diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index 8849e3102591f72888a435edccfa4b5a7896183d..51c3c7bbf97660fa3548ae41af2218b5ba0efce2 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -86,7 +86,7 @@ paddle.fluid.layers.conv2d (ArgSpec(args=['input', 'num_filters', 'filter_size',
 paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None)), ('document', '37042620f9bd3a2da6e5d3138b2f724b'))
 paddle.fluid.layers.sequence_pool (ArgSpec(args=['input', 'pool_type', 'is_test'], varargs=None, keywords=None, defaults=(False,)), ('document', 'a194fb80614023f543df3949fbd0d0b8'))
 paddle.fluid.layers.sequence_softmax (ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None)), ('document', '19ef6f9cdd27feac8a1ae060f19c10b4'))
-paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', '85f9690b1b285def19077a41d9dba36c'))
+paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', '502bad9e8bc7ef24817d0d4b20f61df3'))
 paddle.fluid.layers.pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True)), ('document', 'bbd84e855e660cd1084bb71a2fd0cdaa'))
 paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True)), ('document', '043de7333b79ee0ac55053c14ed81625'))
 paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '859b887174d06f361658f69cb7c06d95'))
diff --git a/paddle/fluid/operators/jit/more/mix/mix.cc b/paddle/fluid/operators/jit/more/mix/mix.cc
index 4f309501b6ddd6d9ac5e2a25e223241e318d41ca..1a9fc9ed7bfa1ea42873683b6b432b9087ea3dea 100644
--- a/paddle/fluid/operators/jit/more/mix/mix.cc
+++ b/paddle/fluid/operators/jit/more/mix/mix.cc
@@ -54,8 +54,10 @@ void Softmax(const T* x, T* y, int n, int bs, int remain) {
   auto compute_hmax = KernelFuncs<HMaxTuple<T>, CPUPlace>::Cache().At(n);
   auto compute_hsum = KernelFuncs<HSumTuple<T>, CPUPlace>::Cache().At(n);
   auto compute_vscal = KernelFuncs<VScalTuple<T>, CPUPlace>::Cache().At(n);
-  auto compute_stridesum = KernelFuncs<StrideASumTuple<T>, CPUPlace>::Cache().At(n);
-  auto compute_stridescal = KernelFuncs<StrideScalTuple<T>, CPUPlace>::Cache().At(n);
+  auto compute_stridesum =
+      KernelFuncs<StrideASumTuple<T>, CPUPlace>::Cache().At(n);
+  auto compute_stridescal =
+      KernelFuncs<StrideScalTuple<T>, CPUPlace>::Cache().At(n);
   auto compute_vaddbias =
       KernelFuncs<VAddBiasTuple<T>, CPUPlace>::Cache().At(n);
   auto compute_vexp = KernelFuncs<VExpTuple<T>, CPUPlace>::Cache().At(n);
diff --git a/paddle/fluid/operators/jit/more/mkl/mkl.cc b/paddle/fluid/operators/jit/more/mkl/mkl.cc
index fc8800ec7241167d32aff51d94d61cdd888944f6..75ebddb125989b121b62d42b50e896eccd392a71 100644
--- a/paddle/fluid/operators/jit/more/mkl/mkl.cc
+++ b/paddle/fluid/operators/jit/more/mkl/mkl.cc
@@ -79,18 +79,20 @@ void VScal<double>(const double* a, const double* x, double* y, int n) {
 }
 
 template <>
-void StrideScal<float>(const float* a, const float* x, float* y, int n, int stride) {
+void StrideScal<float>(const float* a, const float* x, float* y, int n,
+                       int stride) {
   if (x == y) {
-    platform::dynload::cblas_sscal(n/stride, *a, y, stride);
+    platform::dynload::cblas_sscal(n / stride, *a, y, stride);
   } else {
     refer::StrideScal<float>(a, x, y, n, stride);
   }
 }
 
 template <>
-void StrideScal<double>(const double* a, const double* x, double* y, int n, int stride) {
+void StrideScal<double>(const double* a, const double* x, double* y, int n,
+                        int stride) {
   if (x == y) {
-    platform::dynload::cblas_dscal(n/stride, *a, y, stride);
+    platform::dynload::cblas_dscal(n / stride, *a, y, stride);
   } else {
     refer::StrideScal<double>(a, x, y, n, stride);
   }
@@ -148,12 +150,12 @@ void ASum<double>(const double* x, double* res, int n) {
 
 template <>
 void StrideASum<float>(const float* x, float* res, int n, int stride) {
-  res[0] = platform::dynload::cblas_sasum(n/stride, x, stride);
+  res[0] = platform::dynload::cblas_sasum(n / stride, x, stride);
 }
 
 template <>
 void StrideASum<double>(const double* x, double* res, int n, int stride) {
-  res[0] = platform::dynload::cblas_dasum(n/stride, x, stride);
+  res[0] = platform::dynload::cblas_dasum(n / stride, x, stride);
 }
 
 // TODO(TJ): tuning me carefully on AVX, AVX2 and AVX512
diff --git a/paddle/fluid/operators/jit/more/mkl/mkl.h b/paddle/fluid/operators/jit/more/mkl/mkl.h
index 1fbb87b0cf9ef1030d21a4c98da1e45503a397ec..968895bb6f8034db30fcdb36bdbf05804aba55f4 100644
--- a/paddle/fluid/operators/jit/more/mkl/mkl.h
+++ b/paddle/fluid/operators/jit/more/mkl/mkl.h
@@ -135,7 +135,7 @@ template <typename T>
 void StrideScal(const T* a, const T* x, T* y, int n, int stride);
 
 template <typename T>
-void Softmax(const T* x, T* y, int n, int bs, int remain=1) {
+void Softmax(const T* x, T* y, int n, int bs, int remain = 1) {
   std::vector<T> entities(bs);
   for (int i = 0; i < bs; ++i) {
     entities[i] = x[i * n];
diff --git a/paddle/fluid/operators/jit/refer/refer.h b/paddle/fluid/operators/jit/refer/refer.h
index c62925232ba0b42aa02f37e0f6d6dbac2bebd13c..4aeb2fd6282a87f44dfefa4e0d5dd87d0d8c8804 100644
--- a/paddle/fluid/operators/jit/refer/refer.h
+++ b/paddle/fluid/operators/jit/refer/refer.h
@@ -414,13 +414,13 @@ void HSum(const T* x, T* res, int n) {
 template <typename T>
 void StrideASum(const T* x, T* res, int n, int stride) {
   res[0] = x[0];
-  for (int i = stride; i < n; i+=stride) {
+  for (int i = stride; i < n; i += stride) {
     res[0] += std::abs(x[i]);
   }
 }
 
 template <typename T>
-void StrideScal(const T* a, const T* x, T* y, int n , int stride) {
+void StrideScal(const T* a, const T* x, T* y, int n, int stride) {
   for (int i = 0; i < n; ++i) {
     if (i % stride == 0) {
       y[i] = x[i] * a[0];
diff --git a/paddle/fluid/operators/jit/test.cc b/paddle/fluid/operators/jit/test.cc
index 1397e5be181e3dfa7ea72b361f1b28fc6f5f83e6..d8a0b2cbf53f7a02288f45f184daa9f69cc49657 100644
--- a/paddle/fluid/operators/jit/test.cc
+++ b/paddle/fluid/operators/jit/test.cc
@@ -723,7 +723,7 @@ void TestKernelSoftmax() {
   VLOG(10) << "Test JITKernel: " << jit::to_string(KernelTuple::kernel_type);
   for (int bs : {1, 2, 10}) {
     for (int n : TestSizes()) {
-      for (int m : {1, 2, 3}) { // remain
+      for (int m : {1, 2, 3}) {  // remain
         if (m > n || n % m != 0) {
           continue;
         }
@@ -770,7 +770,7 @@ void TestKernelStrideASum() {
   using T = typename KernelTuple::data_type;
   VLOG(10) << "Test JITKernel: " << jit::to_string(KernelTuple::kernel_type);
   for (int d : TestSizes()) {
-    for (int m : {1, 2, 3}) { // stride
+    for (int m : {1, 2, 3}) {  // stride
       if (m > d || d % m != 0) {
         continue;
       }
@@ -782,7 +782,7 @@ void TestKernelStrideASum() {
       ref(x.data(), &ref_res, d, m);
 
       auto verifier = [](const typename KernelTuple::func_type tgt,
-                         const std::vector<T>& x, const T ref_res, 
+                         const std::vector<T>& x, const T ref_res,
                          const int m) {
         EXPECT_TRUE(tgt != nullptr);
         T tgt_res;
@@ -801,7 +801,7 @@ void TestKernelStrideScal() {
   // for (int d : TestSizes()) {
   //   for (int m : {1, 2, 3}) { // stride
   for (int d : {4}) {
-    for (int m : {2}) { // stride
+    for (int m : {2}) {  // stride
       if (m > d || d % m != 0) {
         continue;
       }
diff --git a/paddle/fluid/operators/math/softmax.h b/paddle/fluid/operators/math/softmax.h
index f8e250fa2e70b3592dd172566f3e8af61df11df2..a7a30a71e4cf176987cc75be1958a762a08b09ae 100644
--- a/paddle/fluid/operators/math/softmax.h
+++ b/paddle/fluid/operators/math/softmax.h
@@ -31,7 +31,7 @@ template <typename DeviceContext, typename T>
 class SoftmaxGradFunctor {
  public:
   void operator()(const DeviceContext& context, const int axis_dim,
-                  const framework::Tensor* y, const framework::Tensor* y_grad, 
+                  const framework::Tensor* y, const framework::Tensor* y_grad,
                   framework::Tensor* x_grad);
 };
 
diff --git a/paddle/fluid/operators/math/softmax_impl.h b/paddle/fluid/operators/math/softmax_impl.h
index dea8142cc83074182ec15496850e6fa8ef351cc4..6f6f33345f5336a8b8ff100c0286914ef629283f 100644
--- a/paddle/fluid/operators/math/softmax_impl.h
+++ b/paddle/fluid/operators/math/softmax_impl.h
@@ -94,8 +94,9 @@ class SoftmaxFunctor<DeviceContext, float, true, enable_if_CPU<DeviceContext>> {
 
 template <typename DeviceContext, typename T>
 void SoftmaxGradFunctor<DeviceContext, T>::operator()(
-    const DeviceContext& context, const int axis_dim, const framework::Tensor* y,
-    const framework::Tensor* y_grad, framework::Tensor* x_grad) {
+    const DeviceContext& context, const int axis_dim,
+    const framework::Tensor* y, const framework::Tensor* y_grad,
+    framework::Tensor* x_grad) {
   auto softmax = EigenMatrix<T>::From(*y);
   auto softmax_grad = EigenMatrix<T>::From(*y_grad);
   auto logits_grad = EigenMatrix<T>::From(*x_grad);
diff --git a/paddle/fluid/operators/softmax_op.cc b/paddle/fluid/operators/softmax_op.cc
index 9cbb6691f404975fe4e7ca3e8b5c9462c7630c03..b812d2cdebc82f5248c8032e941feaa2bf40ac76 100644
--- a/paddle/fluid/operators/softmax_op.cc
+++ b/paddle/fluid/operators/softmax_op.cc
@@ -49,10 +49,8 @@ class SoftmaxOp : public framework::OperatorWithKernel {
     auto use_cudnn = ctx->Attrs().Get<bool>("use_cudnn");
     auto use_mkldnn = ctx->Attrs().Get<bool>("use_mkldnn");
     if (axis != rank_x - 1 && axis != -1) {
-      PADDLE_ENFORCE(!use_cudnn, 
-          "CUDNN kernel only support axis as -1.");
-      PADDLE_ENFORCE(!use_mkldnn, 
-          "MKLDNN kernel only support axis as -1.");
+      PADDLE_ENFORCE(!use_cudnn, "CUDNN kernel only support axis as -1.");
+      PADDLE_ENFORCE(!use_mkldnn, "MKLDNN kernel only support axis as -1.");
     }
 
     ctx->SetOutputDim("Out", ctx->GetInputDim("X"));
diff --git a/paddle/fluid/operators/softmax_op.h b/paddle/fluid/operators/softmax_op.h
index bbea935101f689a2ce3eb17432c7a89ecc5c1ed4..a964c3b57a635b3e5f0a4c163e3b3c13d465102b 100644
--- a/paddle/fluid/operators/softmax_op.h
+++ b/paddle/fluid/operators/softmax_op.h
@@ -66,10 +66,12 @@ class SoftmaxKernel : public framework::OpKernel<T> {
 
 #ifdef PADDLE_ON_INFERENCE
     math::SoftmaxFunctor<DeviceContext, T, true>()(
-        context.template device_context<DeviceContext>(), axis_dim, &X_2d, &Out_2d);
+        context.template device_context<DeviceContext>(), axis_dim, &X_2d,
+        &Out_2d);
 #else
     math::SoftmaxFunctor<DeviceContext, T, false>()(
-        context.template device_context<DeviceContext>(), axis_dim, &X_2d, &Out_2d);
+        context.template device_context<DeviceContext>(), axis_dim, &X_2d,
+        &Out_2d);
 #endif
   }
 };
@@ -96,8 +98,8 @@ class SoftmaxGradKernel : public framework::OpKernel<T> {
     dOut_2d.ShareDataWith(*dOut).Resize({n, d});
 
     math::SoftmaxGradFunctor<DeviceContext, T>()(
-        context.template device_context<DeviceContext>(), axis_dim, &Out_2d, &dOut_2d,
-        &dX_2d);
+        context.template device_context<DeviceContext>(), axis_dim, &Out_2d,
+        &dOut_2d, &dX_2d);
   }
 };
 
diff --git a/paddle/fluid/operators/warpctc_cudnn_op.cu.cc b/paddle/fluid/operators/warpctc_cudnn_op.cu.cc
index 716faf2995e6b8af6f5168cff4e3f33660f16120..8d97396fdae56748054036bfaf3882e7e402ab47 100644
--- a/paddle/fluid/operators/warpctc_cudnn_op.cu.cc
+++ b/paddle/fluid/operators/warpctc_cudnn_op.cu.cc
@@ -69,7 +69,8 @@ class CudnnCTCKernel : public framework::OpKernel<T> {
     int rank = logits->dims().size();
     Tensor in_2d = framework::ReshapeToMatrix(*logits, rank - 1);
     Tensor out_2d = framework::ReshapeToMatrix(softmax_logits, rank - 1);
-    math::SoftmaxFunctor<DeviceContext, T, false>()(dev_ctx, -1, &in_2d, &out_2d);
+    math::SoftmaxFunctor<DeviceContext, T, false>()(dev_ctx, -1, &in_2d,
+                                                    &out_2d);
 
     // ctc needs sequences data stored in transposed padding format
     // logits and grad using padding data of layout 'TNC'