Align kernel/operator header layout

- Redirect validate documentation to configure
- Align header names
- Align class layout

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ia40f67383826a66e9f9a33745d66805551e31a3a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5897
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
diff --git a/src/core/cpu/kernels/CpuAddKernel.h b/src/core/cpu/kernels/CpuAddKernel.h
index 3ebaa46..717d013 100644
--- a/src/core/cpu/kernels/CpuAddKernel.h
+++ b/src/core/cpu/kernels/CpuAddKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPUADDKERNEL_H
-#define ARM_COMPUTE_CPUADDKERNEL_H
+#ifndef ARM_COMPUTE_CPU_ADD_KERNEL_H
+#define ARM_COMPUTE_CPU_ADD_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -84,4 +84,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPUADDKERNEL_H */
+#endif /* ARM_COMPUTE_CPU_ADD_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuConcatenateBatchKernel.cpp b/src/core/cpu/kernels/CpuConcatenateBatchKernel.cpp
index 5df5ac3..16c0efc 100644
--- a/src/core/cpu/kernels/CpuConcatenateBatchKernel.cpp
+++ b/src/core/cpu/kernels/CpuConcatenateBatchKernel.cpp
@@ -146,11 +146,6 @@
 }
 } // namespace
 
-CpuConcatenateBatchKernel::CpuConcatenateBatchKernel()
-    : _func(nullptr), _batch_offset(0)
-{
-}
-
 void CpuConcatenateBatchKernel::configure(const ITensorInfo *src, unsigned int batch_offset, ITensorInfo *dst)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
diff --git a/src/core/cpu/kernels/CpuConcatenateBatchKernel.h b/src/core/cpu/kernels/CpuConcatenateBatchKernel.h
index 99e8d84..1706926 100644
--- a/src/core/cpu/kernels/CpuConcatenateBatchKernel.h
+++ b/src/core/cpu/kernels/CpuConcatenateBatchKernel.h
@@ -21,17 +21,14 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_CONCATENATEBATCH_KERNEL_H
-#define ARM_COMPUTE_CPU_CONCATENATEBATCH_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_CONCATENATE_BATCH_KERNEL_H
+#define ARM_COMPUTE_CPU_CONCATENATE_BATCH_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
 
 namespace arm_compute
 {
-// Forward declarations
-class ITensor;
-
 namespace cpu
 {
 namespace kernels
@@ -42,7 +39,7 @@
 class CpuConcatenateBatchKernel : public ICpuKernel
 {
 public:
-    CpuConcatenateBatchKernel();
+    CpuConcatenateBatchKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConcatenateBatchKernel);
     /** Configure kernel for a given list of arguments
      *
@@ -51,11 +48,9 @@
      * @param[in,out] dst          Destination tensor info. Data types supported: Same as @p src.
      */
     void configure(const ITensorInfo *src, unsigned int batch_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref CpuConcatenateBatchKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Source tensor info. Data types supported: All.
-     * @param[in] batch_offset The offset on axis # 3.
-     * @param[in] dst          Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref CpuConcatenateBatchKernel::configure()
      *
      * @return a status
      */
@@ -69,10 +64,10 @@
     using BatchConcatFunction = void(const ITensor *, ITensor *, unsigned int, const Window &);
 
 private:
-    BatchConcatFunction *_func;
-    unsigned int         _batch_offset;
+    BatchConcatFunction *_func{ nullptr };
+    unsigned int         _batch_offset{ 0 };
 };
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_CONCATENATEBATCH_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_CONCATENATE_BATCH_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuConcatenateDepthKernel.cpp b/src/core/cpu/kernels/CpuConcatenateDepthKernel.cpp
index a7e5cd8..133499d 100644
--- a/src/core/cpu/kernels/CpuConcatenateDepthKernel.cpp
+++ b/src/core/cpu/kernels/CpuConcatenateDepthKernel.cpp
@@ -146,11 +146,6 @@
 }
 } // namespace
 
-CpuConcatenateDepthKernel::CpuConcatenateDepthKernel()
-    : _func(nullptr), _depth_offset(0)
-{
-}
-
 void CpuConcatenateDepthKernel::configure(const ITensorInfo *src, unsigned int depth_offset, ITensorInfo *dst)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
diff --git a/src/core/cpu/kernels/CpuConcatenateDepthKernel.h b/src/core/cpu/kernels/CpuConcatenateDepthKernel.h
index af89c24..3ec19a8 100644
--- a/src/core/cpu/kernels/CpuConcatenateDepthKernel.h
+++ b/src/core/cpu/kernels/CpuConcatenateDepthKernel.h
@@ -22,8 +22,8 @@
  * SOFTWARE.
  */
 
-#ifndef ARM_COMPUTE_CPU_CONCATENATEDEPTH_KERNEL_H
-#define ARM_COMPUTE_CPU_CONCATENATEDEPTH_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H
+#define ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -43,7 +43,7 @@
 class CpuConcatenateDepthKernel : public ICpuKernel
 {
 public:
-    CpuConcatenateDepthKernel();
+    CpuConcatenateDepthKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConcatenateDepthKernel);
     /** Configure kernel for a given list of arguments
      *
@@ -56,11 +56,9 @@
      *
      */
     void configure(const ITensorInfo *src, unsigned int depth_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref CpuConcatenateDepthKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Source tensor info. Data types supported:  QASYMM8/QASYMM8_SIGNED/F16/F32.
-     * @param[in] depth_offset The offset on the Z axis.
-     * @param[in] dst          Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref CpuConcatenateDepthKernel::configure()
      *
      * @return a status
      */
@@ -74,10 +72,10 @@
     using DepthConcatFunction = void(const ITensor *, ITensor *, unsigned int, const Window &);
 
 private:
-    DepthConcatFunction *_func;
-    unsigned int         _depth_offset;
+    DepthConcatFunction *_func{ nullptr };
+    unsigned int         _depth_offset{ 0 };
 };
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_CONCATENATEDEPTH_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuConcatenateHeightKernel.cpp b/src/core/cpu/kernels/CpuConcatenateHeightKernel.cpp
index 54b9726..dfd442b 100644
--- a/src/core/cpu/kernels/CpuConcatenateHeightKernel.cpp
+++ b/src/core/cpu/kernels/CpuConcatenateHeightKernel.cpp
@@ -62,11 +62,6 @@
 }
 } // namespace
 
-CpuConcatenateHeightKernel::CpuConcatenateHeightKernel()
-    : _height_offset(0)
-{
-}
-
 void CpuConcatenateHeightKernel::configure(const ITensorInfo *src, unsigned int height_offset, ITensorInfo *dst)
 {
     ARM_COMPUTE_UNUSED(src);
diff --git a/src/core/cpu/kernels/CpuConcatenateHeightKernel.h b/src/core/cpu/kernels/CpuConcatenateHeightKernel.h
index 609bb21..e5e15e1 100644
--- a/src/core/cpu/kernels/CpuConcatenateHeightKernel.h
+++ b/src/core/cpu/kernels/CpuConcatenateHeightKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_CONCATENATEHEIGHT_KERNEL_H
-#define ARM_COMPUTE_CPU_CONCATENATEHEIGHT_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_CONCATENATE_HEIGHT_KERNEL_H
+#define ARM_COMPUTE_CPU_CONCATENATE_HEIGHT_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -39,7 +39,7 @@
 class CpuConcatenateHeightKernel : public ICpuKernel
 {
 public:
-    CpuConcatenateHeightKernel();
+    CpuConcatenateHeightKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConcatenateHeightKernel);
     /** Configure kernel for a given list of arguments
      *
@@ -49,11 +49,9 @@
      *
      */
     void configure(const ITensorInfo *src, unsigned int height_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref CpuConcatenateHeightKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src           Source tensor info. Data types supported: All
-     * @param[in] height_offset The starting offset on the Y axis for the output tensor.
-     * @param[in] dst           Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref CpuConcatenateHeightKernel::configure()
      *
      * @return a status
      */
@@ -64,9 +62,9 @@
     const char *name() const override;
 
 private:
-    unsigned int _height_offset;
+    unsigned int _height_offset{ 0 };
 };
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_CONCATENATEHEIGHT_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_CONCATENATE_HEIGHT_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuConcatenateWidthKernel.cpp b/src/core/cpu/kernels/CpuConcatenateWidthKernel.cpp
index effcbc3..ad33b0c 100644
--- a/src/core/cpu/kernels/CpuConcatenateWidthKernel.cpp
+++ b/src/core/cpu/kernels/CpuConcatenateWidthKernel.cpp
@@ -62,11 +62,6 @@
 }
 } // namespace
 
-CpuConcatenateWidthKernel::CpuConcatenateWidthKernel()
-    : _width_offset(0)
-{
-}
-
 void CpuConcatenateWidthKernel::configure(const ITensorInfo *src, unsigned int width_offset, ITensorInfo *dst)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
diff --git a/src/core/cpu/kernels/CpuConcatenateWidthKernel.h b/src/core/cpu/kernels/CpuConcatenateWidthKernel.h
index afdc3cc..f64191e 100644
--- a/src/core/cpu/kernels/CpuConcatenateWidthKernel.h
+++ b/src/core/cpu/kernels/CpuConcatenateWidthKernel.h
@@ -22,8 +22,8 @@
  * SOFTWARE.
  */
 
-#ifndef ARM_COMPUTE_CPU_CONCATENATEWIDTH_KERNEL_H
-#define ARM_COMPUTE_CPU_CONCATENATEWIDTH_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_CONCATENATE_WIDTH_KERNEL_H
+#define ARM_COMPUTE_CPU_CONCATENATE_WIDTH_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -40,7 +40,7 @@
 class CpuConcatenateWidthKernel : public ICPPKernel
 {
 public:
-    CpuConcatenateWidthKernel();
+    CpuConcatenateWidthKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConcatenateWidthKernel);
     /** Configure kernel for a given list of arguments
      *
@@ -49,11 +49,9 @@
      * @param[in,out] dst          Destination tensor info. Data types supported: Same as @p src.
      */
     void configure(const ITensorInfo *src, unsigned int width_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref CpuConcatenateWidthKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Source tensor info. Data types supported: All
-     * @param[in] width_offset The offset on the X axis.
-     * @param[in] dst          Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref CpuConcatenateWidthKernel::configure()
      *
      * @return a status
      */
@@ -64,9 +62,9 @@
     const char *name() const override;
 
 private:
-    unsigned int _width_offset;
+    unsigned int _width_offset{ 0 };
 };
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_CONCATENATEWIDTH_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_CONCATENATE_WIDTH_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.cpp b/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.cpp
index d91ee64..5bf70dc 100644
--- a/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.cpp
+++ b/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.cpp
@@ -34,11 +34,6 @@
 {
 namespace kernels
 {
-CpuConvertFullyConnectedWeightsKernel::CpuConvertFullyConnectedWeightsKernel()
-    : _factor1(0), _factor2(0)
-{
-}
-
 void CpuConvertFullyConnectedWeightsKernel::configure(const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_input_shape,
                                                       DataLayout data_layout)
 
diff --git a/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.h b/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.h
index c867e3d..3ba3162 100644
--- a/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.h
+++ b/src/core/cpu/kernels/CpuConvertFullyConnectedWeightsKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_KERNEL_H
-#define ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H
+#define ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -44,8 +44,7 @@
 class CpuConvertFullyConnectedWeightsKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
-    CpuConvertFullyConnectedWeightsKernel();
+    CpuConvertFullyConnectedWeightsKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConvertFullyConnectedWeightsKernel);
     /** Set the src and dst tensor.
      *
@@ -55,12 +54,9 @@
      * @param[in] data_layout          The data layout the weights have been trained in.
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_input_shape, DataLayout data_layout);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuConvertFullyConnectedWeightsKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src                  Source weights tensor info to convert. Must be 2 dimensional. Data types supported: All.
-     * @param[in] dst                  The converted weights tensor info. Shape and Data Type: Same as @p src.
-     * @param[in] original_input_shape Shape of the original src tensor (the one entering fully connected layer).
-     * @param[in] data_layout          The data layout the weights have been trained in.
+     * Similar to @ref CpuConvertFullyConnectedWeightsKernel::configure()
      *
      * @return a status
      */
@@ -71,8 +67,8 @@
     const char *name() const override;
 
 private:
-    unsigned int _factor1; /*  equals to the number of elements per original src plane if @p data_layout == NCHW; its number of channels otherwise */
-    unsigned int _factor2; /*  equals to the number of elements per original src plane if @p data_layout == NHWC; its number of channels otherwise */
+    unsigned int _factor1{ 0 }; /* equals to the number of elements per original src plane if @p data_layout == NCHW; its number of channels otherwise */
+    unsigned int _factor2{ 0 }; /* equals to the number of elements per original src plane if @p data_layout == NHWC; its number of channels otherwise */
 
     /** Template function to run the permute
      *
@@ -86,4 +82,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_KERNEL_H */
\ No newline at end of file
+#endif /* ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H */
\ No newline at end of file
diff --git a/src/core/cpu/kernels/CpuCopyKernel.h b/src/core/cpu/kernels/CpuCopyKernel.h
index 98b79a9..e2f1ed6 100644
--- a/src/core/cpu/kernels/CpuCopyKernel.h
+++ b/src/core/cpu/kernels/CpuCopyKernel.h
@@ -46,11 +46,9 @@
      * @param[in]  padding (Optional) Padding to be applied to the input tensor
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, const PaddingList &padding = PaddingList());
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuCopyKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src     Source tensor. Data types supported: All
-     * @param[in] dst     Destination tensor. Data types supported: same as @p src.
-     * @param[in] padding (Optional) Padding to be applied to the input tensor
+     * Similar to @ref CpuCopyKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.cpp b/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.cpp
index eac9baa..5530eba 100644
--- a/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.cpp
+++ b/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.cpp
@@ -803,11 +803,6 @@
 }
 } // namespace
 
-CpuDepthwiseConv2dNativeKernel::CpuDepthwiseConv2dNativeKernel()
-    : _func(), _conv_info(), _depth_multiplier(1), _dilation(), _output_multiplier(), _output_shift(), _has_biases()
-{
-}
-
 void CpuDepthwiseConv2dNativeKernel::configure(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, weights, dst);
@@ -945,6 +940,11 @@
     auto       dst     = tensors.get_tensor(TensorType::ACL_DST);
     (this->*_func)(src, weights, biases, dst, window, _has_biases);
 }
+
+const char *CpuDepthwiseConv2dNativeKernel::name() const
+{
+    return "CpuDepthwiseConv2dNativeKernel";
+}
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
diff --git a/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.h b/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.h
index 559c46d..eb7041f 100644
--- a/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.h
+++ b/src/core/cpu/kernels/CpuDepthwiseConv2dNativeKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_DEPTHWISECONV2DNATIVEKERNEL_H
-#define ARM_COMPUTE_CPU_DEPTHWISECONV2DNATIVEKERNEL_H
+#ifndef ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_NATIVE_KERNEL_H
+#define ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_NATIVE_KERNEL_H
 
 #include "arm_compute/core/utils/misc/Traits.h"
 #include "src/core/common/Macros.h"
@@ -43,12 +43,7 @@
 class CpuDepthwiseConv2dNativeKernel : public ICpuKernel
 {
 public:
-    const char *name() const override
-    {
-        return "CpuDepthwiseConv2dNativeKernel";
-    }
-    /** Default constructor */
-    CpuDepthwiseConv2dNativeKernel();
+    CpuDepthwiseConv2dNativeKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDepthwiseConv2dNativeKernel);
 
     /** Initialize the function's source, destination and parameters.
@@ -75,6 +70,7 @@
 
     // Inherited methods overridden:
     void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override;
+    const char *name() const override;
 
 private:
     template <typename T>
@@ -95,15 +91,15 @@
      */
     using DepthwiseFunctionPtr = void (CpuDepthwiseConv2dNativeKernel::*)(const ITensor *src, const ITensor *weights, const ITensor *bias, ITensor *dst, const Window &window, bool has_biases);
 
-    DepthwiseFunctionPtr _func;
-    PadStrideInfo        _conv_info;
-    unsigned int         _depth_multiplier;
-    Size2D               _dilation;
-    std::vector<int>     _output_multiplier;
-    std::vector<int>     _output_shift;
-    bool                 _has_biases;
+    DepthwiseFunctionPtr _func{ nullptr };
+    PadStrideInfo        _conv_info{};
+    unsigned int         _depth_multiplier{ 1 };
+    Size2D               _dilation{};
+    std::vector<int>     _output_multiplier{};
+    std::vector<int>     _output_shift{};
+    bool                 _has_biases{ false };
 };
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_DEPTHWISECONV2DNATIVEKERNEL_H */
+#endif /* ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_NATIVE_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuDequantizeKernel.h b/src/core/cpu/kernels/CpuDequantizeKernel.h
index 798f32c..e80aa3a 100644
--- a/src/core/cpu/kernels/CpuDequantizeKernel.h
+++ b/src/core/cpu/kernels/CpuDequantizeKernel.h
@@ -37,7 +37,6 @@
 class CpuDequantizeKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuDequantizeKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDequantizeKernel);
     /** Set input, output tensors.
diff --git a/src/core/cpu/kernels/CpuDirectConv2dKernel.h b/src/core/cpu/kernels/CpuDirectConv2dKernel.h
index 62ed96f..9bef1c4 100644
--- a/src/core/cpu/kernels/CpuDirectConv2dKernel.h
+++ b/src/core/cpu/kernels/CpuDirectConv2dKernel.h
@@ -21,15 +21,14 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_DIRECTCONV2D_KERNEL_H
-#define ARM_COMPUTE_CPU_DIRECTCONV2D_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_DIRECT_CONV2D_KERNEL_H
+#define ARM_COMPUTE_CPU_DIRECT_CONV2D_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
 
 namespace arm_compute
 {
-class ITensor;
 namespace cpu
 {
 namespace kernels
@@ -38,7 +37,6 @@
 class CpuDirectConv2dKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuDirectConv2dKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDirectConv2dKernel);
     /** Set the src, weights, and dst tensors.
diff --git a/src/core/cpu/kernels/CpuDirectConv2dOutputStageKernel.h b/src/core/cpu/kernels/CpuDirectConv2dOutputStageKernel.h
index 62bc5d4..749411c 100644
--- a/src/core/cpu/kernels/CpuDirectConv2dOutputStageKernel.h
+++ b/src/core/cpu/kernels/CpuDirectConv2dOutputStageKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_DIRECTCONV2D_OUTPUTSTAGE_KERNEL_H
-#define ARM_COMPUTE_CPU_DIRECTCONV2D_OUTPUTSTAGE_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_DIRECT_CONV2D_OUTPUT_STAGE_KERNEL_H
+#define ARM_COMPUTE_CPU_DIRECT_CONV2D_OUTPUT_STAGE_KERNEL_H
 
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/common/Macros.h"
@@ -30,7 +30,6 @@
 
 namespace arm_compute
 {
-class ITensor;
 namespace cpu
 {
 namespace kernels
@@ -44,7 +43,6 @@
 class CpuDirectConv2dOutputStageKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuDirectConv2dOutputStageKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDirectConv2dOutputStageKernel);
     /** Set the accumulate buffer and the biases of the kernel.
@@ -84,4 +82,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_DIRECTCONV2D_OUTPUTSTAGE_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_DIRECT_CONV2D_OUTPUT_STAGE_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuElementwiseKernel.h b/src/core/cpu/kernels/CpuElementwiseKernel.h
index 50c8d29..75137da 100644
--- a/src/core/cpu/kernels/CpuElementwiseKernel.h
+++ b/src/core/cpu/kernels/CpuElementwiseKernel.h
@@ -29,7 +29,6 @@
 
 namespace arm_compute
 {
-class ITensor;
 namespace cpu
 {
 namespace kernels
@@ -89,7 +88,6 @@
 class CpuArithmeticKernel : public CpuElementwiseKernel
 {
 public:
-    /** Default constructor */
     CpuArithmeticKernel() = default;
 
     /** Configure kernel
@@ -130,7 +128,6 @@
 class CpuDivisionKernel : public CpuArithmeticKernel
 {
 public:
-    /** Default constructor */
     CpuDivisionKernel() = default;
 
     /** Configure kernel
@@ -157,7 +154,6 @@
 class CpuPowerKernel : public CpuArithmeticKernel
 {
 public:
-    /** Default constructor */
     CpuPowerKernel() = default;
 
     /** Configure kernel
@@ -184,7 +180,6 @@
 class CpuComparisonKernel : public CpuElementwiseKernel
 {
 public:
-    /** Default constructor */
     CpuComparisonKernel() = default;
 
     /** Configure kernel
diff --git a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
index 91fa75e..56e3297 100644
--- a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
+++ b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
@@ -105,11 +105,6 @@
 }
 } // namespace
 
-CpuElementwiseUnaryKernel::CpuElementwiseUnaryKernel()
-    : _op()
-{
-}
-
 void CpuElementwiseUnaryKernel::configure(ElementWiseUnary op, const ITensorInfo &src, ITensorInfo &dst)
 {
     ARM_COMPUTE_ERROR_THROW_ON(validate(op, src, dst));
@@ -169,6 +164,11 @@
     ARM_COMPUTE_ERROR_ON(func == nullptr);
     func(src, dst, window, _op);
 }
+
+const char *CpuElementwiseUnaryKernel::name() const
+{
+    return "CpuElementwiseUnaryKernel";
+}
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
diff --git a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.h b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.h
index ceb90dc..43c6ede 100644
--- a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.h
+++ b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.h
@@ -30,7 +30,6 @@
 
 namespace arm_compute
 {
-class ITensor;
 namespace cpu
 {
 namespace kernels
@@ -39,19 +38,11 @@
  *
  * Element-wise operation is computed by:
  * @f[ dst(x) = OP(src(x))@f]
- *
  */
 class CpuElementwiseUnaryKernel : public ICpuKernel
 {
 public:
-    const char *name() const override
-    {
-        return "CpuElementwiseUnaryKernel";
-    }
-    /** Default constructor */
-    CpuElementwiseUnaryKernel();
-    /** Default destructor */
-    ~CpuElementwiseUnaryKernel() = default;
+    CpuElementwiseUnaryKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuElementwiseUnaryKernel);
 
     /** Function to configure the @ref CpuElementwiseUnaryKernel
@@ -61,19 +52,17 @@
      * @param[out] dst Output tensor. Data types supported: Same as @p src.
      */
     void configure(ElementWiseUnary op, const ITensorInfo &src, ITensorInfo &dst);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuElementwiseUnaryKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] op  Arithmetic operation to be executed.
-     * @param[in] src First tensor input info. Data types supported: F16/F32, F16/F32/S32 for NEG/ABS operations.
-     * @param[in] dst Output tensor info. Data types supported: Same as @p src.
+     * Similar to CpuElementwiseUnaryKernel::configure()
      *
-     * @return a Status
+     * @return a status
      */
     static Status validate(ElementWiseUnary op, const ITensorInfo &src, const ITensorInfo &dst);
 
     // Inherited methods overridden:
     void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override;
+    const char *name() const override;
 
     /** Common signature for all the specialised elementwise unary micro-kernels
      *
@@ -82,7 +71,7 @@
     using ElementwiseUnaryUkernelPtr = std::add_pointer<void(const ITensor *, ITensor *, const Window &, ElementWiseUnary)>::type;
 
 private:
-    ElementWiseUnary _op;
+    ElementWiseUnary _op{};
 };
 } // namespace kernels
 } // namespace cpu
diff --git a/src/core/cpu/kernels/CpuGemmInterleave4x4Kernel.h b/src/core/cpu/kernels/CpuGemmInterleave4x4Kernel.h
index 243aab9..8f1a543 100644
--- a/src/core/cpu/kernels/CpuGemmInterleave4x4Kernel.h
+++ b/src/core/cpu/kernels/CpuGemmInterleave4x4Kernel.h
@@ -55,7 +55,6 @@
 class CpuGemmInterleave4x4Kernel : public ICpuKernel
 {
 public:
-    /** Default Constructor */
     CpuGemmInterleave4x4Kernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmInterleave4x4Kernel);
     /** Initialise the kernel's src and dst.
@@ -79,4 +78,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_GEMM_INTERLEAVE4x4_KERNEL_H*/
+#endif /* ARM_COMPUTE_CPU_GEMM_INTERLEAVE4x4_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ScaleKernel.h b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ScaleKernel.h
index 646242d..f3cdbdc 100644
--- a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ScaleKernel.h
+++ b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ScaleKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32_SCALE_KERNEL_H
-#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32_SCALE_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32_SCALE_KERNEL_H
+#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32_SCALE_KERNEL_H
 
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/common/Macros.h"
@@ -30,6 +30,7 @@
 
 namespace arm_compute
 {
+// Forward declarations
 class ITensor;
 namespace cpu
 {
@@ -53,7 +54,6 @@
 class CpuGemmLowpQuantizeDownInt32ScaleKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuGemmLowpQuantizeDownInt32ScaleKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmLowpQuantizeDownInt32ScaleKernel);
     /** Initialise the kernel's input and output.
@@ -104,4 +104,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32_SCALE_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32_SCALE_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h
index 4d743e9..7a1197d 100644
--- a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h
+++ b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H
-#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H
+#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H
 
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/common/Macros.h"
@@ -30,6 +30,7 @@
 
 namespace arm_compute
 {
+// Forward declaration
 class ITensor;
 namespace cpu
 {
@@ -50,7 +51,6 @@
 class CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel);
     /** Initialise the kernel's input and output.
@@ -108,4 +108,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT16_SCALEBYFIXEDPOINT_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h
index a941f1f..9ebb529 100644
--- a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h
+++ b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H
-#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H
+#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H
 
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/common/Macros.h"
@@ -30,6 +30,7 @@
 
 namespace arm_compute
 {
+// Forward declaration
 class ITensor;
 namespace cpu
 {
@@ -51,7 +52,6 @@
 class CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel);
     /** Initialise the kernel's input and output.
@@ -111,4 +111,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOINT8_SCALEBYFIXEDPOINT_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
index 9b4c056..312cad9 100644
--- a/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
+++ b/src/core/cpu/kernels/CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H
-#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H
+#ifndef ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H
+#define ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H
 
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/common/Macros.h"
@@ -30,6 +30,7 @@
 
 namespace arm_compute
 {
+// Forward declaration
 class ITensor;
 namespace cpu
 {
@@ -51,7 +52,6 @@
 class CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel);
     /** Initialise the kernel's input and output.
@@ -105,4 +105,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWNINT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_GEMMLOWP_QUANTIZEDOWN_INT32TOUINT8_SCALEBYFIXEDPOINT_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h b/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h
index c8e6fa9..f9450b9 100644
--- a/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h
+++ b/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h
@@ -44,7 +44,6 @@
 class CpuGemmMatrixAdditionKernel : public ICpuKernel
 {
 public:
-    /** Constructor */
     CpuGemmMatrixAdditionKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmMatrixAdditionKernel);
     /** Initialise the kernel's input and output.
diff --git a/src/core/cpu/kernels/CpuGemmMatrixMultiplyKernel.h b/src/core/cpu/kernels/CpuGemmMatrixMultiplyKernel.h
index bf13342..974ff85 100644
--- a/src/core/cpu/kernels/CpuGemmMatrixMultiplyKernel.h
+++ b/src/core/cpu/kernels/CpuGemmMatrixMultiplyKernel.h
@@ -42,7 +42,6 @@
 class CpuGemmMatrixMultiplyKernel : public ICpuKernel
 {
 public:
-    /** Constructor */
     CpuGemmMatrixMultiplyKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmMatrixMultiplyKernel);
     /** Initialise the kernel's input and output.
@@ -89,4 +88,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_GEMM_MATRIX_MULTIPLY_KERNEL_H*/
+#endif /* ARM_COMPUTE_CPU_GEMM_MATRIX_MULTIPLY_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuGemmTranspose1xWKernel.h b/src/core/cpu/kernels/CpuGemmTranspose1xWKernel.h
index c9c22bd..1a9287f 100644
--- a/src/core/cpu/kernels/CpuGemmTranspose1xWKernel.h
+++ b/src/core/cpu/kernels/CpuGemmTranspose1xWKernel.h
@@ -71,7 +71,6 @@
 class CpuGemmTranspose1xWKernel : public ICpuKernel
 {
 public:
-    /** Constructor */
     CpuGemmTranspose1xWKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmTranspose1xWKernel);
     /** Configure kernel for a given list of arguments
@@ -95,4 +94,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_GEMM_TRANSPOSE1xW_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_GEMM_TRANSPOSE1xW_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuMulKernel.h b/src/core/cpu/kernels/CpuMulKernel.h
index 3e667bc..3ea176c 100644
--- a/src/core/cpu/kernels/CpuMulKernel.h
+++ b/src/core/cpu/kernels/CpuMulKernel.h
@@ -37,7 +37,6 @@
 class CpuMulKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuMulKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuMulKernel);
     /** Initialise the kernel's input, dst and border mode.
@@ -122,7 +121,6 @@
 class CpuComplexMulKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuComplexMulKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuComplexMulKernel);
     /** Initialise the kernel's src, dst and border mode.
diff --git a/src/core/cpu/kernels/CpuPermuteKernel.h b/src/core/cpu/kernels/CpuPermuteKernel.h
index 9c59d5b..2955f38 100644
--- a/src/core/cpu/kernels/CpuPermuteKernel.h
+++ b/src/core/cpu/kernels/CpuPermuteKernel.h
@@ -48,13 +48,9 @@
      * @param[in]  perm Permutation vector
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, const PermutationVector &perm);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuPermuteKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Arbitrary permutation vectors are supported with rank not greater than 4
-     *
-     * @param[in] src  Source tensor to permute. Data types supported: All
-     * @param[in] dst  Destination tensor. Data types supported: Same as @p src
-     * @param[in] perm Permutation vector
+     * Similar to @ref CpuPermuteKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/cpu/kernels/CpuPool2dKernel.h b/src/core/cpu/kernels/CpuPool2dKernel.h
index ff7d7bb..9ed398b 100644
--- a/src/core/cpu/kernels/CpuPool2dKernel.h
+++ b/src/core/cpu/kernels/CpuPool2dKernel.h
@@ -38,7 +38,6 @@
 class CpuPool2dKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuPool2dKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuPool2dKernel);
     /** Configure kernel for a given list of arguments
@@ -80,4 +79,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_POOL2D_KERNEL_H */
+#endif /* ARM_COMPUTE_CPU_POOL2D_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuQuantizeKernel.h b/src/core/cpu/kernels/CpuQuantizeKernel.h
index d3422d3..834a2e0 100644
--- a/src/core/cpu/kernels/CpuQuantizeKernel.h
+++ b/src/core/cpu/kernels/CpuQuantizeKernel.h
@@ -40,7 +40,6 @@
 class CpuQuantizeKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuQuantizeKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuQuantizeKernel);
     /** Set the input, output.
diff --git a/src/core/cpu/kernels/CpuReshapeKernel.h b/src/core/cpu/kernels/CpuReshapeKernel.h
index add6782..1425fbe 100644
--- a/src/core/cpu/kernels/CpuReshapeKernel.h
+++ b/src/core/cpu/kernels/CpuReshapeKernel.h
@@ -46,10 +46,9 @@
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
 
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuReshapeKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data type supported: All
-     * @param[in] dst Destination tensor info. Data type supported: Same as @p src
+     * Similar to @ref CpuReshapeKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/cpu/kernels/CpuScaleKernel.h b/src/core/cpu/kernels/CpuScaleKernel.h
index afaf074..a2b6537 100644
--- a/src/core/cpu/kernels/CpuScaleKernel.h
+++ b/src/core/cpu/kernels/CpuScaleKernel.h
@@ -38,7 +38,6 @@
 class CpuScaleKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuScaleKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuScaleKernel);
     /** Initialise the kernel's inputs, output and interpolation policy
@@ -106,4 +105,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_SCALEKERNEL_H */
+#endif /* ARM_COMPUTE_CPU_SCALEKERNEL_H */
diff --git a/src/core/cpu/kernels/CpuSoftmaxKernel.h b/src/core/cpu/kernels/CpuSoftmaxKernel.h
index 2912098..776c0d6 100644
--- a/src/core/cpu/kernels/CpuSoftmaxKernel.h
+++ b/src/core/cpu/kernels/CpuSoftmaxKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_SOFTMAXKERNEL_H
-#define ARM_COMPUTE_CPU_SOFTMAXKERNEL_H
+#ifndef ARM_COMPUTE_CPU_SOFTMAX_KERNEL_H
+#define ARM_COMPUTE_CPU_SOFTMAX_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/cpu/ICpuKernel.h"
@@ -37,7 +37,6 @@
 class CpuLogits1DMaxKernel : public ICpuKernel
 {
 public:
-    /** Constructor */
     CpuLogits1DMaxKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuLogits1DMaxKernel);
     /** Set the input and output tensors.
@@ -71,7 +70,6 @@
 class CpuLogits1DSoftmaxKernel : public ICpuKernel
 {
 public:
-    /** Default constructor */
     CpuLogits1DSoftmaxKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuLogits1DSoftmaxKernel);
 
@@ -110,4 +108,4 @@
 } // namespace kernels
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_SOFTMAXKERNEL_H */
+#endif /* ARM_COMPUTE_CPU_SOFTMAX_KERNEL_H */
diff --git a/src/core/cpu/kernels/CpuTransposeKernel.h b/src/core/cpu/kernels/CpuTransposeKernel.h
index f09f427..920349d 100644
--- a/src/core/cpu/kernels/CpuTransposeKernel.h
+++ b/src/core/cpu/kernels/CpuTransposeKernel.h
@@ -45,10 +45,9 @@
      * @param[out] dst Destination tensor. Data types supported: Same as @p src
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuTransposeKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor to permute. Data types supported: All
-     * @param[in] dst Destination tensor. Data types supported: Same as @p src
+     * Similar to CpuTransposeKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClActivationKernel.cpp b/src/core/gpu/cl/kernels/ClActivationKernel.cpp
index e892d6a..21c0563 100644
--- a/src/core/gpu/cl/kernels/ClActivationKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClActivationKernel.cpp
@@ -87,7 +87,6 @@
 } // namespace
 
 ClActivationKernel::ClActivationKernel()
-    : _run_in_place(false)
 {
     _type = CLKernelType::ELEMENTWISE;
 }
diff --git a/src/core/gpu/cl/kernels/ClActivationKernel.h b/src/core/gpu/cl/kernels/ClActivationKernel.h
index 68c309e..720b16a 100644
--- a/src/core/gpu/cl/kernels/ClActivationKernel.h
+++ b/src/core/gpu/cl/kernels/ClActivationKernel.h
@@ -51,12 +51,9 @@
      * @param[in]      act_info        Activation layer information.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, ActivationLayerInfo act_info);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClActivationKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src      Source tensor info. In case of @p dst tensor info = nullptr, this tensor will store the result
-     *                     of the activation function. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
-     * @param[in] dst      Destination tensor info. Data type supported: same as @p src
-     * @param[in] act_info Activation layer information.
+     * Similar to @ref ClActivationKernel::configure()
      *
      * @return a status
      */
@@ -66,7 +63,7 @@
     void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override;
 
 private:
-    bool _run_in_place;
+    bool _run_in_place{ false };
 };
 } // namespace kernels
 } // namespace opencl
diff --git a/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.cpp b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.cpp
index dbc628d..fba1b0e 100644
--- a/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.cpp
@@ -60,7 +60,6 @@
 } // namespace
 
 ClBatchConcatenateKernel::ClBatchConcatenateKernel()
-    : _batch_offset(0)
 {
     _type = CLKernelType::ELEMENTWISE;
 }
diff --git a/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h
index d9fa905..2963d7c 100644
--- a/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h
+++ b/src/core/gpu/cl/kernels/ClBatchConcatenateKernel.h
@@ -40,7 +40,6 @@
 class ClBatchConcatenateKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClBatchConcatenateKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClBatchConcatenateKernel);
     /** Initialise the kernel's source and destination
@@ -55,11 +54,9 @@
      *
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int batch_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClBatchConcatenateKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Input tensor info. Data types supported: All.
-     * @param[in] batch_offset The offset on axis # 3.
-     * @param[in] dst          Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref ClBatchConcatenateKernel::configure()
      *
      * @return a status
      */
@@ -69,7 +66,7 @@
     void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override;
 
 private:
-    unsigned int _batch_offset;
+    unsigned int _batch_offset{ 0 };
 };
 } // namespace kernels
 } // namespace opencl
diff --git a/src/core/gpu/cl/kernels/ClConvertFullyConnectedWeightsKernel.h b/src/core/gpu/cl/kernels/ClConvertFullyConnectedWeightsKernel.h
index 6f4f09d..3976fd4 100644
--- a/src/core/gpu/cl/kernels/ClConvertFullyConnectedWeightsKernel.h
+++ b/src/core/gpu/cl/kernels/ClConvertFullyConnectedWeightsKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CLCONVERTFULLYCONNECTEDWEIGHTSKERNEL_H
-#define ARM_COMPUTE_CLCONVERTFULLYCONNECTEDWEIGHTSKERNEL_H
+#ifndef ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H
+#define ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/gpu/cl/ClCompileContext.h"
@@ -30,8 +30,6 @@
 
 namespace arm_compute
 {
-class ICLTensor;
-
 /** Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa.
  *
  * @note This function can be applied to the 2D weights used by a Fully Connected layer if:
@@ -58,12 +56,11 @@
      * @param[in]  data_layout        The data layout the weights have been trained in.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_src_shape, DataLayout data_layout);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClConvertFullyConnectedWeightsKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src                Source weights tensor info to convert. Must be 2 dimensional. Data types supported: All.
-     * @param[in] dst                The converted weights tensor info. Shape and Data Type: Same as @p src.
-     * @param[in] original_src_shape Shape of the original src tensor (the one entering fully connected layer).
-     * @param[in] data_layout        The data layout the weights have been trained in.
+     * Similar to @ref ClConvertFullyConnectedWeightsKernel::configure()
+     *
+     * @return a status
      */
     static Status validate(const ITensorInfo *src, const ITensorInfo *dst, const TensorShape &original_src_shape, DataLayout data_layout);
 
@@ -73,4 +70,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLCONVERTFULLYCONNECTEDWEIGHTSKERNEL_H */
+#endif /* ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClCopyKernel.h b/src/core/gpu/cl/kernels/ClCopyKernel.h
index f3eb0aa..d2732c4 100644
--- a/src/core/gpu/cl/kernels/ClCopyKernel.h
+++ b/src/core/gpu/cl/kernels/ClCopyKernel.h
@@ -48,11 +48,9 @@
      * @param[in]  dst_window      (Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, Window *dst_window = nullptr);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClCopyKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src        Source tensor info. Data types supported: All.
-     * @param[in] dst        Destination tensor info. Data types supported: same as @p src.
-     * @param[in] dst_window (Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.
+     * Similar to @ref ClCopyKernel::configure()
      *
      * @return a status
      */
@@ -68,4 +66,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_COPY_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_COPY_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClCropKernel.cpp b/src/core/gpu/cl/kernels/ClCropKernel.cpp
index ef2e48b..a052ef5 100644
--- a/src/core/gpu/cl/kernels/ClCropKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClCropKernel.cpp
@@ -41,11 +41,6 @@
 {
 namespace kernels
 {
-void ClCropKernel::configure(const ITensorInfo *src, ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value, Window *dst_window)
-{
-    configure(CLKernelLibrary::get().get_compile_context(), src, dst, start, end, batch_index, extrapolation_value, dst_window);
-}
-
 ClCropKernel::ClCropKernel()
 {
     _type = CLKernelType::ELEMENTWISE;
diff --git a/src/core/gpu/cl/kernels/ClCropKernel.h b/src/core/gpu/cl/kernels/ClCropKernel.h
index 7120dbb..d819122 100644
--- a/src/core/gpu/cl/kernels/ClCropKernel.h
+++ b/src/core/gpu/cl/kernels/ClCropKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CLCROPKERNEL_H
-#define ARM_COMPUTE_CLCROPKERNEL_H
+#ifndef ARM_COMPUTE_CL_CROP_KERNEL_H
+#define ARM_COMPUTE_CL_CROP_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/gpu/cl/ClCompileContext.h"
@@ -44,19 +44,6 @@
      *
      * @note Supported tensor rank: up to 4
      *
-     * @param[in]  src                 Source tensor info. Data type supported: All. Data layouts supported: NHWC.
-     * @param[out] dst                 Destination tensor info. Data type supported: F32
-     * @param[in]  start               Coordinates of where to start cropping the image.
-     * @param[in]  end                 Coordinates of where to end cropping the image.
-     * @param[in]  batch_index         Fourth dimension index of the 3D image to crop in @p src.
-     * @param[in]  extrapolation_value Value to be used for values outside of the image. Default is 0.
-     * @param[in]  dst_window          Output window to be used in case cropped image is being copied into a tensor. Default is nullptr.
-     */
-    void configure(const ITensorInfo *src, ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value = 0, Window *dst_window = nullptr);
-    /** Configure kernel
-     *
-     * @note Supported tensor rank: up to 4
-     *
      * @param[in]  compile_context     The compile context to be used.
      * @param[in]  src                 Source tensor info. Data type supported: All. Data layouts supported: NHWC.
      * @param[out] dst                 Destination tensor info. Data type supported: F32
@@ -68,18 +55,11 @@
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value = 0,
                    Window *dst_window = nullptr);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref CLStridedSliceKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Supported tensor rank: up to 4
+     * Similar to @ref ClCropKernel::configure()
      *
-     * @param[in] src                 Source tensor info. Data type supported: All. Data layouts supported: NHWC.
-     * @param[in] dst                 Destination tensor info. Data type supported: F32
-     * @param[in] start               Coordinates of where to start cropping the image.
-     * @param[in] end                 Coordinates of where to end cropping the image.
-     * @param[in] batch_index         Fourth dimension index of the 3D image to crop in @p src.
-     * @param[in] extrapolation_value Value to be used for values outside of the image. Default is 0.
-     * @param[in] dst_window          Output window to be used in case cropped image is being copied into a tensor. Default is nullptr.
+     * @return a status
      */
     static Status validate(const ITensorInfo *src, const ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value = 0,
                            Window *dst_window = nullptr);
@@ -95,4 +75,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLCROPKERNEL_H */
+#endif /* ARM_COMPUTE_CL_CROP_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClDepthConcatenateKernel.h b/src/core/gpu/cl/kernels/ClDepthConcatenateKernel.h
index 103ef00..0f40847 100644
--- a/src/core/gpu/cl/kernels/ClDepthConcatenateKernel.h
+++ b/src/core/gpu/cl/kernels/ClDepthConcatenateKernel.h
@@ -40,7 +40,6 @@
 class ClDepthConcatenateKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClDepthConcatenateKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClDepthConcatenateKernel);
     /** Initialise the kernel's source and destination
@@ -55,11 +54,9 @@
      *
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int depth_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClDepthConcatenateKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32
-     * @param[in] depth_offset The offset on the Z axis.
-     * @param[in] dst          Destination tensor info. Data types supported: Same as @p src.
+     * Similar to @ref ClDepthConcatenateKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClDequantizeKernel.h b/src/core/gpu/cl/kernels/ClDequantizeKernel.h
index 2460674..0912e1b 100644
--- a/src/core/gpu/cl/kernels/ClDequantizeKernel.h
+++ b/src/core/gpu/cl/kernels/ClDequantizeKernel.h
@@ -38,7 +38,6 @@
 class ClDequantizeKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClDequantizeKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClDequantizeKernel);
     /** Initialise the kernel's input and output
diff --git a/src/core/gpu/cl/kernels/ClDirectConv2dKernel.h b/src/core/gpu/cl/kernels/ClDirectConv2dKernel.h
index b592a21..4880d4a 100644
--- a/src/core/gpu/cl/kernels/ClDirectConv2dKernel.h
+++ b/src/core/gpu/cl/kernels/ClDirectConv2dKernel.h
@@ -86,4 +86,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_DIRECT_CONV2D_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_DIRECT_CONV2D_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClElementwiseKernel.cpp b/src/core/gpu/cl/kernels/ClElementwiseKernel.cpp
index 7bfdb9e..b645353 100644
--- a/src/core/gpu/cl/kernels/ClElementwiseKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClElementwiseKernel.cpp
@@ -276,21 +276,12 @@
     _type = CLKernelType::ELEMENTWISE;
 }
 
-void ClElementwiseKernel::configure_common(ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst)
-{
-    configure_common(CLKernelLibrary::get().get_compile_context(), src1, src2, dst);
-}
-
 void ClElementwiseKernel::configure_common(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst)
 {
     // Configure kernel window
     auto win_config = validate_and_configure_window(*src1, *src2, *dst);
     ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
 
-    _src1 = src1;
-    _src2 = src2;
-    _dst  = dst;
-
     std::string kernel_name = "elementwise_operation_" + name();
     if(is_data_type_quantized(src1->data_type()))
     {
diff --git a/src/core/gpu/cl/kernels/ClElementwiseKernel.h b/src/core/gpu/cl/kernels/ClElementwiseKernel.h
index 7f55151..ab5c777 100644
--- a/src/core/gpu/cl/kernels/ClElementwiseKernel.h
+++ b/src/core/gpu/cl/kernels/ClElementwiseKernel.h
@@ -44,7 +44,6 @@
 class ClElementwiseKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClElementwiseKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClElementwiseKernel);
 
@@ -80,30 +79,14 @@
     /** Commmon configure function for element-wise operators with no additional options (e.g., Div, Min, Max, SquaredDiff)
      *
      */
-    void configure_common(ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst);
-    /** Commmon configure function for element-wise operators with no additional options (e.g., Div, Min, Max, SquaredDiff)
-     *
-     */
     void configure_common(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst);
 
     ActivationLayerInfo _act_info{};
-
-private:
-    const ITensorInfo *_src1
-    {
-        nullptr
-    }; /**< Source tensor info 1 */
-    const ITensorInfo *_src2
-    {
-        nullptr
-    };                            /**< Source tensor info 2 */
-    ITensorInfo *_dst{ nullptr }; /**< Destination tensor info */
 };
 
 class ClLogicalBinaryKernel : public ClElementwiseKernel
 {
 public:
-    /** Default constructor */
     ClLogicalBinaryKernel() = default;
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClLogicalBinaryKernel);
     /** Function to configure kernel
@@ -115,12 +98,11 @@
      * @param[in] dst             Destination tensor info. Data types supported: same as @p src1.
      */
     void configure(const ClCompileContext &compile_context, LogicalOperation op, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst);
-    /** Static function to check if the given configuration is valid for this kernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] op   Logical binary operation to be executed.
-     * @param[in] src1 First source tensor info. Data types supported: U8.
-     * @param[in] src2 Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst  Destination tensor info. Data types supported: same as @p src1.
+     * Similar to @ref ClLogicalBinaryKernel::configure()
+     *
+     * @return a status
      */
     static Status validate(LogicalOperation op, const ITensorInfo *src1, const ITensorInfo *src2, const ITensorInfo *dst);
 
@@ -153,16 +135,11 @@
     void configure(const ClCompileContext &compile_context, ArithmeticOperation op, ITensorInfo *input1, ITensorInfo *input2, ITensorInfo *output, const ConvertPolicy &policy,
                    const ActivationLayerInfo &act_info = ActivationLayerInfo());
 
-    /** Static function to check if given info will lead to a valid configuration of @ref ClSaturatedArithmeticKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] op       Arithmetic operation to be executed.
-     * @param[in] input1   First tensor input info info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32.
-     * @param[in] input2   Second tensor input info info. Data types supported: Same as @p input1.
-     * @param[in] output   Output tensor info info. Data types supported: Same as @p input1.
-     * @param[in] policy   Policy to use to handle overflow.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClSaturatedArithmeticKernel::configure()
      *
-     * @return a Status
+     * @return a status
      */
     static Status validate(ArithmeticOperation op, const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, const ConvertPolicy &policy,
                            const ActivationLayerInfo &act_info = ActivationLayerInfo());
@@ -197,15 +174,11 @@
     void configure(const ClCompileContext &compile_context, ArithmeticOperation op, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst,
                    const ActivationLayerInfo &act_info = ActivationLayerInfo());
 
-    /** Static function to check if given info will lead to a valid configuration of @ref ClArithmeticKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] op       Arithmetic operation to be executed.
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst      Destination tensor info. Data types supported: same as @p src1.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClArithmeticKernel::configure()
      *
-     * @return a Status
+     * @return a status
      */
     static Status validate(ArithmeticOperation op, const ITensorInfo *src1, const ITensorInfo *src2, const ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
 
diff --git a/src/core/gpu/cl/kernels/ClElementwiseUnaryKernel.h b/src/core/gpu/cl/kernels/ClElementwiseUnaryKernel.h
index 225869b..64cc2f7 100644
--- a/src/core/gpu/cl/kernels/ClElementwiseUnaryKernel.h
+++ b/src/core/gpu/cl/kernels/ClElementwiseUnaryKernel.h
@@ -48,11 +48,9 @@
      * @param[in]  op              Element wise unary operation to perform.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const ElementWiseUnary &op);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClElementWiseUnaryKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
-     * @param[in] op  Element wise unary operation to perform.
+     * Similar to @ref ClElementWiseUnaryKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClFillKernel.cpp b/src/core/gpu/cl/kernels/ClFillKernel.cpp
index 526a466..f213bf8 100644
--- a/src/core/gpu/cl/kernels/ClFillKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClFillKernel.cpp
@@ -47,13 +47,6 @@
     _type = CLKernelType::ELEMENTWISE;
 }
 
-void ClFillKernel::configure(ITensorInfo      *tensor,
-                             const PixelValue &constant_value,
-                             Window           *window)
-{
-    configure(CLKernelLibrary::get().get_compile_context(), tensor, constant_value, window);
-}
-
 void ClFillKernel::configure(const CLCompileContext &compile_context, ITensorInfo *tensor,
                              const PixelValue &constant_value,
                              Window           *window)
diff --git a/src/core/gpu/cl/kernels/ClFillKernel.h b/src/core/gpu/cl/kernels/ClFillKernel.h
index 9542c20..ecc2546 100644
--- a/src/core/gpu/cl/kernels/ClFillKernel.h
+++ b/src/core/gpu/cl/kernels/ClFillKernel.h
@@ -42,24 +42,15 @@
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClFillKernel);
     /** Initialise the kernel's tensor and filling value
      *
-     * @param[in,out] tensor         Input tensor info. Supported data types: All.
-     * @param[in]     constant_value The value used to fill the planes of the tensor
-     * @param[in]     window         Window to be used in case setting only part of a tensor. Default is nullptr.
-     */
-    void configure(ITensorInfo *tensor, const PixelValue &constant_value, Window *window = nullptr);
-    /** Initialise the kernel's tensor and filling value
-     *
      * @param[in]     compile_context The compile context to be used.
      * @param[in,out] tensor          Input tensor info. Supported data types: All.
      * @param[in]     constant_value  The value used to fill the planes of the tensor
      * @param[in]     window          Window to be used in case setting only part of a tensor. Default is nullptr.
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *tensor, const PixelValue &constant_value, Window *window = nullptr);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClFillKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] tensor         Source tensor info. Data types supported: All.
-     * @param[in] constant_value The value used to fill the planes of the tensor
-     * @param[in] window         Window to be used in case setting only part of a tensor. Default is nullptr.
+     * Similar to @ref ClFillKernel::configure()
      *
      * @return a status
      */
@@ -74,4 +65,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLMEMSETRKERNEL_H */
+#endif /* ARM_COMPUTE_CL_FILL_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClFloorKernel.h b/src/core/gpu/cl/kernels/ClFloorKernel.h
index 3bc648b..57c9906 100644
--- a/src/core/gpu/cl/kernels/ClFloorKernel.h
+++ b/src/core/gpu/cl/kernels/ClFloorKernel.h
@@ -47,11 +47,9 @@
      * @param[out] dst             Destination tensor info. Same as @p src
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref ClFloorKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data type supported: F16/F32.
-     * @param[in] dst Destination tensor info. Same as @p src
+     * Similar to @ref ClFloorKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyNativeKernel.h b/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyNativeKernel.h
index 491c3e4..eaa125f 100644
--- a/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyNativeKernel.h
+++ b/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyNativeKernel.h
@@ -78,4 +78,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_NATIVE_KERNEL_H*/
+#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_NATIVE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedKernel.h b/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedKernel.h
index b99dec3..99cff01 100644
--- a/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedKernel.h
+++ b/src/core/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedKernel.h
@@ -87,4 +87,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_RESHAPED_KERNEL_H*/
+#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_RESHAPED_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h b/src/core/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
index c3bdc75..cd7bf27 100644
--- a/src/core/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
+++ b/src/core/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
@@ -85,4 +85,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_GEMM_MATRIXMULTIPLY_NATIVE_KERNEL_H*/
+#endif /* ARM_COMPUTE_CL_GEMM_MATRIXMULTIPLY_NATIVE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClHeightConcatenateKernel.h b/src/core/gpu/cl/kernels/ClHeightConcatenateKernel.h
index 9a4380a..0733078 100644
--- a/src/core/gpu/cl/kernels/ClHeightConcatenateKernel.h
+++ b/src/core/gpu/cl/kernels/ClHeightConcatenateKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CL_HEIGHT_CONCATENATE_LAYER_KERNEL_H
-#define ARM_COMPUTE_CL_HEIGHT_CONCATENATE_LAYER_KERNEL_H
+#ifndef ARM_COMPUTE_CL_HEIGHT_CONCATENATE_KERNEL_H
+#define ARM_COMPUTE_CL_HEIGHT_CONCATENATE_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/gpu/cl/ClCompileContext.h"
@@ -40,7 +40,6 @@
 class ClHeightConcatenateKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClHeightConcatenateKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClHeightConcatenateKernel);
     /** Initialise the kernel's source and destination
@@ -52,11 +51,9 @@
      *
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int height_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClHeightConcatenateKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src           Source tensor info. Data types supported: All.
-     * @param[in] height_offset The starting offset on the Y axis for the dst tensor.
-     * @param[in] dst           Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClHeightConcatenateKernel::configure()
      *
      * @return a status
      */
@@ -71,4 +68,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_HEIGHT_CONCATENATE_LAYER_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_HEIGHT_CONCATENATE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClMulKernel.h b/src/core/gpu/cl/kernels/ClMulKernel.h
index 9c70301..dec8dba 100644
--- a/src/core/gpu/cl/kernels/ClMulKernel.h
+++ b/src/core/gpu/cl/kernels/ClMulKernel.h
@@ -38,7 +38,6 @@
 class ClMulKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClMulKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClMulKernel);
     /** Initialise the kernel's src and dst.
@@ -87,7 +86,6 @@
 class ClComplexMulKernel : public ICLKernel
 {
 public:
-    /** Default constructor */
     ClComplexMulKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClComplexMulKernel);
     /** Initialise the kernel's src and dst.
diff --git a/src/core/gpu/cl/kernels/ClPermuteKernel.h b/src/core/gpu/cl/kernels/ClPermuteKernel.h
index 326110a..839e224 100644
--- a/src/core/gpu/cl/kernels/ClPermuteKernel.h
+++ b/src/core/gpu/cl/kernels/ClPermuteKernel.h
@@ -41,7 +41,6 @@
 class ClPermuteKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClPermuteKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClPermuteKernel);
     /** Set the src and dst of the kernel.
@@ -54,13 +53,9 @@
      * @param[in] perm            Permutation vector
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const PermutationVector &perm);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClPermuteKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Arbitrary permutation vectors are supported with rank not greater than 4
-     *
-     * @param[in] src  The src tensor info. Data types supported: All.
-     * @param[in] dst  The dst tensor info. Data types supported: same as @p src.
-     * @param[in] perm Permutation vector
+     * Similar to @ref ClPermuteKernel::configure()
      *
      * @return a status
      */
@@ -75,4 +70,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_PERMUTE_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_PERMUTE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClPool2dKernel.cpp b/src/core/gpu/cl/kernels/ClPool2dKernel.cpp
index 9d5a24f..e522814 100644
--- a/src/core/gpu/cl/kernels/ClPool2dKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClPool2dKernel.cpp
@@ -203,7 +203,6 @@
 } // namespace
 
 ClPool2dKernel::ClPool2dKernel()
-    : _pool_info(), _data_layout(DataLayout::UNKNOWN), _border_size(0), _num_elems_processed_per_iteration(1)
 {
     _type = CLKernelType::POOL;
 }
diff --git a/src/core/gpu/cl/kernels/ClPool2dKernel.h b/src/core/gpu/cl/kernels/ClPool2dKernel.h
index 8ecb8eb..ab8c56a 100644
--- a/src/core/gpu/cl/kernels/ClPool2dKernel.h
+++ b/src/core/gpu/cl/kernels/ClPool2dKernel.h
@@ -38,7 +38,6 @@
 class ClPool2dKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClPool2dKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClPool2dKernel);
 
@@ -65,10 +64,10 @@
     BorderSize border_size() const override;
 
 public:
-    PoolingLayerInfo _pool_info;
-    DataLayout       _data_layout;
-    BorderSize       _border_size;
-    unsigned int     _num_elems_processed_per_iteration;
+    PoolingLayerInfo _pool_info{};
+    DataLayout       _data_layout{ DataLayout::UNKNOWN };
+    BorderSize       _border_size{ 0 };
+    unsigned int     _num_elems_processed_per_iteration{ 1 };
 };
 } // namespace kernels
 } // namespace opencl
diff --git a/src/core/gpu/cl/kernels/ClQuantizeKernel.h b/src/core/gpu/cl/kernels/ClQuantizeKernel.h
index cd97298..1991a2f 100644
--- a/src/core/gpu/cl/kernels/ClQuantizeKernel.h
+++ b/src/core/gpu/cl/kernels/ClQuantizeKernel.h
@@ -41,7 +41,6 @@
 class ClQuantizeKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClQuantizeKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClQuantizeKernel);
     /** Set the input, output.
diff --git a/src/core/gpu/cl/kernels/ClReshapeKernel.h b/src/core/gpu/cl/kernels/ClReshapeKernel.h
index 3cd8369..01e1ee8 100644
--- a/src/core/gpu/cl/kernels/ClReshapeKernel.h
+++ b/src/core/gpu/cl/kernels/ClReshapeKernel.h
@@ -47,11 +47,9 @@
      * @param[out] dst             Destination tensor info. Data type supported: Same as @p src
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref ClReshapeKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data type supported: All
-     * @param[in] dst Destination tensor info. Data type supported: Same as @p src
+     * Similar to @ref ClReshapeKernel::configure()
      *
      * @return a status
      */
@@ -63,4 +61,4 @@
 } // namespace opencl
 } // namespace kernels
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_RESHAPE_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_RESHAPE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClScaleKernel.h b/src/core/gpu/cl/kernels/ClScaleKernel.h
index 826c482..8333c7d 100644
--- a/src/core/gpu/cl/kernels/ClScaleKernel.h
+++ b/src/core/gpu/cl/kernels/ClScaleKernel.h
@@ -31,8 +31,6 @@
 
 namespace arm_compute
 {
-class ICLTensor;
-
 namespace opencl
 {
 namespace kernels
@@ -41,10 +39,8 @@
 class ClScaleKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClScaleKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClScaleKernel);
-
     /** Initialise the kernel's inputs, output and interpolation policy
      *
      * @param[in]  compile_context The compile context to be used.
@@ -54,13 +50,9 @@
      * @param[in]  info            @ref ScaleKernelInfo Kernel descriptor to be used to configure.
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, const ScaleKernelInfo &info);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref ClScaleKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src  Source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32
-     * @param[in] dst  Destination tensor info. Data types supported: Same as @p src
-     *                 All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
-     * @param[in] info @ref ScaleKernelInfo Kernel descriptor to be used to validate
+     * Similar to @ref ClScaleKernel::configure()
      *
      * @return a status
      */
@@ -71,9 +63,9 @@
     void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
 
 private:
-    DataLayout _data_layout = DataLayout::UNKNOWN;
+    DataLayout _data_layout{ DataLayout::UNKNOWN };
 };
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLSCALEKERNEL_H */
+#endif /* ARM_COMPUTE_CL_SCALE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClSoftmaxKernel.h b/src/core/gpu/cl/kernels/ClSoftmaxKernel.h
index db1aca3..a2ad02d 100644
--- a/src/core/gpu/cl/kernels/ClSoftmaxKernel.h
+++ b/src/core/gpu/cl/kernels/ClSoftmaxKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CLSOFTMAXLAYERKERNEL_H
-#define ARM_COMPUTE_CLSOFTMAXLAYERKERNEL_H
+#ifndef ARM_COMPUTE_CL_SOFTMAX_KERNEL_H
+#define ARM_COMPUTE_CL_SOFTMAX_KERNEL_H
 
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/KernelDescriptors.h"
@@ -50,7 +50,6 @@
     /** Info for whether a parallel reduction will be run and the vector size of the execution. */
     using ParallelReductionInfo = std::tuple<bool, unsigned int>;
 
-    /** Default constructor */
     ClLogits1DMaxShiftExpSumKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClLogits1DMaxShiftExpSumKernel);
     /** Configure the kernel using the given information about tensors
@@ -63,12 +62,9 @@
      * @param[in]     info            Contains information consumed by kernels for softmax described in @ref SoftmaxKernelInfo.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo &src, ITensorInfo &max, ITensorInfo &dst, ITensorInfo &sum, const SoftmaxKernelInfo &info);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClLogits1DMaxShiftExpSumKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32
-     * @param[in] max Max values tensor. Data types supported: same as @p src
-     * @param[in] dst Destination tensor. Data types supported: same as @p src
-     * @param[in] sum Sum of 1D logits tensor. Data types supported: same as @p src
+     * Similar to @ref ClLogits1DMaxShiftExpSumKernel::configure()
      *
      * @return a status
      */
@@ -93,7 +89,6 @@
 class ClLogits1DNormKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClLogits1DNormKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClLogits1DNormKernel);
 
@@ -106,12 +101,9 @@
      * @param[in]  info            Contains information consumed by kernels for softmax described in @ref SoftmaxKernelInfo.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo &src, const ITensorInfo &sum, ITensorInfo &dst, const SoftmaxKernelInfo &info);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClLogits1DNormKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src  Source tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported.
-     * @param[in] sum  Sum tensor. Dimensions should be dim(input)-1. Data types supported: same as @p input
-     * @param[in] dst  Destination tensor. Data types supported: QASYMM8 for S32 @p input, or same as @p input
-     * @param[in] info Contains information consumed by kernels for softmax described in @ref SoftmaxKernelInfo.
+     * Similar to @ref ClLogits1DNormKernel::configure()
      *
      * @return a status
      */
@@ -123,4 +115,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLSOFTMAXLAYERKERNEL_H */
+#endif /* ARM_COMPUTE_CL_SOFTMAX_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClTransposeKernel.h b/src/core/gpu/cl/kernels/ClTransposeKernel.h
index 7d1226c..c8379d4 100644
--- a/src/core/gpu/cl/kernels/ClTransposeKernel.h
+++ b/src/core/gpu/cl/kernels/ClTransposeKernel.h
@@ -47,10 +47,9 @@
      * @param[in] dst             The dst tensor info. Data types supported: Same as @p src
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClTransposeKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src The src tensor info. Data types supported: All.
-     * @param[in] dst The dst tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClTransposeKernel::configure()
      *
      * @return a status
      */
@@ -62,4 +61,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_TRANSPOSE_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_TRANSPOSE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClWidthConcatenate2TensorsKernel.h b/src/core/gpu/cl/kernels/ClWidthConcatenate2TensorsKernel.h
index 56202ba..15e0757 100644
--- a/src/core/gpu/cl/kernels/ClWidthConcatenate2TensorsKernel.h
+++ b/src/core/gpu/cl/kernels/ClWidthConcatenate2TensorsKernel.h
@@ -40,7 +40,6 @@
 class ClWidthConcatenate2TensorsKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWidthConcatenate2TensorsKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWidthConcatenate2TensorsKernel);
     /** Initialise the kernel's sources and destination
@@ -51,11 +50,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: Same as @p src1.
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClWidthConcatenate2TensorsKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1 First tensor info. Data types supported: All.
-     * @param[in] src2 Second tensor info. Data types supported: same as @p src1
-     * @param[in] dst  Destination tensor info. Data types supported: Same as @p src1.
+     * Similar to @ref ClWidthConcatenate2TensorsKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h b/src/core/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h
index 19bda65..1e3f47f 100644
--- a/src/core/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h
+++ b/src/core/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h
@@ -41,7 +41,6 @@
 class ClWidthConcatenate4TensorsKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWidthConcatenate4TensorsKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWidthConcatenate4TensorsKernel);
     /** Initialise the kernel's sources and destination
@@ -54,13 +53,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src1.
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *src3, ITensorInfo *src4, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClWidthConcatenate4TensorsKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1 First tensor info. Data types supported: All.
-     * @param[in] src2 Second tensor info. Data types supported: same as @p src1
-     * @param[in] src3 Third tensor info. Data types supported: same as @p src1
-     * @param[in] src4 Fourth tensor info. Data types supported: same as @p src1
-     * @param[in] dst  Destination tensor info. Data types supported: same as @p src1.
+     * Similar to @ref ClWidthConcatenate4TensorsKernel::configure()
      *
      * @return a status
      */
diff --git a/src/core/gpu/cl/kernels/ClWidthConcatenateKernel.h b/src/core/gpu/cl/kernels/ClWidthConcatenateKernel.h
index 6bc8e57..300c4be 100644
--- a/src/core/gpu/cl/kernels/ClWidthConcatenateKernel.h
+++ b/src/core/gpu/cl/kernels/ClWidthConcatenateKernel.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CL_WIDTH_CONCATENATE_LAYER_KERNEL_H
-#define ARM_COMPUTE_CL_WIDTH_CONCATENATE_LAYER_KERNEL_H
+#ifndef ARM_COMPUTE_CL_WIDTH_CONCATENATE_KERNEL_H
+#define ARM_COMPUTE_CL_WIDTH_CONCATENATE_KERNEL_H
 
 #include "src/core/common/Macros.h"
 #include "src/core/gpu/cl/ClCompileContext.h"
@@ -40,7 +40,6 @@
 class ClWidthConcatenateKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWidthConcatenateKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWidthConcatenateKernel);
     /** Initialise the kernel's source and destination
@@ -52,11 +51,9 @@
      *
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int width_offset, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref ClWidthConcatenateKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src          Source tensor info. Data types supported: All.
-     * @param[in] width_offset The offset on the X axis.
-     * @param[in] dst          Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClWidthConcatenateKernel::configure()
      *
      * @return a status
      */
@@ -68,4 +65,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_WIDTH_CONCATENATE_LAYER_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_WIDTH_CONCATENATE_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClWinogradFilterTransformKernel.h b/src/core/gpu/cl/kernels/ClWinogradFilterTransformKernel.h
index 13200dc..145954f 100644
--- a/src/core/gpu/cl/kernels/ClWinogradFilterTransformKernel.h
+++ b/src/core/gpu/cl/kernels/ClWinogradFilterTransformKernel.h
@@ -39,7 +39,6 @@
 class ClWinogradFilterTransformKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWinogradFilterTransformKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWinogradFilterTransformKernel);
     /** Set the input and output tensor.
@@ -75,4 +74,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_WINOGRAD_FILTER_TRANSFORM_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_WINOGRAD_FILTER_TRANSFORM_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.cpp b/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.cpp
index 62db228..538d8ae 100644
--- a/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.cpp
@@ -101,7 +101,6 @@
 } // namespace
 
 ClWinogradInputTransformKernel::ClWinogradInputTransformKernel()
-    : _border_size(0), _data_layout(DataLayout::UNKNOWN), _num_tiles_x(0), _num_tiles_y(0), _step_z(1)
 {
     _type = CLKernelType::WINOGRAD;
 }
diff --git a/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.h b/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.h
index 76b4527..40fc2f3 100644
--- a/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.h
+++ b/src/core/gpu/cl/kernels/ClWinogradInputTransformKernel.h
@@ -39,7 +39,6 @@
 class ClWinogradInputTransformKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWinogradInputTransformKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWinogradInputTransformKernel);
     /** Set the input and output of the kernel.
@@ -76,13 +75,13 @@
 private:
     using WinogradKey = std::pair<std::pair<int, int>, std::pair<int, int>>;
 
-    BorderSize   _border_size;
-    DataLayout   _data_layout;
-    int          _num_tiles_x;
-    int          _num_tiles_y;
-    unsigned int _step_z;
+    BorderSize   _border_size{ 0 };
+    DataLayout   _data_layout{ DataLayout::UNKNOWN };
+    int          _num_tiles_x{ 0 };
+    int          _num_tiles_y{ 0 };
+    unsigned int _step_z{ 1 };
 };
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_WINOGRAD_INPUT_TRANSFORM_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_WINOGRAD_INPUT_TRANSFORM_KERNEL_H */
diff --git a/src/core/gpu/cl/kernels/ClWinogradOutputTransformKernel.h b/src/core/gpu/cl/kernels/ClWinogradOutputTransformKernel.h
index 2948d3f..22b7f07 100644
--- a/src/core/gpu/cl/kernels/ClWinogradOutputTransformKernel.h
+++ b/src/core/gpu/cl/kernels/ClWinogradOutputTransformKernel.h
@@ -39,7 +39,6 @@
 class ClWinogradOutputTransformKernel : public IClKernel
 {
 public:
-    /** Default constructor */
     ClWinogradOutputTransformKernel();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWinogradOutputTransformKernel);
     /** Set the input and output tensor.
@@ -64,7 +63,6 @@
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src, ITensorInfo *bias, ITensorInfo *dst, const WinogradInfo &winograd_info,
                    const ActivationLayerInfo &act_info = ActivationLayerInfo());
-
     /** Static function to check if given info will lead to a valid configuration
      *
      * Similar to ClWinogradOutputTransformKernel::configure()
@@ -84,4 +82,4 @@
 } // namespace kernels
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CL_WINOGRAD_OUTPUT_TRANSFORM_KERNEL_H */
+#endif /* ARM_COMPUTE_CL_WINOGRAD_OUTPUT_TRANSFORM_KERNEL_H */
diff --git a/src/runtime/cpu/operators/CpuActivation.h b/src/runtime/cpu/operators/CpuActivation.h
index 0ae16bf..ded4a37 100644
--- a/src/runtime/cpu/operators/CpuActivation.h
+++ b/src/runtime/cpu/operators/CpuActivation.h
@@ -34,8 +34,6 @@
 class CpuActivation : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuActivation() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  input           Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
@@ -43,11 +41,9 @@
      * @param[in]  activation_info Activation layer parameters.
      */
     void configure(const ITensorInfo *input, ITensorInfo *output, const ActivationLayerInfo &activation_info);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuActivation
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] input    Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
-     * @param[in] output   Destination tensor info. Data type supported: same as @p src
-     * @param[in] act_info Activation layer information.
+     * Similar to @ref CpuActivation::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuAdd.h b/src/runtime/cpu/operators/CpuAdd.h
index 8ae7833..febb79e 100644
--- a/src/runtime/cpu/operators/CpuAdd.h
+++ b/src/runtime/cpu/operators/CpuAdd.h
@@ -34,8 +34,6 @@
 class CpuAdd : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuAdd() = default;
     /** Initialise the kernel's input, dst and border mode.
      *
      * Valid configurations (src0,src1) -> dst :
@@ -60,13 +58,9 @@
      *
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuAdd
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src0     First input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in] src1     Second input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in] dst      The dst tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32.
-     * @param[in] policy   Overflow policy.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
+     * Similar to @ref CpuAdd::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuCast.h b/src/runtime/cpu/operators/CpuCast.h
index 2aea2d2..26f5740 100644
--- a/src/runtime/cpu/operators/CpuCast.h
+++ b/src/runtime/cpu/operators/CpuCast.h
@@ -34,8 +34,6 @@
 class CpuCast : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuCast() = default;
     /** Configure operator for a given list of arguments
      *
      * Input data type must be different than output data type.
diff --git a/src/runtime/cpu/operators/CpuConcatenate.cpp b/src/runtime/cpu/operators/CpuConcatenate.cpp
index 23eb3fc..bb475b7 100644
--- a/src/runtime/cpu/operators/CpuConcatenate.cpp
+++ b/src/runtime/cpu/operators/CpuConcatenate.cpp
@@ -42,11 +42,6 @@
 {
 namespace cpu
 {
-CpuConcatenate::CpuConcatenate()
-    : _concat_kernels(), _num_srcs(0), _axis(0)
-{
-}
-
 void CpuConcatenate::configure(const std::vector<const ITensorInfo *> &srcs_vector, ITensorInfo *dst, size_t axis)
 {
     ARM_COMPUTE_ERROR_ON(dst == nullptr);
diff --git a/src/runtime/cpu/operators/CpuConcatenate.h b/src/runtime/cpu/operators/CpuConcatenate.h
index d2af3e2..55eab54 100644
--- a/src/runtime/cpu/operators/CpuConcatenate.h
+++ b/src/runtime/cpu/operators/CpuConcatenate.h
@@ -43,8 +43,7 @@
 class CpuConcatenate : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuConcatenate();
+    CpuConcatenate() = default;
     /** Configure operator for a given list of arguments
      *
      * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis.
@@ -56,15 +55,9 @@
      * @param[in]     axis        Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
      */
     void configure(const std::vector<const ITensorInfo *> &srcs_vector, ITensorInfo *dst, size_t axis);
-    /** Static function to check if given info will lead to a valid configuration of @ref NEConcatenateLayer
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis.
-     * @note Preconditions can be found respectively at @ref kernels::CpuConcatenateWidthKernel, @ref kernels::CpuConcatenateHeightKernel,
-     *       @ref kernels::CpuConcatenateDepthKernel and @ref kernels::CpuConcatenateBatchKernel.
-     *
-     * @param[in] srcs_vector The vectors containing all the tensors info to concatenate. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
-     * @param[in] dst         Output tensor info. Data types supported: Same as @p srcs_vector.
-     * @param[in] axis        Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
+     * Similar to @ref CpuConcatenate::configure()
      *
      * @return a status
      */
@@ -74,9 +67,9 @@
     void run(ITensorPack &tensors) override;
 
 private:
-    std::vector<std::unique_ptr<ICpuKernel>> _concat_kernels;
-    unsigned int                             _num_srcs;
-    unsigned int                             _axis;
+    std::vector<std::unique_ptr<ICpuKernel>> _concat_kernels{};
+    unsigned int                             _num_srcs{ 0 };
+    unsigned int                             _axis{ 0 };
 };
 } // namespace cpu
 } // namespace arm_compute
diff --git a/src/runtime/cpu/operators/CpuConvertFullyConnectedWeights.h b/src/runtime/cpu/operators/CpuConvertFullyConnectedWeights.h
index 3f1ddf1..53ee17f 100644
--- a/src/runtime/cpu/operators/CpuConvertFullyConnectedWeights.h
+++ b/src/runtime/cpu/operators/CpuConvertFullyConnectedWeights.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_H
-#define ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_H
+#ifndef ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_H
+#define ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_H
 
 #include "src/runtime/cpu/ICpuOperator.h"
 
@@ -34,8 +34,6 @@
 class CpuConvertFullyConnectedWeights : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuConvertFullyConnectedWeights() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  src                Source tensor to permute. Data types supported: All
@@ -44,12 +42,9 @@
      * @param[in]  data_layout        The data layout the weights have been trained in.
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_src_shape, DataLayout data_layout);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuConvertFullyConnectedWeights
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src                Source tensor to permute. Data types supported: All
-     * @param[in] dst                Destination tensor. Data types supported: Same as @p dst
-     * @param[in] original_src_shape Shape of the original src tensor (the one entering fully connected layer).
-     * @param[in] data_layout        The data layout the weights have been trained in.
+     * Similar to @ref CpuConvertFullyConnectedWeights::configure()
      *
      * @return a status
      */
@@ -59,4 +54,4 @@
 };
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_CONVERTFULLYCONNECTEDWEIGHTS_H */
+#endif /* ARM_COMPUTE_CPU_CONVERT_FULLYCONNECTED_WEIGHTS_H */
diff --git a/src/runtime/cpu/operators/CpuCopy.h b/src/runtime/cpu/operators/CpuCopy.h
index 057bb6e..861bbb7 100644
--- a/src/runtime/cpu/operators/CpuCopy.h
+++ b/src/runtime/cpu/operators/CpuCopy.h
@@ -34,19 +34,15 @@
 class CpuCopy : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuCopy() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  src Source tensor info. Data type supported: All
      * @param[out] dst Destination info. Data type supported: Same as @p src
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuCopy
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data type supported: All
-     * @param[in] dst Destination tensor info. Data type supported: Same as @p src
+     * Similar to @ref CpuCopy::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuDepthwiseConv2d.cpp b/src/runtime/cpu/operators/CpuDepthwiseConv2d.cpp
index f577e94..8141487 100644
--- a/src/runtime/cpu/operators/CpuDepthwiseConv2d.cpp
+++ b/src/runtime/cpu/operators/CpuDepthwiseConv2d.cpp
@@ -71,12 +71,6 @@
 }
 } // namespace
 
-CpuDepthwiseConv2d::CpuDepthwiseConv2dOptimizedInternal::CpuDepthwiseConv2dOptimizedInternal()
-    : _dwc_optimized_func(nullptr), _permute_input(nullptr), _permute_weights(nullptr), _permute_output(nullptr), _activationlayer_function(nullptr), _has_bias(false), _is_quantized(false),
-      _is_nchw(true), _permute(false), _is_activationlayer_enabled(false), _is_prepared(false)
-{
-}
-
 void CpuDepthwiseConv2d::CpuDepthwiseConv2dOptimizedInternal::configure(ITensorInfo           *src,
                                                                         const ITensorInfo     *weights,
                                                                         const ITensorInfo     *biases,
@@ -264,12 +258,6 @@
     }
 }
 
-CpuDepthwiseConv2d::CpuDepthwiseConv2dGeneric::CpuDepthwiseConv2dGeneric()
-    : _depthwise_conv_kernel(nullptr), _permute_input(nullptr), _permute_weights(nullptr), _permute_output(nullptr), _activationlayer_function(nullptr), _is_nchw(true), _is_prepared(false),
-      _is_activationlayer_enabled(false)
-{
-}
-
 void CpuDepthwiseConv2d::CpuDepthwiseConv2dGeneric::configure(ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, weights, dst);
@@ -432,11 +420,6 @@
     }
 }
 
-CpuDepthwiseConv2d::CpuDepthwiseConv2d()
-    : _depth_conv_func(DepthwiseConvolutionFunction::GENERIC), _func_optimized(), _func_generic()
-{
-}
-
 void CpuDepthwiseConv2d::configure(ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info)
 {
     _depth_conv_func = get_depthwiseconvolution_function(src, weights, (biases != nullptr) ? biases : nullptr, dst, info);
diff --git a/src/runtime/cpu/operators/CpuDepthwiseConv2d.h b/src/runtime/cpu/operators/CpuDepthwiseConv2d.h
index ae9f894..dd4839b 100644
--- a/src/runtime/cpu/operators/CpuDepthwiseConv2d.h
+++ b/src/runtime/cpu/operators/CpuDepthwiseConv2d.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_DEPTHWISECONV2D_H
-#define ARM_COMPUTE_CPU_DEPTHWISECONV2D_H
+#ifndef ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_H
+#define ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_H
 
 #include "arm_compute/core/ITensorInfo.h"
 #include "arm_compute/core/experimental/Types.h"
@@ -45,7 +45,7 @@
 {
 public:
     /** Default constructor */
-    CpuDepthwiseConv2d();
+    CpuDepthwiseConv2d() = default;
     /** Initialize the function's source, destination, weights and convolution information.
      *
      * @param[in, out] src     Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/F16/F32
@@ -57,7 +57,6 @@
      * @param[in]      info    Depthwise convolution meta-data.
      */
     void configure(ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info);
-
     /** Static function to check if given info will lead to a valid configuration
      *
      * Similar to CpuDepthwiseConv2d::configure()
@@ -65,7 +64,6 @@
      * @return a status
      */
     static Status validate(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *dst, const ConvolutionInfo &info);
-
     /** Static function to choose the best depthwise convolution function for @ref CpuDepthwiseConv2d
      *
      * @param[in] src     Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/F16/F32
@@ -100,7 +98,7 @@
     {
     public:
         /** Default constructor */
-        CpuDepthwiseConv2dOptimizedInternal();
+        CpuDepthwiseConv2dOptimizedInternal() = default;
         /** Prevent instances of this class from being copied (As this class contains pointers) */
         CpuDepthwiseConv2dOptimizedInternal(const CpuDepthwiseConv2dOptimizedInternal &) = delete;
         /** Default move constructor */
@@ -121,7 +119,6 @@
          * @param[in]      info    Depthwise convolution meta-data.
          */
         void configure(ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, ITensorInfo *dst, const ConvolutionInfo &info);
-
         /** Static function to check if given info will lead to a valid configuration
          *
          * Similar to CpuDepthwiseConv2dOptimizedInternal::configure()
@@ -157,7 +154,7 @@
     {
     public:
         /** Default constructor */
-        CpuDepthwiseConv2dGeneric();
+        CpuDepthwiseConv2dGeneric() = default;
         /** Prevent instances of this class from being copied (As this class contains pointers) */
         CpuDepthwiseConv2dGeneric(const CpuDepthwiseConv2dGeneric &) = delete;
         /** Default move constructor */
@@ -203,10 +200,10 @@
         bool                                                     _is_activationlayer_enabled{ false };
     };
 
-    DepthwiseConvolutionFunction        _depth_conv_func;
-    CpuDepthwiseConv2dOptimizedInternal _func_optimized;
-    CpuDepthwiseConv2dGeneric           _func_generic;
+    DepthwiseConvolutionFunction        _depth_conv_func{ DepthwiseConvolutionFunction::GENERIC };
+    CpuDepthwiseConv2dOptimizedInternal _func_optimized{};
+    CpuDepthwiseConv2dGeneric           _func_generic{};
 };
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_DEPTHWISECONV2D_H */
+#endif /* ARM_COMPUTE_CPU_DEPTHWISE_CONV2D_H */
diff --git a/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h b/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
index 7084516..f3d3b61 100644
--- a/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
+++ b/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
@@ -35,10 +35,8 @@
 class CpuDepthwiseConv2dAssemblyDispatch : public ICpuOperator
 {
 public:
-    /** Default constructor */
     CpuDepthwiseConv2dAssemblyDispatch();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDepthwiseConv2dAssemblyDispatch);
-    /** Default destructor */
     ~CpuDepthwiseConv2dAssemblyDispatch();
     /** Initialize the function's source, destination, kernels and border_size.
      *
@@ -67,6 +65,7 @@
      * @return True if activation is supported else false
      */
     static bool is_activation_supported(const ActivationLayerInfo &activation);
+
     // Inherited methods overridden:
     void run(ITensorPack &tensors) override;
     void prepare(ITensorPack &tensors) override;
diff --git a/src/runtime/cpu/operators/CpuDequantize.h b/src/runtime/cpu/operators/CpuDequantize.h
index d1fb9e8..fdbd6a5 100644
--- a/src/runtime/cpu/operators/CpuDequantize.h
+++ b/src/runtime/cpu/operators/CpuDequantize.h
@@ -34,8 +34,6 @@
 class CpuDequantize : public ICpuOperator
 {
 public:
-    /** Default Constructor */
-    CpuDequantize() = default;
     /** Configure the kernel.
      *
      * @param[in]  src Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/QSYMM8/QSYMM16.
diff --git a/src/runtime/cpu/operators/CpuDirectConv2d.h b/src/runtime/cpu/operators/CpuDirectConv2d.h
index 9e584b9..c17b076 100644
--- a/src/runtime/cpu/operators/CpuDirectConv2d.h
+++ b/src/runtime/cpu/operators/CpuDirectConv2d.h
@@ -55,9 +55,7 @@
 class CpuDirectConv2d : public ICpuOperator
 {
 public:
-    /** Constructor */
     CpuDirectConv2d(std::shared_ptr<IMemoryManager> memory_manager = nullptr);
-    /** Destructor */
     ~CpuDirectConv2d();
     /** Set the input, weights, biases and output tensors.
      *
diff --git a/src/runtime/cpu/operators/CpuElementwise.h b/src/runtime/cpu/operators/CpuElementwise.h
index 899a2ff..ef5caf2 100644
--- a/src/runtime/cpu/operators/CpuElementwise.h
+++ b/src/runtime/cpu/operators/CpuElementwise.h
@@ -52,13 +52,11 @@
      * @param[out] dst  The output tensor information.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst);
-    /** Static function to check if the given information will lead to a valid configuration
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in]  src0 The first source tensor information.
-     * @param[in]  src1 The second source tensor information. With PRelu, this is used as alpha tensor.
-     * @param[out] dst  The output tensor information.
+     * Similar to @ref CpuElementwiseArithmetic::configure()
      *
-     * @return A status
+     * @return a status
      */
     static Status validate(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst);
 };
@@ -85,11 +83,9 @@
      * @param[out]     dst  Output tensor info. Data types supported: Same as @p src0.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref cpu::kernels::CpuArithmeticKernel for division
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src0 First tensor input info. Data types supported: S32/F16/F32.
-     * @param[in] src1 Second tensor input info. Data types supported: Same as @p src0.
-     * @param[in] dst  Output tensor info. Data types supported: Same as @p src0.
+     * Similar to @ref CpuElementwiseDivision::configure()
      *
      * @return a status
      */
@@ -112,11 +108,9 @@
      * @param[out]     dst  Output tensor info. Data types supported: Same as @p src0.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref cpu::kernels::CpuArithmeticKernel for power
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src0 First tensor input info. Data types supported: F16/F32.
-     * @param[in] src1 Second tensor input info. Data types supported: Same as @p src0.
-     * @param[in] dst  Output tensor info. Data types supported: Same as @p src0.
+     * Similar to @ref CpuElementwisePower::configure()
      *
      * @return a status
      */
@@ -139,12 +133,9 @@
      * @param[in]      op   Comparison Operation to be performed.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst, ComparisonOperation op);
-    /** Static function to check if given info will lead to a valid configuration of @ref cpu::kernels::CpuComparisonKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src0 First tensor input info. Data types supported: QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32.
-     * @param[in] src1 Second tensor input info. Data types supported: Same as @p src0.
-     * @param[in] dst  Output tensor info. Data types supported: U16/U32.
-     * @param[in] op   Comparison Operation to be performed.
+     * Similar to @ref CpuElementwiseComparison::configure()
      *
      * @return a status
      */
@@ -167,11 +158,9 @@
      * @param[out]     dst  Output tensor info. Data types supported: U16/U32.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref cpu::kernels::CpuComparisonKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src0 First tensor input info. Data types supported: QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32.
-     * @param[in] src1 Second tensor input info. Data types supported: Same as @p src0.
-     * @param[in] dst  Output tensor info. Data types supported: U16/U32.
+     * Similar to @ref CpuElementwiseComparisonStatic::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuElementwiseUnary.h b/src/runtime/cpu/operators/CpuElementwiseUnary.h
index 721ba2a..5ea29e0 100644
--- a/src/runtime/cpu/operators/CpuElementwiseUnary.h
+++ b/src/runtime/cpu/operators/CpuElementwiseUnary.h
@@ -43,9 +43,7 @@
     void configure(ElementWiseUnary op, const ITensorInfo &src, ITensorInfo &dst);
     /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] op  Unary operation to execute
-     * @param[in] src First tensor input info. Data types supported: F16/F32, F16/F32/S32 for NEG/ABS operations.
-     * @param[in] dst Output tensor info. Data types supported: Same as @p input.
+     * Similar to @ref CpuElementwiseUnary::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuFill.h b/src/runtime/cpu/operators/CpuFill.h
index fac8e76..b946467 100644
--- a/src/runtime/cpu/operators/CpuFill.h
+++ b/src/runtime/cpu/operators/CpuFill.h
@@ -34,8 +34,6 @@
 class CpuFill : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuFill() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in,out] tensor         Tensor to fill. Supported data types: All
diff --git a/src/runtime/cpu/operators/CpuFlatten.h b/src/runtime/cpu/operators/CpuFlatten.h
index ae71453..3e24a93 100644
--- a/src/runtime/cpu/operators/CpuFlatten.h
+++ b/src/runtime/cpu/operators/CpuFlatten.h
@@ -34,8 +34,6 @@
 class CpuFlatten : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuFlatten() = default;
     /** Configure operator for a given list of arguments
      *
      * Valid data layouts:
diff --git a/src/runtime/cpu/operators/CpuFloor.h b/src/runtime/cpu/operators/CpuFloor.h
index cbb9d56..0cd0cc0 100644
--- a/src/runtime/cpu/operators/CpuFloor.h
+++ b/src/runtime/cpu/operators/CpuFloor.h
@@ -34,18 +34,15 @@
 class CpuFloor : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuFloor() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in] src Source tensor info. Data types supported: F16/F32.
      * @param[in] dst Destination tensor info. Data type supported: same as @p src
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuFloor
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data type supported: same as @p src
+     * Similar to @ref CpuFloor::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuGemmDirectConv2d.h b/src/runtime/cpu/operators/CpuGemmDirectConv2d.h
index b572f36..7fb20b3 100644
--- a/src/runtime/cpu/operators/CpuGemmDirectConv2d.h
+++ b/src/runtime/cpu/operators/CpuGemmDirectConv2d.h
@@ -41,10 +41,8 @@
 class CpuGemmDirectConv2d : public ICpuOperator
 {
 public:
-    /** Constructor */
     CpuGemmDirectConv2d();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmDirectConv2d);
-    /** Destructor */
     ~CpuGemmDirectConv2d();
     /** Set the input and output tensors.
      *
diff --git a/src/runtime/cpu/operators/CpuGemmLowpOutputStage.h b/src/runtime/cpu/operators/CpuGemmLowpOutputStage.h
index 848aaea..bed88a6 100644
--- a/src/runtime/cpu/operators/CpuGemmLowpOutputStage.h
+++ b/src/runtime/cpu/operators/CpuGemmLowpOutputStage.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CPU_GEMMLOWP_OUTPUTSTAGE_H
-#define ARM_COMPUTE_CPU_GEMMLOWP_OUTPUTSTAGE_H
+#ifndef ARM_COMPUTE_CPU_GEMMLOWP_OUTPUT_STAGE_H
+#define ARM_COMPUTE_CPU_GEMMLOWP_OUTPUT_STAGE_H
 
 #include "arm_compute/core/Types.h"
 #include "src/runtime/cpu/ICpuOperator.h"
@@ -51,10 +51,6 @@
 class CpuGemmLowpOutputStage : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuGemmLowpOutputStage() = default;
-    /** Default destructor */
-    ~CpuGemmLowpOutputStage() = default;
     /** Initialise the kernel's inputs, output
      *
      * Valid data layouts:
@@ -87,4 +83,4 @@
 };
 } // namespace cpu
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CPU_GEMMLOWP_OUTPUTSTAGE_H */
+#endif /* ARM_COMPUTE_CPU_GEMMLOWP_OUTPUT_STAGE_H */
diff --git a/src/runtime/cpu/operators/CpuMul.h b/src/runtime/cpu/operators/CpuMul.h
index 6e71718..da518c4 100644
--- a/src/runtime/cpu/operators/CpuMul.h
+++ b/src/runtime/cpu/operators/CpuMul.h
@@ -35,8 +35,6 @@
 class CpuMul : public ICpuOperator
 {
 public:
-    /** Default Constructor */
-    CpuMul() = default;
     /** Initialise the kernel's inputs, dst and convertion policy.
      *
      * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
@@ -81,8 +79,6 @@
 class CpuComplexMul : public ICpuOperator
 {
 public:
-    /** Default Constructor */
-    CpuComplexMul() = default;
     /** Initialise the kernel's inputs, dst.
      *
      * @param[in, out] src1     First input tensor. Data types supported: F32. Number of channels supported: 2 (complex tensor).
diff --git a/src/runtime/cpu/operators/CpuPermute.h b/src/runtime/cpu/operators/CpuPermute.h
index 2b30d7f..2500017 100644
--- a/src/runtime/cpu/operators/CpuPermute.h
+++ b/src/runtime/cpu/operators/CpuPermute.h
@@ -34,8 +34,6 @@
 class CpuPermute : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuPermute() = default;
     /** Configure operator for a given list of arguments
      *
      * @note Arbitrary permutation vectors are supported with rank not greater than 4
@@ -45,13 +43,9 @@
      * @param[in]  perm Permutation vector
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, const PermutationVector &perm);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuPermute
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Arbitrary permutation vectors are supported with rank not greater than 4
-     *
-     * @param[in] src  Source tensor to permute. Data types supported: All
-     * @param[in] dst  Destination tensor. Data types supported: Same as @p dst
-     * @param[in] perm Permutation vector
+     * Similar to @ref CpuPermute::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuPool2d.h b/src/runtime/cpu/operators/CpuPool2d.h
index 68416b5..7feff91 100644
--- a/src/runtime/cpu/operators/CpuPool2d.h
+++ b/src/runtime/cpu/operators/CpuPool2d.h
@@ -46,10 +46,8 @@
 class CpuPool2d : public ICpuOperator
 {
 public:
-    /** Constructor */
     CpuPool2d();
     ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuPool2d);
-    /** Default destructor */
     ~CpuPool2d();
     /** Set the src and dst tensors.
      *
diff --git a/src/runtime/cpu/operators/CpuQuantize.h b/src/runtime/cpu/operators/CpuQuantize.h
index 09afffd..9a34a36 100644
--- a/src/runtime/cpu/operators/CpuQuantize.h
+++ b/src/runtime/cpu/operators/CpuQuantize.h
@@ -34,8 +34,6 @@
 class CpuQuantize : public ICpuOperator
 {
 public:
-    /** Default Constructor */
-    CpuQuantize() = default;
     /** Set the input and output tensors.
      *
      * @param[in]  src Source tensor info. The dimensions over the third will be interpreted as batches. Data types supported: QASYMM8/QASYMM8_SIGNED/F32/F16.
diff --git a/src/runtime/cpu/operators/CpuReshape.h b/src/runtime/cpu/operators/CpuReshape.h
index e136043..581b55e 100644
--- a/src/runtime/cpu/operators/CpuReshape.h
+++ b/src/runtime/cpu/operators/CpuReshape.h
@@ -34,19 +34,15 @@
 class CpuReshape : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuReshape() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  src Source tensor info. Data type supported: All
      * @param[out] dst Destination info. Data type supported: Same as @p src
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuReshape
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data type supported: All
-     * @param[in] dst Destination tensor info. Data type supported: Same as @p src
+     * Similar to @ref CpuReshape::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuScale.cpp b/src/runtime/cpu/operators/CpuScale.cpp
index 681a15e..475cb2d 100644
--- a/src/runtime/cpu/operators/CpuScale.cpp
+++ b/src/runtime/cpu/operators/CpuScale.cpp
@@ -86,22 +86,18 @@
 }
 } // namespace
 
-CpuScale::CpuScale()
-    : _scale_info(InterpolationPolicy::NEAREST_NEIGHBOR, BorderMode::UNDEFINED), _data_layout(DataLayout::UNKNOWN), _is_prepared(false)
-{
-}
-
 void CpuScale::configure(ITensorInfo *src, ITensorInfo *dst, const ScaleKernelInfo &info)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
     ARM_COMPUTE_ERROR_THROW_ON(CpuScale::validate(src, dst, info));
 
-    _scale_info = info;
+    _scale_info  = info;
+    _is_prepared = false;
 
     // Get data layout and width/height indices
-    _data_layout = _scale_info.data_layout == DataLayout::UNKNOWN ? src->data_layout() : _scale_info.data_layout;
-    const int        idx_width   = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::WIDTH);
-    const int        idx_height  = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::HEIGHT);
+    _data_layout         = _scale_info.data_layout == DataLayout::UNKNOWN ? src->data_layout() : _scale_info.data_layout;
+    const int idx_width  = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::WIDTH);
+    const int idx_height = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::HEIGHT);
 
     // Compute the ratio between source width/height and destination width/height
     const bool is_align_corners_used = _scale_info.align_corners && arm_compute::scale_utils::is_align_corners_allowed_sampling_policy(_scale_info.sampling_policy);
@@ -205,8 +201,8 @@
         auto       offsets = tensors.get_tensor(TensorType::ACL_INT_2);
 
         // Get data layout and width/height indices
-        const int        idx_width   = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::WIDTH);
-        const int        idx_height  = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::HEIGHT);
+        const int idx_width  = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::WIDTH);
+        const int idx_height = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::HEIGHT);
 
         // Compute the ratio between source width/height and destination width/height
         const bool is_align_corners_used = _scale_info.align_corners && arm_compute::scale_utils::is_align_corners_allowed_sampling_policy(_scale_info.sampling_policy);
diff --git a/src/runtime/cpu/operators/CpuScale.h b/src/runtime/cpu/operators/CpuScale.h
index 90248a8..b83e04b 100644
--- a/src/runtime/cpu/operators/CpuScale.h
+++ b/src/runtime/cpu/operators/CpuScale.h
@@ -40,8 +40,6 @@
 class CpuScale : public ICpuOperator
 {
 public:
-    /** Default Constructor */
-    CpuScale();
     /** Initialize the function's source, destination, interpolation type and border_mode.
      *
      * @param[in, out] src  Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/U8/S16/F16/F32. (Written to only for @p border_mode != UNDEFINED)
@@ -49,11 +47,9 @@
      * @param[in]      info @ref ScaleKernelInfo to be used for configuration
      */
     void configure(ITensorInfo *src, ITensorInfo *dst, const ScaleKernelInfo &info);
-    /** Static function to check if given info will lead to a valid configuration of @ref NEScale
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src  Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/U8/S16/F16/F32. (Written to only for @p border_mode != UNDEFINED)
-     * @param[in] dst  Destination tensor info. Data type supported: Same as @p src. All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
-     * @param[in] info @ref ScaleKernelInfo to be used for validation
+     * Similar to @ref CpuScale::configure()
      *
      * @return a status
      */
@@ -64,10 +60,10 @@
     void run(ITensorPack &tensors) override;
 
 private:
-    ScaleKernelInfo _scale_info;
-    DataLayout      _data_layout;
-    bool            _is_prepared;
+    ScaleKernelInfo _scale_info{ InterpolationPolicy::NEAREST_NEIGHBOR, BorderMode::UNDEFINED };
+    DataLayout      _data_layout{ DataLayout::UNKNOWN };
+    bool            _is_prepared{ false };
 };
 } // namespace cpu
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CPU_SCALE_H */
+#endif /* ARM_COMPUTE_CPU_SCALE_H */
diff --git a/src/runtime/cpu/operators/CpuSoftmax.h b/src/runtime/cpu/operators/CpuSoftmax.h
index 3881797..a9ac803 100644
--- a/src/runtime/cpu/operators/CpuSoftmax.h
+++ b/src/runtime/cpu/operators/CpuSoftmax.h
@@ -57,7 +57,6 @@
 class CpuSoftmaxGeneric : public ICpuOperator
 {
 public:
-    /** Constructor */
     CpuSoftmaxGeneric();
     /** Set the input and output tensors.
      *
@@ -69,14 +68,9 @@
      *                       axis=1, softmax will be applied to 4x6=24 vectors of size 5. Defaults to 0
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst, float beta = 1.0f, int32_t axis = 0);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuSoftmax
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src  Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
-     * @param[in] dst  Destination tensor info. Data types supported: same as @p input
-     * @param[in] beta (Optional) A scaling factor for the exponent.
-     * @param[in] axis (Optional) The dimension in which to apply the function. E.g. for input of shape 4x5x6 and
-     *                       axis=1, softmax will be applied to 4x6=24 vectors of size 5. Defaults to 0
+     * Similar to @ref CpuSoftmaxGeneric::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuSub.h b/src/runtime/cpu/operators/CpuSub.h
index 099ffef..aad01fe 100644
--- a/src/runtime/cpu/operators/CpuSub.h
+++ b/src/runtime/cpu/operators/CpuSub.h
@@ -56,26 +56,9 @@
      * @param[in]  act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
      */
     void configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuSub
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * Valid configurations (src0,src1) -> dst :
-     *
-     *   - (U8,U8)                          -> U8
-     *   - (U8,U8)                          -> S16
-     *   - (QASYMM8, QASYMM8)               -> QASYMM8
-     *   - (QASYMM8_SIGNED, QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (S16,U8)                         -> S16
-     *   - (U8,S16)                         -> S16
-     *   - (S16,S16)                        -> S16
-     *   - (S32,S32)                        -> S32
-     *   - (F16,F16)                        -> F16
-     *   - (F32,F32)                        -> F32
-     *
-     * @param[in] src0     First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/S32/F16/F32
-     * @param[in] src1     Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/S32/F16/F32
-     * @param[in] dst      Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/S32/F16/F32
-     * @param[in] policy   Policy to use to handle overflow. Convert policy cannot be WRAP if datatype is quantized.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
+     * Similar to @ref CpuSub::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/cpu/operators/CpuTranspose.h b/src/runtime/cpu/operators/CpuTranspose.h
index c0232dd..0735924 100644
--- a/src/runtime/cpu/operators/CpuTranspose.h
+++ b/src/runtime/cpu/operators/CpuTranspose.h
@@ -34,18 +34,15 @@
 class CpuTranspose : public ICpuOperator
 {
 public:
-    /** Constructor */
-    CpuTranspose() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  src Source tensor to permute. Data types supported: All
      * @param[out] dst Destintation tensor. Data types supported: Same as @p src
      */
     void configure(const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref CpuTranspose
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor to permute. Data types supported: All
-     * @param[in] dst Destination tensor. Data types supported: Same as @p dst
+     * Similar to @ref CpuTranspose::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClActivation.h b/src/runtime/gpu/cl/operators/ClActivation.h
index 235b826..82ef8ac 100644
--- a/src/runtime/gpu/cl/operators/ClActivation.h
+++ b/src/runtime/gpu/cl/operators/ClActivation.h
@@ -35,8 +35,6 @@
 class ClActivation : public IClOperator
 {
 public:
-    /** Constructor */
-    ClActivation() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  compile_context The compile context to be used.
@@ -45,11 +43,9 @@
      * @param[in]  activation_info Activation layer parameters.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, const ActivationLayerInfo &activation_info);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClActivation
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src      Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
-     * @param[in] dst      Destination tensor info. Data type supported: same as @p src
-     * @param[in] act_info Activation layer information.
+     * Similar to @ref ClActivation::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClAdd.h b/src/runtime/gpu/cl/operators/ClAdd.h
index f751d8d..7b84a76 100644
--- a/src/runtime/gpu/cl/operators/ClAdd.h
+++ b/src/runtime/gpu/cl/operators/ClAdd.h
@@ -39,8 +39,6 @@
 class ClAdd : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClAdd() = default;
     /** Configure function for a given list of arguments.
      *
      * Valid configurations (src1,src2) -> dst :
@@ -68,27 +66,9 @@
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, ConvertPolicy policy,
                    const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref ClAdd
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * Valid configurations (src1,src2) -> dst :
-     *
-     *   - (U8,U8)           -> U8
-     *   - (U8,U8)           -> S16
-     *   - (S16,U8)          -> S16
-     *   - (U8,S16)          -> S16
-     *   - (S16,S16)         -> S16
-     *   - (S32,S32)         -> S32
-     *   - (F16,F16)         -> F16
-     *   - (F32,F32)         -> F32
-     *   - (QASYMM8,QASYMM8) -> QASYMM8
-     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (QSYMM16,QSYMM16) -> QSYMM16
-     *
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] dst      Destination tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] policy   Policy to use to handle overflow.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClAdd::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClCast.h b/src/runtime/gpu/cl/operators/ClCast.h
index 69e028d..107eb2b 100644
--- a/src/runtime/gpu/cl/operators/ClCast.h
+++ b/src/runtime/gpu/cl/operators/ClCast.h
@@ -35,8 +35,6 @@
 class ClCast : public IClOperator
 {
 public:
-    /** Constructor */
-    ClCast() = default;
     /** Configure operator for a given list of arguments
      *
      * @note Input data type must be different than output data type.
diff --git a/src/runtime/gpu/cl/operators/ClConcatenate.cpp b/src/runtime/gpu/cl/operators/ClConcatenate.cpp
index 4385fcf..d3c05ea 100644
--- a/src/runtime/gpu/cl/operators/ClConcatenate.cpp
+++ b/src/runtime/gpu/cl/operators/ClConcatenate.cpp
@@ -42,13 +42,6 @@
 {
 namespace opencl
 {
-ClConcatenate::ClConcatenate()
-    : _concat_kernels(),
-      _num_inputs(0),
-      _axis(Window::DimX)
-{
-}
-
 void ClConcatenate::configure(const CLCompileContext &compile_context, const std::vector<ITensorInfo *> &src_vector, ITensorInfo *dst, size_t axis)
 {
     ARM_COMPUTE_ERROR_ON(dst == nullptr);
diff --git a/src/runtime/gpu/cl/operators/ClConcatenate.h b/src/runtime/gpu/cl/operators/ClConcatenate.h
index 0d960a6..fb1235b 100644
--- a/src/runtime/gpu/cl/operators/ClConcatenate.h
+++ b/src/runtime/gpu/cl/operators/ClConcatenate.h
@@ -44,8 +44,7 @@
 class ClConcatenate : public IClOperator
 {
 public:
-    /** Default constructor */
-    ClConcatenate();
+    ClConcatenate() = default;
     /** Initialise the kernel's inputs vector and dst.
      *
      * @note Input and dst tensor dimensions preconditions defer depending on the concatenation axis.
@@ -59,15 +58,9 @@
      * @param[in]     axis            Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
      */
     void configure(const ClCompileContext &compile_context, const std::vector<ITensorInfo *> &src_vector, ITensorInfo *dst, size_t axis);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClConcatenate
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Input and dst tensor dimensions preconditions defer depending on the concatenation axis.
-     * @note Preconditions can be found respectively at @ref kernels::ClWidthConcatenateKernel,
-     *       @ref kernels::ClHeightConcatenateKernel and @ref kernels::ClDepthConcatenateKernel.
-     *
-     * @param[in] src_vector The vectors containing all the tensors info to concatenate. Data types supported: All
-     * @param[in] dst        Destination tensor info. Data types supported: same as @p src_vector.
-     * @param[in] axis       Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
+     * Similar to @ref ClConcatenate::configure()
      *
      * @return a status
      */
@@ -77,9 +70,9 @@
     void run(ITensorPack &tensors) override;
 
 private:
-    std::vector<std::unique_ptr<IClKernel>> _concat_kernels;
-    unsigned int                            _num_inputs;
-    unsigned int                            _axis;
+    std::vector<std::unique_ptr<IClKernel>> _concat_kernels{};
+    unsigned int                            _num_inputs{ 0 };
+    unsigned int                            _axis{ 0 };
 };
 } // namespace opencl
 } // namespace arm_comPUTE
diff --git a/src/runtime/gpu/cl/operators/ClConvertFullyConnectedWeights.h b/src/runtime/gpu/cl/operators/ClConvertFullyConnectedWeights.h
index efedc2f..7ea35c5 100644
--- a/src/runtime/gpu/cl/operators/ClConvertFullyConnectedWeights.h
+++ b/src/runtime/gpu/cl/operators/ClConvertFullyConnectedWeights.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CL_CONVERTFULLYCONNECTEDWEIGHTS_H
-#define ARM_COMPUTE_CL_CONVERTFULLYCONNECTEDWEIGHTS_H
+#ifndef ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_H
+#define ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_H
 
 #include "src/core/gpu/cl/ClCompileContext.h"
 #include "src/runtime/gpu/cl/IClOperator.h"
@@ -35,8 +35,6 @@
 class ClConvertFullyConnectedWeights : public IClOperator
 {
 public:
-    /** Constructor */
-    ClConvertFullyConnectedWeights() = default;
     /** Initialise the kernel's inputs and outputs
      *
      * @param[in] compile_context    The compile context to be used.
@@ -46,12 +44,9 @@
      * @param[in] data_layout        The data layout the weights have been trained in.
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_src_shape, DataLayout data_layout);
-    /**  Static function to check if given info will lead to a valid configuration of @ref kernels::ClConvertFullyConnectedWeightsKernel.
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src                First tensor src info. Data types supported: All.
-     * @param[in] dst                Output tensor info. Data types supported: same as @p src.
-     * @param[in] original_src_shape Shape of the original src tensor (the one entering fully connected layer).
-     * @param[in] data_layout        The data layout the weights have been trained in.
+     * Similar to @ref ClConvertFullyConnectedWeights::configure()
      *
      * @return a status
      */
@@ -59,4 +54,4 @@
 };
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_CONVERTFULLYCONNECTEDWEIGHTS_H */
+#endif /* ARM_COMPUTE_CL_CONVERT_FULLYCONNECTED_WEIGHTS_H */
diff --git a/src/runtime/gpu/cl/operators/ClCopy.h b/src/runtime/gpu/cl/operators/ClCopy.h
index 0b99676..e8ea812 100644
--- a/src/runtime/gpu/cl/operators/ClCopy.h
+++ b/src/runtime/gpu/cl/operators/ClCopy.h
@@ -36,8 +36,6 @@
 class ClCopy : public IClOperator
 {
 public:
-    /** Constructor */
-    ClCopy() = default;
     /** Initialise the function's source and destination.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -47,11 +45,9 @@
      *
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, Window *dst_window = nullptr);
-    /** Static function to check if given info will lead to a valid configuration of @ref kernels::ClCopyKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src        Source tensor info. Data types supported: All.
-     * @param[in] dst        Output tensor info. Data types supported: Same as @p src.
-     * @param[in] dst_window (Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.
+     * Similar to @ref ClCopy::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClCrop.h b/src/runtime/gpu/cl/operators/ClCrop.h
index acfbf14..cca69d6 100644
--- a/src/runtime/gpu/cl/operators/ClCrop.h
+++ b/src/runtime/gpu/cl/operators/ClCrop.h
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CL_COPY_H
-#define ARM_COMPUTE_CL_COPY_H
+#ifndef ARM_COMPUTE_CL_CROP_H
+#define ARM_COMPUTE_CL_CROP_H
 
 #include "arm_compute/core/Window.h"
 #include "src/core/gpu/cl/ClCompileContext.h"
@@ -36,8 +36,6 @@
 class ClCrop : public IClOperator
 {
 public:
-    /** Constructor */
-    ClCrop() = default;
     /** Initialise the function's source and destination.
      *
      * @note Supported tensor rank: up to 4
@@ -53,22 +51,15 @@
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value = 0,
                    Window *dst_window = nullptr);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref kernels::ClCropKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Supported tensor rank: up to 4
+     * Similar to @ref ClCrop::configure()
      *
-     * @param[in] src                 Source tensor info. Data type supported: All. Data layouts supported: NHWC.
-     * @param[in] dst                 Destination tensor info. Data type supported: F32
-     * @param[in] start               Coordinates of where to start cropping the image.
-     * @param[in] end                 Coordinates of where to end cropping the image.
-     * @param[in] batch_index         Fourth dimension index of the 3D image to crop in @p src.
-     * @param[in] extrapolation_value Value to be used for values outside of the image. Default is 0.
-     * @param[in] dst_window          Output window to be used in case cropped image is being copied into a tensor. Default is nullptr.
+     * @return a status
      */
     static Status validate(const ITensorInfo *src, const ITensorInfo *dst, Coordinates2D start, Coordinates2D end, uint32_t batch_index, float extrapolation_value = 0,
                            Window *dst_window = nullptr);
 };
 } // namespace opencl
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CL_COPY_H */
+#endif /* ARM_COMPUTE_CL_CROP_H */
diff --git a/src/runtime/gpu/cl/operators/ClDequantize.h b/src/runtime/gpu/cl/operators/ClDequantize.h
index 47fad3e..5bcdcb2 100644
--- a/src/runtime/gpu/cl/operators/ClDequantize.h
+++ b/src/runtime/gpu/cl/operators/ClDequantize.h
@@ -35,8 +35,6 @@
 class ClDequantize : public IClOperator
 {
 public:
-    /** Constructor */
-    ClDequantize() = default;
     /** Set the input and output tensors.
      *
      * @param[in]  compile_context The compile context to be used.
diff --git a/src/runtime/gpu/cl/operators/ClDirectConv2d.h b/src/runtime/gpu/cl/operators/ClDirectConv2d.h
index e069733..a2785b5 100644
--- a/src/runtime/gpu/cl/operators/ClDirectConv2d.h
+++ b/src/runtime/gpu/cl/operators/ClDirectConv2d.h
@@ -42,7 +42,6 @@
 class ClDirectConv2d : public IClOperator
 {
 public:
-    /** Constructor */
     ClDirectConv2d() = default;
     /** Set the src and dst tensors.
      *
diff --git a/src/runtime/gpu/cl/operators/ClElementwiseOperations.h b/src/runtime/gpu/cl/operators/ClElementwiseOperations.h
index b9ab140..c01b107 100644
--- a/src/runtime/gpu/cl/operators/ClElementwiseOperations.h
+++ b/src/runtime/gpu/cl/operators/ClElementwiseOperations.h
@@ -39,8 +39,6 @@
 class ClElementwiseDivision : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClElementwiseDivision() = default;
     /** Configure function for a given list of arguments.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -50,12 +48,9 @@
      * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref ClElementwiseDivision
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1     First source tensor info. Data types supported: F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst      Destination tensor info. Data types supported: same as @p src1.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClElementwiseDivision::configure()
      *
      * @return a status
      */
@@ -70,8 +65,6 @@
 class ClElementwiseMax : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClElementwiseMax() = default;
     /** Configure function for a given list of arguments.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -81,12 +74,9 @@
      * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref opencl::kernels::ClArithmeticKernel for max
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst      Destination tensor info. Data types supported: same as @p src1.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClElementwiseMax::configure()
      *
      * @return a status
      */
@@ -101,8 +91,6 @@
 class ClElementwiseMin : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClElementwiseMin() = default;
     /** Configure function for a given list of arguments.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -112,12 +100,9 @@
      * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref opencl::kernels::ClArithmeticKernel for min
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst      Destination tensor info. Data types supported: same as @p src1.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClElementwiseMin::configure()
      *
      * @return a status
      */
@@ -132,8 +117,6 @@
 class ClElementwiseSquaredDiff : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClElementwiseSquaredDiff() = default;
     /** Configure function for a given list of arguments.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -143,12 +126,9 @@
      * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref opencl::kernels::ClArithmeticKernel for squared difference
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: same as @p src1.
-     * @param[in] dst      Destination tensor info. Data types supported: same as @p src1.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClElementwiseSquaredDiff::configure()
      *
      * @return a status
      */
@@ -163,8 +143,6 @@
 class ClElementwisePower : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClElementwisePower() = default;
     /** Configure function for a given list of arguments.
      *
      * @param[in]  compile_context The compile context to be used.
@@ -174,12 +152,9 @@
      * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref opencl::kernels::ClArithmeticKernel for power
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src1     First source tensor info. Data types supported: F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: F16/F32.
-     * @param[in] dst      Destination tensor info. Data types supported: F16/F32.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClElementwisePower::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClElementwiseUnary.h b/src/runtime/gpu/cl/operators/ClElementwiseUnary.h
index b40e3e9..b9acf6f 100644
--- a/src/runtime/gpu/cl/operators/ClElementwiseUnary.h
+++ b/src/runtime/gpu/cl/operators/ClElementwiseUnary.h
@@ -35,8 +35,6 @@
 class ClRsqrt : public IClOperator
 {
 public:
-    /** Constructor */
-    ClRsqrt() = default;
     /** Initialize the function
      *
      * @param[in]  compile_context The compile context to be used.
@@ -44,10 +42,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClRsqrt
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClRsqrt::configure()
      *
      * @return a status
      */
@@ -58,8 +55,6 @@
 class ClExp : public IClOperator
 {
 public:
-    /** Constructor */
-    ClExp() = default;
     /** Initialize the function
      *
      * @param[in]  compile_context The compile context to be used.
@@ -67,10 +62,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClExp
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClExp::configure()
      *
      * @return a status
      */
@@ -81,8 +75,6 @@
 class ClNeg : public IClOperator
 {
 public:
-    /** Constructor */
-    ClNeg() = default;
     /** Initialize the function
      *
      * @param[in]  compile_context The compile context to be used.
@@ -90,10 +82,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClNeg
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClNeg::configure()
      *
      * @return a status
      */
@@ -104,8 +95,6 @@
 class ClSin : public IClOperator
 {
 public:
-    /** Constructor */
-    ClSin() = default;
     /** Initialize the function
      *
      * @param[in]  compile_context The compile context to be used.
@@ -113,10 +102,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClSin
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClSin::configure()
      *
      * @return a status
      */
@@ -127,8 +115,6 @@
 class ClLog : public IClOperator
 {
 public:
-    /** Constructor */
-    ClLog() = default;
     /** Initialize the function
      *
      * @param[in]  compile_context The compile context to be used.
@@ -136,10 +122,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClLog
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClLog::configure()
      *
      * @return a status
      */
@@ -157,10 +142,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClAbs
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClAbs::configure()
      *
      * @return a status
      */
@@ -178,10 +162,9 @@
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src.
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClRound
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to @ref ClRound::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClFill.h b/src/runtime/gpu/cl/operators/ClFill.h
index e632d88..cc79b91 100644
--- a/src/runtime/gpu/cl/operators/ClFill.h
+++ b/src/runtime/gpu/cl/operators/ClFill.h
@@ -36,8 +36,6 @@
 class ClFill : public IClOperator
 {
 public:
-    /** Constructor */
-    ClFill() = default;
     /** Initialise the kernel's tensor and filling value
      *
      * @param[in]     compile_context The compile context to be used.
@@ -46,11 +44,9 @@
      * @param[in]     window          Window to be used in case setting only part of a tensor. Default is nullptr.
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *tensor, const PixelValue &constant_value, Window *window = nullptr);
-    /** Static function to check if given info will lead to a valid configuration of @ref kernels::ClFillKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] tensor         Source tensor info. Data types supported: All.
-     * @param[in] constant_value The value used to fill the planes of the tensor.
-     * @param[in] window         Window to be used in case setting only part of a tensor. Default is nullptr.
+     * Similar to ClFill::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClFlatten.h b/src/runtime/gpu/cl/operators/ClFlatten.h
index 20ad06e..8bd619b 100644
--- a/src/runtime/gpu/cl/operators/ClFlatten.h
+++ b/src/runtime/gpu/cl/operators/ClFlatten.h
@@ -35,8 +35,6 @@
 class ClFlatten : public IClOperator
 {
 public:
-    /** Constructor */
-    ClFlatten() = default;
     /** Configure operator for a given list of arguments
      *
      * Valid data layouts:
diff --git a/src/runtime/gpu/cl/operators/ClFloor.h b/src/runtime/gpu/cl/operators/ClFloor.h
index f54eef9..90bdee6 100644
--- a/src/runtime/gpu/cl/operators/ClFloor.h
+++ b/src/runtime/gpu/cl/operators/ClFloor.h
@@ -35,8 +35,6 @@
 class ClFloor : public IClOperator
 {
 public:
-    /** Constructor */
-    ClFloor() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in] compile_context The compile context to be used.
@@ -44,10 +42,9 @@
      * @param[in] dst             Destination tensor info. Data type supported: same as @p src
      */
     void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /** Static function to check if given info will lead to a valid configuration of @ref ClFloor
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Source tensor info. Data types supported: F16/F32.
-     * @param[in] dst Destination tensor info. Data type supported: same as @p src
+     * Similar to ClFloor::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClLogicalNot.h b/src/runtime/gpu/cl/operators/ClLogicalNot.h
index 25ddf56..782ac08 100644
--- a/src/runtime/gpu/cl/operators/ClLogicalNot.h
+++ b/src/runtime/gpu/cl/operators/ClLogicalNot.h
@@ -35,8 +35,6 @@
 class ClLogicalNot : public IClOperator
 {
 public:
-    /** Constructor */
-    ClLogicalNot() = default;
     /** Configure operator for a given list of arguments
      *
      * @param[in]  compile_context The compile context to be used.
@@ -46,8 +44,7 @@
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
     /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src Soure tensor info. Data types supported: U8.
-     * @param[in] dst Destination tensor info. Data types supported: same as @p src.
+     * Similar to ClLogicalNot::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClMul.h b/src/runtime/gpu/cl/operators/ClMul.h
index 4a662b3..29d5885 100644
--- a/src/runtime/gpu/cl/operators/ClMul.h
+++ b/src/runtime/gpu/cl/operators/ClMul.h
@@ -35,8 +35,6 @@
 class ClMul : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClMul() = default;
     /** Initialise the kernel's sources, dst and convertion policy.
      *
      * Valid configurations (src1,src2) -> Output :
@@ -81,8 +79,6 @@
 class ClComplexMul : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClComplexMul() = default;
     /** Initialise the kernel's sources, dst.
      *
      * @param[in]      compile_context The compile context to be used.
diff --git a/src/runtime/gpu/cl/operators/ClPRelu.h b/src/runtime/gpu/cl/operators/ClPRelu.h
index 70202ae..3a02030 100644
--- a/src/runtime/gpu/cl/operators/ClPRelu.h
+++ b/src/runtime/gpu/cl/operators/ClPRelu.h
@@ -38,8 +38,6 @@
 class ClPRelu : public IClOperator
 {
 public:
-    /** Default constructor */
-    ClPRelu() = default;
     /** Set the input and output tensor.
      *
      * @note If the output tensor is a nullptr or is equal to the input, the activation function will be performed in-place
@@ -50,11 +48,9 @@
      * @param[out] output          Destination tensor. Data type supported: same as @p input
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *input, ITensorInfo *alpha, ITensorInfo *output);
-    /** Static function to check if given info will lead to a valid configuration of @ref arm_compute::opencl::kernels::ClArithmeticKernel for PRELU
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] input  Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
-     * @param[in] alpha  PRelu layer parameters. Data types supported: same of @p input.
-     * @param[in] output Destination tensor info. Data type supported: same as @p input
+     * Similar to ClPRelu::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClPermute.h b/src/runtime/gpu/cl/operators/ClPermute.h
index 20e7a32..867aba0 100644
--- a/src/runtime/gpu/cl/operators/ClPermute.h
+++ b/src/runtime/gpu/cl/operators/ClPermute.h
@@ -35,8 +35,6 @@
 class ClPermute : public IClOperator
 {
 public:
-    /** Constructor */
-    ClPermute() = default;
     /** Initialise the kernel's inputs and outputs and permute vector
      *
      * @note Arbitrary permutation vectors are supported with rank not greater than 4
@@ -47,13 +45,9 @@
      * @param[in] perm            Permutation vector
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const PermutationVector &perm);
-    /**  Static function to check if given info will lead to a valid configuration of @ref kernels::ClPermuteKernel.
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @note Arbitrary permutation vectors are supported with rank not greater than 4
-     *
-     * @param[in] src  First tensor src info. Data types supported: All.
-     * @param[in] dst  Output tensor info. Data types supported: same as @p src.
-     * @param[in] perm Permutation vector
+     * Similar to ClPermute::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClQuantize.h b/src/runtime/gpu/cl/operators/ClQuantize.h
index 0b6d2c8..b15d389 100644
--- a/src/runtime/gpu/cl/operators/ClQuantize.h
+++ b/src/runtime/gpu/cl/operators/ClQuantize.h
@@ -35,8 +35,6 @@
 class ClQuantize : public IClOperator
 {
 public:
-    /** Constructor */
-    ClQuantize() = default;
     /** Set the input and output tensors.
      *
      * @param[in]  compile_context The compile context to be used.
diff --git a/src/runtime/gpu/cl/operators/ClReshape.h b/src/runtime/gpu/cl/operators/ClReshape.h
index 8cccc57..b3d9267 100644
--- a/src/runtime/gpu/cl/operators/ClReshape.h
+++ b/src/runtime/gpu/cl/operators/ClReshape.h
@@ -35,8 +35,6 @@
 class ClReshape : public IClOperator
 {
 public:
-    /** Constructor */
-    ClReshape() = default;
     /** Initialise the kernel's inputs and outputs
      *
      * @param[in]  compile_context The compile context to be used.
@@ -44,11 +42,9 @@
      * @param[out] output          Output info. Data type supported: Same as @p input
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *input, ITensorInfo *output);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref kernels::ClReshapeKernel
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] input  Input tensor info. Data type supported: All
-     * @param[in] output Output tensor info. Data type supported: Same as @p input
+     * Similar to ClReshape::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClScale.h b/src/runtime/gpu/cl/operators/ClScale.h
index 6eccb59..905c43a 100644
--- a/src/runtime/gpu/cl/operators/ClScale.h
+++ b/src/runtime/gpu/cl/operators/ClScale.h
@@ -51,13 +51,9 @@
      * @param[in]     info            @ref ScaleKernelInfo descriptor to be used to configure
      */
     void configure(const CLCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, const ScaleKernelInfo &info);
-
-    /** Static function to check if given info will lead to a valid configuration of @ref ClScale
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src  Source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32.
-     * @param[in] dst  Output tensor info. Data type supported: Same as @p src
-     *                 All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
-     * @param[in] info @ref ScaleKernelInfo descriptor to be used to validate
+     * Similar to ClScale::configure()
      *
      * @return a status
      */
@@ -71,4 +67,4 @@
 };
 } // namespace opencl
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_CLSCALE_H */
+#endif /* ARM_COMPUTE_CLSCALE_H */
diff --git a/src/runtime/gpu/cl/operators/ClSoftmax.h b/src/runtime/gpu/cl/operators/ClSoftmax.h
index f19a51f..c85b193 100644
--- a/src/runtime/gpu/cl/operators/ClSoftmax.h
+++ b/src/runtime/gpu/cl/operators/ClSoftmax.h
@@ -51,15 +51,13 @@
      * @param[in]  src             Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32 for Softmax and F16/F32 for Log Softmax
      * @param[out] dst             Destination tensor info. Data types supported: same as @p src
      * @param[in]  info            Contains information consumed by kernels for softmax described in @ref SoftmaxKernelInfo.
-     *
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo &src, ITensorInfo &dst, const SoftmaxKernelInfo &info);
-    /** Static function to check if the given info will lead to a valid configuration
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in]  src  Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32 for Softmax and F16/F32 for Log Softmax
-     * @param[out] dst  Destination tensor info. Data types supported: same as @p src
-     * @param[in]  info Contains information consumed by kernels for softmax described in @ref SoftmaxKernelInfo.
+     * Similar to ClSoftmax::configure()
      *
+     * @return a status
      */
     static Status validate(const ITensorInfo &src, const ITensorInfo &dst, const SoftmaxKernelInfo &info);
     // Inherited methods overridden:
diff --git a/src/runtime/gpu/cl/operators/ClSub.h b/src/runtime/gpu/cl/operators/ClSub.h
index bcad84d..2dac11c 100644
--- a/src/runtime/gpu/cl/operators/ClSub.h
+++ b/src/runtime/gpu/cl/operators/ClSub.h
@@ -39,8 +39,6 @@
 class ClSub : public IClOperator
 {
 public:
-    /** Default Constructor */
-    ClSub() = default;
     /** Configure function for a given list of arguments.
      *
      * Valid configurations (src1,src2) -> dst :
@@ -68,27 +66,9 @@
      */
     void configure(const ClCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *dst, ConvertPolicy policy,
                    const ActivationLayerInfo &act_info = ActivationLayerInfo());
-    /** Static function to check if given info will lead to a valid configuration of @ref ClSub
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * Valid configurations (src1,src2) -> dst :
-     *
-     *   - (U8,U8)           -> U8
-     *   - (U8,U8)           -> S16
-     *   - (S16,U8)          -> S16
-     *   - (U8,S16)          -> S16
-     *   - (S16,S16)         -> S16
-     *   - (S32,S32)         -> S32
-     *   - (F16,F16)         -> F16
-     *   - (F32,F32)         -> F32
-     *   - (QASYMM8,QASYMM8) -> QASYMM8
-     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (QSYMM16,QSYMM16) -> QSYMM16
-     *
-     * @param[in] src1     First source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] src2     Second source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] dst      Destination tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
-     * @param[in] policy   Policy to use to handle overflow.
-     * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+     * Similar to @ref ClSub::configure()
      *
      * @return a status
      */
diff --git a/src/runtime/gpu/cl/operators/ClTranspose.h b/src/runtime/gpu/cl/operators/ClTranspose.h
index d898f67..dcd8082 100644
--- a/src/runtime/gpu/cl/operators/ClTranspose.h
+++ b/src/runtime/gpu/cl/operators/ClTranspose.h
@@ -35,8 +35,6 @@
 class ClTranspose : public IClOperator
 {
 public:
-    /** Constructor */
-    ClTranspose() = default;
     /** Initialise the kernel's inputs and outputs
      *
      * @param[in] compile_context The compile context to be used.
@@ -44,10 +42,9 @@
      * @param[in] dst             The dst tensor info. Data types supported: Same as @p src
      */
     void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst);
-    /**  Static function to check if given info will lead to a valid configuration of @ref kernels::ClTransposeKernel.
+    /** Static function to check if given info will lead to a valid configuration
      *
-     * @param[in] src First tensor src info. Data types supported: All.
-     * @param[in] dst Output tensor info. Data types supported: same as @p src.
+     * Similar to ClTranspose::configure()
      *
      * @return a status
      */