diff --git a/paddle/fluid/operators/elementwise_mul_op.h b/paddle/fluid/operators/elementwise_mul_op.h
index 46d69ed87d4c2eeae674730b00858b6358b97773..e2b59b31120964d49d2de29ed327ffe0e6d44ddc 100644
--- a/paddle/fluid/operators/elementwise_mul_op.h
+++ b/paddle/fluid/operators/elementwise_mul_op.h
@@ -40,80 +40,14 @@ class ElementwiseMulKernel : public framework::OpKernel<T> {
 };
 
 template <typename T>
-struct ElementwiseMulGradFunctor {
-  template <typename Device, typename X, typename Y, typename Z, typename dX,
-            typename dY, typename dZ>
-  void operator()(Device d, X x, Y y, Z z, dX dx, dY dy, dZ dz) {
-    auto x_e = framework::EigenVector<T>::Flatten(*x);
-    auto y_e = framework::EigenVector<T>::Flatten(*y);
-    auto dz_e = framework::EigenVector<T>::Flatten(*dz);
-
-    if (dx) {
-      auto dx_e = framework::EigenVector<T>::Flatten(*dx);
-      dx_e.device(d) = dz_e * y_e;
-    }
-
-    if (dy) {
-      auto dy_e = framework::EigenVector<T>::Flatten(*dy);
-      dy_e.device(d) = x_e * dz_e;
-    }
-  }
+struct IdentityGrad_DX {
+  HOSTDEVICE T operator()(T x, T y, T out, T dout) const { return dout * y; }
 };
 
 template <typename T>
-struct ElementwiseMulBroadCastGradFunctor {
-  template <typename Device, typename X, typename Y, typename Z, typename dX,
-            typename dY, typename dZ, typename Pre, typename N>
-  void operator()(Device d, X x, Y y, Z z, dX dx, dY dy, dZ dz, Pre pre, N n) {
-    auto x_e = framework::EigenVector<T>::Flatten(*x);
-    auto y_e = framework::EigenVector<T>::Flatten(*y);
-    auto dz_e = framework::EigenVector<T>::Flatten(*dz);
-
-    auto y_e_bcast = y_e.reshape(Eigen::DSizes<int, 2>(1, n))
-                         .broadcast(Eigen::DSizes<int, 2>(pre, 1))
-                         .reshape(Eigen::DSizes<int, 1>(x_e.size()));
-
-    if (dx) {
-      auto dx_e = framework::EigenVector<T>::Flatten(*dx);
-      dx_e.device(d) = dz_e * y_e_bcast;
-    }
-
-    if (dy) {
-      auto dy_e = framework::EigenVector<T>::Flatten(*dy);
-      dy_e.device(d) = (x_e * dz_e)
-                           .reshape(Eigen::DSizes<int, 2>(pre, n))
-                           .sum(Eigen::array<int, 1>{{0}});
-    }
-  }
+struct IdentityGrad_DY {
+  HOSTDEVICE T operator()(T x, T y, T out, T dout) const { return dout * x; }
 };
-
-template <typename T>
-struct ElementwiseMulBroadCast2GradFunctor {
-  template <typename Device, typename X, typename Y, typename Z, typename dX,
-            typename dY, typename dZ, typename Pre, typename N, typename Post>
-  void operator()(Device d, X x, Y y, Z z, dX dx, dY dy, dZ dz, Pre pre, N n,
-                  Post post) {
-    auto x_e = framework::EigenVector<T>::Flatten(*x);
-    auto y_e = framework::EigenVector<T>::Flatten(*y);
-    auto dz_e = framework::EigenVector<T>::Flatten(*dz);
-
-    auto y_e_bcast = y_e.reshape(Eigen::DSizes<int, 3>(1, n, 1))
-                         .broadcast(Eigen::DSizes<int, 3>(pre, 1, post))
-                         .reshape(Eigen::DSizes<int, 1>(x_e.size()));
-    if (dx) {
-      auto dx_e = framework::EigenVector<T>::Flatten(*dx);
-      dx_e.device(d) = dz_e * y_e_bcast;
-    }
-
-    if (dy) {
-      auto dy_e = framework::EigenVector<T>::Flatten(*dy);
-      dy_e.device(d) = (x_e * dz_e)
-                           .reshape(Eigen::DSizes<int, 3>(pre, n, post))
-                           .sum(Eigen::array<int, 2>{{0, 2}});
-    }
-  }
-};
-
 template <typename DeviceContext, typename T>
 class ElementwiseMulGradKernel : public framework::OpKernel<T> {
  public:
@@ -127,12 +61,11 @@ class ElementwiseMulGradKernel : public framework::OpKernel<T> {
     auto* dx = ctx.Output<Tensor>(framework::GradVarName("X"));
     auto* dy = ctx.Output<Tensor>(framework::GradVarName("Y"));
     int axis = ctx.Attr<int>("axis");
-    ElementwiseGradCompute<DeviceContext, T, ElementwiseMulGradFunctor<T>,
-                           ElementwiseMulBroadCastGradFunctor<T>,
-                           ElementwiseMulBroadCast2GradFunctor<T>>(
-        ctx, x, y, out, dout, axis, dx, dy);
+    ElemwiseGradCompute<DeviceContext, T, IdentityGrad_DX<T>,
+                        IdentityGrad_DY<T>>(ctx, *x, *y, *out, *dout, axis, dx,
+                                            dy, IdentityGrad_DX<T>(),
+                                            IdentityGrad_DY<T>());
   }
 };
-
 }  // namespace operators
 }  // namespace paddle
diff --git a/paddle/fluid/operators/elementwise_op_function.h b/paddle/fluid/operators/elementwise_op_function.h
index ffda53a383ced411415e528886a23f28f6a62648..0b4238436ffcc586fe8bc7abbe4cfbc1654dcb88 100644
--- a/paddle/fluid/operators/elementwise_op_function.h
+++ b/paddle/fluid/operators/elementwise_op_function.h
@@ -301,7 +301,7 @@ struct ElemwiseGradNoBroadcast {
       dx_[i] = dx_op_(x_[i], y_[i], out_[i], dout_[i]);
     }
     if (dy_ != nullptr) {
-      dy_[i] = dx_op_(x_[i], y_[i], out_[i], dout_[i]);
+      dy_[i] = dy_op_(x_[i], y_[i], out_[i], dout_[i]);
     }
   }