diff --git a/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
index 659594f..6208c20 100644
--- a/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
@@ -28,7 +28,7 @@
 #include "arm_compute/core/NEON/kernels/NEDepthwiseIm2ColKernel.h"
 #include "arm_compute/core/NEON/kernels/NEDepthwiseVectorToTensorKernel.h"
 #include "arm_compute/core/NEON/kernels/NEDepthwiseWeightsReshapeKernel.h"
-#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerBiasAccumulateKernel.h"
+#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerOutputStageKernel.h"
 #include "arm_compute/core/NEON/kernels/NEFillBorderKernel.h"
 #include "arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h"
 #include "arm_compute/core/Types.h"
@@ -67,10 +67,10 @@
     void run() override;
 
 private:
-    NEDepthwiseConvolutionLayer3x3Kernel         _kernel;
-    NEDirectConvolutionLayerBiasAccumulateKernel _bias_kernel;
-    NEFillBorderKernel                           _border_handler;
-    bool                                         _has_bias;
+    NEDepthwiseConvolutionLayer3x3Kernel      _kernel;
+    NEDirectConvolutionLayerOutputStageKernel _output_stage_kernel;
+    NEFillBorderKernel                        _border_handler;
+    bool                                      _has_bias;
 };
 
 /** Basic function to execute a generic depthwise convolution. This function calls the following NEON kernels:
diff --git a/arm_compute/runtime/NEON/functions/NEDirectConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEDirectConvolutionLayer.h
index 09a5496..e1aa839 100644
--- a/arm_compute/runtime/NEON/functions/NEDirectConvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEDirectConvolutionLayer.h
@@ -24,8 +24,8 @@
 #ifndef __ARM_COMPUTE_NEDIRECTCONVOLUTIONLAYER_H__
 #define __ARM_COMPUTE_NEDIRECTCONVOLUTIONLAYER_H__
 
-#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerBiasAccumulateKernel.h"
 #include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerKernel.h"
+#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerOutputStageKernel.h"
 #include "arm_compute/core/NEON/kernels/NEFillBorderKernel.h"
 #include "arm_compute/core/Types.h"
 #include "arm_compute/runtime/IFunction.h"
@@ -42,7 +42,7 @@
  *  This function calls the following NEON kernels:
  *
  * -# @ref NEFillBorderKernel for the input
- * -# @ref NEDirectConvolutionLayerBiasAccumulateKernel
+ * -# @ref NEDirectConvolutionLayerOutputStageKernel
  * -# @ref NEDirectConvolutionLayerKernel
  */
 class NEDirectConvolutionLayer : public IFunction
@@ -93,12 +93,13 @@
     void run() override;
 
 private:
-    MemoryGroup                                  _memory_group;
-    NEDirectConvolutionLayerBiasAccumulateKernel _accumulate_bias_kernel;
-    NEDirectConvolutionLayerKernel               _conv_kernel;
-    NEFillBorderKernel                           _input_border_handler;
-    Tensor                                       _accumulator;
-    bool                                         _has_bias;
+    MemoryGroup                               _memory_group;
+    NEDirectConvolutionLayerOutputStageKernel _output_stage_kernel;
+    NEDirectConvolutionLayerKernel            _conv_kernel;
+    NEFillBorderKernel                        _input_border_handler;
+    Tensor                                    _accumulator;
+    bool                                      _has_bias;
+    bool                                      _is_fixed_point;
 };
 }
 #endif /* __ARM_COMPUTE_NEDIRECTCONVOLUTIONLAYER_H__ */