PD_REGISTER_ACTIVATION_KERNEL(tanh_shrink, TanhShrinkKernel)
 PD_REGISTER_ACTIVATION_KERNEL(elu, EluKernel)
 PD_REGISTER_ACTIVATION_KERNEL(silu, SiluKernel)
diff --git a/paddle/phi/ops/compat/activation_sig.cc b/paddle/phi/ops/compat/activation_sig.cc
index 4d115eed62607d696e2fd2d541506c5a64c59aa8..52351b8bc646dea0d39f987e4ed9c5b27ca0df27 100644
--- a/paddle/phi/ops/compat/activation_sig.cc
+++ b/paddle/phi/ops/compat/activation_sig.cc
@@ -39,19 +39,8 @@ namespace phi {
 
 #define comma ,
 
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Square, "square", );  // NOLINT
-
 DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(HardTanh, "hard_tanh", "t_min" comma "t_max");
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(LeakyRelu, "leaky_relu", "alpha");
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(ThresholdedRelu,
-                               "thresholded_relu",
-                               "threshold");
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(SoftShrink, "soft_shrink", "lambda");
 DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Mish, "mish", "threshold");
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(TanhShrink, "tanh_shrink", );  // NOLINT
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Softsign, "softsign", );       // NOLINT
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Log, "log", );                 // NOLINT
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Celu, "celu", "alpha");        // NOLINT
 DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(HardSwish,
                                "hard_swish",
                                "threshold" comma "scale" comma
@@ -62,106 +51,8 @@ DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(STanh,
                                "stanh",
                                "scale_a" comma "scale_b");  // NOLINT
 
-DEFINE_ACT_GRAD_DEPX_OP_ARGMAP(Softplus,
-                               "softplus",
-                               "beta" comma "threshold");  // NOLINT
-
-DEFINE_ACT_GRAD_DEPOUT_OP_ARGMAP(Relu, "relu", );               // NOLINT
-DEFINE_ACT_GRAD_DEPOUT_OP_ARGMAP(Sigmoid, "sigmoid", );         // NOLINT
-DEFINE_ACT_GRAD_DEPOUT_OP_ARGMAP(Sqrt, "sqrt", );               // NOLINT
-DEFINE_ACT_GRAD_DEPOUT_OP_ARGMAP(Rsqrt, "rsqrt", );             // NOLINT
 DEFINE_ACT_GRAD_DEPOUT_OP_ARGMAP(Relu6, "relu6", "threshold");  // NOLINT
 
-KernelSignature SqrtActiOpArgumentMapping(const ArgumentMappingContext& ctx) {
-  if (ctx.IsDenseTensorInput("X")) {
-    return KernelSignature("sqrt", {"X"}, {}, {"Out"});
-  } else {
-    return KernelSignature("sqrt_sr", {"X"}, {}, {"Out"});
-  }
-}
-
-KernelSignature SquareActiOpArgumentMapping(const ArgumentMappingContext& ctx) {
-  if (ctx.IsDenseTensorInput("X")) {
-    return KernelSignature("square", {"X"}, {}, {"Out"});
-  } else {
-    return KernelSignature("square_sr", {"X"}, {}, {"Out"});
-  }
-}
-
-KernelSignature ReluDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature("relu_double_grad", {"Out", "DDX"}, {}, {"DDOut"});
-}
-
-KernelSignature SigmoidDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "sigmoid_double_grad", {"Out", "DOut", "DDX"}, {}, {"DOutNew", "DDOut"});
-}
-
-KernelSignature SigmoidTripleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature("sigmoid_triple_grad",
-                         {"Out", "DOut", "DDX", "D_DOut_New", "D_DDOut"},
-                         {},
-                         {"D_OutNew", "D_DOut", "D_DDx"});
-}
-
-KernelSignature LeakyReluDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "leaky_relu_double_grad", {"X", "DDX"}, {"alpha"}, {"DDOut"});
-}
-
-KernelSignature LeakyReluOpArgumentMapping(const ArgumentMappingContext& ctx) {
-  return KernelSignature("leaky_relu", {"X"}, {"alpha"}, {"Out"});
-}
-
-KernelSignature EluOpArgumentMapping(const ArgumentMappingContext& ctx) {
-  return KernelSignature("elu", {"X"}, {"alpha"}, {"Out"});
-}
-
-KernelSignature EluGradOpArgumentMapping(const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "elu_grad", {"X", "Out", "Out@GRAD"}, {"alpha"}, {"X@GRAD"});
-}
-
-KernelSignature EluDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "elu_double_grad", {"X", "DOut", "DDX"}, {"alpha"}, {"DX", "DDOut"});
-}
-
-KernelSignature LogDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "log_double_grad", {"X", "DOut", "DDX"}, {}, {"DX", "DDOut"});
-}
-
-KernelSignature SqrtDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "sqrt_double_grad", {"Out", "DX", "DDX"}, {}, {"DOut", "DDOut"});
-}
-
-KernelSignature RsqrtDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "rsqrt_double_grad", {"Out", "DX", "DDX"}, {}, {"DOut", "DDOut"});
-}
-
-KernelSignature CeluDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "celu_double_grad", {"X", "DOut", "DDX"}, {"alpha"}, {"DX", "DDOut"});
-}
-
-KernelSignature SquareDoubleGradOpArgumentMapping(
-    const ArgumentMappingContext& ctx) {
-  return KernelSignature(
-      "square_double_grad", {"X", "DOut", "DDX"}, {}, {"DX", "DDOut"});
-}
-
 KernelSignature PowOpArgumentMapping(const ArgumentMappingContext& ctx) {
   if (ctx.HasInput("FactorTensor")) {
     return KernelSignature("pow", {"X"}, {"FactorTensor"}, {"Out"});
@@ -182,70 +73,17 @@ KernelSignature PowGradOpArgumentMapping(const ArgumentMappingContext& ctx) {
 
 }  // namespace phi
 
-PD_REGISTER_BASE_KERNEL_NAME(relu_grad_grad, relu_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(leaky_relu_grad_grad, leaky_relu_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(softshrink, soft_shrink);
-PD_REGISTER_BASE_KERNEL_NAME(softshrink_grad, soft_shrink_grad);
-PD_REGISTER_BASE_KERNEL_NAME(elu_grad_grad, elu_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(sigmoid_grad_grad, sigmoid_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(log_grad_grad, log_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(sqrt_grad_grad, sqrt_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(rsqrt_grad_grad, rsqrt_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(celu_grad_grad, celu_double_grad);
-PD_REGISTER_BASE_KERNEL_NAME(square_grad_grad, square_double_grad);
 PD_REGISTER_BASE_KERNEL_NAME(brelu, hard_tanh);
 PD_REGISTER_BASE_KERNEL_NAME(brelu_grad, hard_tanh_grad);
 
-PD_REGISTER_ARG_MAPPING_FN(relu_grad, phi::ReluGradOpArgumentMapping);
-
-PD_REGISTER_ARG_MAPPING_FN(square_grad, phi::SquareGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(sqrt_grad, phi::SqrtGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(sqrt_grad_grad,
-                           phi::SqrtDoubleGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(rsqrt_grad, phi::RsqrtGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(rsqrt_grad_grad,
-                           phi::RsqrtDoubleGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(mish_grad, phi::MishGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(stanh_grad, phi::STanhGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(softplus_grad, phi::SoftplusGradOpArgumentMapping);
 
-PD_REGISTER_ARG_MAPPING_FN(relu_grad_grad,
-                           phi::ReluDoubleGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(brelu_grad, phi::HardTanhGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(leaky_relu, phi::LeakyReluOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(leaky_relu_grad,
-                           phi::LeakyReluGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(leaky_relu_grad_grad,
-                           phi::LeakyReluDoubleGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(thresholded_relu_grad,
-                           phi::ThresholdedReluGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(relu6_grad, phi::Relu6GradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(softshrink_grad,
-                           phi::SoftShrinkGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(tanh_shrink_grad,
-                           phi::TanhShrinkGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(elu, phi::EluOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(elu_grad, phi::EluGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(elu_grad_grad, phi::EluDoubleGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(softsign_grad, phi::SoftsignGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(sigmoid_grad, phi::SigmoidGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(sigmoid_grad_grad,
-                           phi::SigmoidDoubleGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(sigmoid_triple_grad,
-                           phi::SigmoidTripleGradOpArgumentMapping);
-
-PD_REGISTER_ARG_MAPPING_FN(log_grad, phi::LogGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(log_grad_grad, phi::LogDoubleGradOpArgumentMapping);
-
-PD_REGISTER_ARG_MAPPING_FN(sqrt, phi::SqrtActiOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(square, phi::SquareActiOpArgumentMapping);
+
 PD_REGISTER_ARG_MAPPING_FN(hard_swish_grad,
                            phi::HardSwishGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(swish_grad, phi::SwishGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(pow_grad, phi::PowGradOpArgumentMapping);
 PD_REGISTER_ARG_MAPPING_FN(pow, phi::PowOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(celu_grad, phi::CeluGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(celu_grad_grad,
-                           phi::CeluDoubleGradOpArgumentMapping);
-PD_REGISTER_ARG_MAPPING_FN(square_grad_grad,
-                           phi::SquareDoubleGradOpArgumentMapping);
diff --git a/python/paddle/tensor/ops.py b/python/paddle/tensor/ops.py
index 0f5bac3c6e58356c2416e3eed00a5b01356a31bb..c4d8b01762a2af9e854874945b330ee0519f91e4 100644
--- a/python/paddle/tensor/ops.py
+++ b/python/paddle/tensor/ops.py
@@ -29,7 +29,6 @@ __deprecated_func_name__ = {
 }
 
 __activations_noattr__ = [
-    'sigmoid',
     'silu',
     'logsigmoid',
     'tanh_shrink',
@@ -38,12 +37,7 @@ __activations_noattr__ = [
     'tanh',
 ]
 
-__unary_func__ = [
-    'sqrt',
-    'rsqrt',
-    'abs',
-    'square',
-]
+__unary_func__ = ['abs']
 
 __inplace_unary_func__ = [
     'exp_',
@@ -85,23 +79,6 @@ for _OP in set(__inplace_unary_func__):
     _func = generate_inplace_fn(_OP)
     globals()[_OP] = _func
 
-add_sample_code(
-    globals()["sigmoid"],
-    r"""
-Examples:
-    .. code-block:: python
-
-        import paddle
-        import paddle.nn.functional as F
-
-        x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
-        out = F.sigmoid(x)
-        print(out)
-        # [0.40131234 0.450166   0.52497919 0.57444252]
-
-""",
-)
-
 add_sample_code(
     globals()["silu"],
     r"""
@@ -163,38 +140,6 @@ Examples:
 """,
 )
 
-add_sample_code(
-    globals()["sqrt"],
-    r"""
-Examples:
-    .. code-block:: python
-
-        import paddle
-
-        x = paddle.to_tensor([0.1, 0.2, 0.3, 0.4])
-        out = paddle.sqrt(x)
-        print(out)
-        # [0.31622777 0.4472136  0.54772256 0.63245553]
-
-""",
-)
-
-add_sample_code(
-    globals()["rsqrt"],
-    r"""
-Examples:
-    .. code-block:: python
-
-        import paddle
-
-        x = paddle.to_tensor([0.1, 0.2, 0.3, 0.4])
-        out = paddle.rsqrt(x)
-        print(out)
-        # [3.16227766 2.23606798 1.82574186 1.58113883]
-
-""",
-)
-
 add_sample_code(
     globals()["abs"],
     r"""
@@ -211,22 +156,6 @@ Examples:
 """,
 )
 
-add_sample_code(
-    globals()["square"],
-    r"""
-Examples:
-    .. code-block:: python
-
-        import paddle
-
-        x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
-        out = paddle.square(x)
-        print(out)
-        # [0.16 0.04 0.01 0.09]
-
-""",
-)
-
 add_sample_code(
     globals()["softplus"],
     r"""
@@ -812,6 +741,85 @@ def round(x, name=None):
     return out
 
 
+def rsqrt(x, name=None):
+    """
+    Rsqrt Activation Operator.
+
+    Please make sure input is legal in case of numeric errors.
+
+    .. math::
+       out = \\frac{1}{\\sqrt{x}}
+
+    Args:
+        x (Tensor): Input of Rsqrt operator, an N-D Tensor, with data type float32, float64 or float16.
+        name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
+
+    Returns:
+        Tensor. Output of Rsqrt operator, a Tensor with shape same as input.
+
+    Examples:
+        .. code-block:: python
+
+            import paddle
+
+            x = paddle.to_tensor([0.1, 0.2, 0.3, 0.4])
+            out = paddle.rsqrt(x)
+            print(out)
+            # [3.16227766 2.23606798 1.82574186 1.58113883]
+
+    """
+    if in_dygraph_mode():
+        return _C_ops.rsqrt(x)
+    if _in_legacy_dygraph():
+        return _legacy_C_ops.rsqrt(x)
+
+    check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'], 'rsqrt')
+    helper = LayerHelper('rsqrt', **locals())
+    out = helper.create_variable_for_type_inference(dtype=x.dtype)
+    helper.append_op(type='rsqrt', inputs={"X": x}, outputs={"Out": out})
+    return out
+
+
+def sigmoid(x, name=None):
+    """
+    Sigmoid Activation.
+
+    .. math::
+       out = \\frac{1}{1 + e^{-x}}
+
+    Args:
+        x (Tensor): Input of Sigmoid operator, an N-D Tensor, with data type float32, float64 or float16.
+        name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
+
+    Returns:
+        Tensor. Output of Sigmoid operator, a Tensor with shape same as input.
+
+    Examples:
+        .. code-block:: python
+
+            import paddle
+            import paddle.nn.functional as F
+
+            x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
+            out = F.sigmoid(x)
+            print(out)
+            # [0.40131234 0.450166   0.52497919 0.57444252]
+
+    """
+    if in_dygraph_mode():
+        return _C_ops.sigmoid(x)
+    if _in_legacy_dygraph():
+        return _legacy_C_ops.sigmoid(x)
+
+    check_variable_and_dtype(
+        x, 'x', ['float16', 'float32', 'float64'], 'sigmoid'
+    )
+    helper = LayerHelper('sigmoid', **locals())
+    out = helper.create_variable_for_type_inference(dtype=x.dtype)
+    helper.append_op(type='sigmoid', inputs={"X": x}, outputs={"Out": out})
+    return out
+
+
 def sin(x, name=None):
     """
     Sine Activation Operator.
@@ -886,6 +894,91 @@ def sinh(x, name=None):
     return out
 
 
+def sqrt(x, name=None):
+    """
+    Sqrt Activation Operator.
+
+    .. math::
+       out=\\sqrt{x}=x^{1/2}
+
+    Args:
+        x (Tensor): Input of Sqrt operator, an N-D Tensor, with data type float32, float64 or float16.
+        name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
+
+    Returns:
+        Tensor. Output of Sqrt operator, a Tensor with shape same as input.
+
+    Examples:
+        .. code-block:: python
+
+            import paddle
+
+            x = paddle.to_tensor([0.1, 0.2, 0.3, 0.4])
+            out = paddle.sqrt(x)
+            print(out)
+            # [0.31622777 0.4472136  0.54772256 0.63245553]
+    """
+    if in_dygraph_mode():
+        return _C_ops.sqrt(x)
+    if _in_legacy_dygraph():
+        return _legacy_C_ops.sqrt(x)
+
+    check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'], 'sqrt')
+    helper = LayerHelper('sqrt', **locals())
+    out = helper.create_variable_for_type_inference(dtype=x.dtype)
+    helper.append_op(type='sqrt', inputs={"X": x}, outputs={"Out": out})
+    return out
+
+
+def square(x, name=None):
+    """
+    Square each elements of the inputs.
+
+    .. math::
+       out = x^2
+
+    Args:
+        x (Tensor): Input of Square operator, an N-D Tensor, with data type float32, float64 or float16.
+        name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
+
+    Returns:
+        Tensor. Output of Square operator, a Tensor with shape same as input.
+
+    Examples:
+        .. code-block:: python
+
+            import paddle
+
+            x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
+            out = paddle.square(x)
+            print(out)
+            # [0.16 0.04 0.01 0.09]
+    """
+    if in_dygraph_mode():
+        return _C_ops.square(x)
+    if _in_legacy_dygraph():
+        return _legacy_C_ops.square(x)
+
+    check_variable_and_dtype(
+        x,
+        'x',
+        [
+            'int32',
+            'int64',
+            'float16',
+            'float32',
+            'float64',
+            'complex64',
+            'complex128',
+        ],
+        'square',
+    )
+    helper = LayerHelper('square', **locals())
+    out = helper.create_variable_for_type_inference(dtype=x.dtype)
+    helper.append_op(type='square', inputs={"X": x}, outputs={"Out": out})
+    return out
+
+
 def tan(x, name=None):
     """
     Tangent Operator. Computes tangent of x element-wise.