COMPMID-903: Implements NEPermute for NHWC conversions

Change-Id: I4083e8d16bb23933634f229a1408dfd0e8f2922a
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120069
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>

1 files changed, 4 insertions, 4 deletions

diff --git a/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
index 682effe84b..1c65b3ccf5 100644
--- a/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEDepthwiseConvolutionLayer.h
@@ -32,10 +32,10 @@
 #include "arm_compute/core/NEON/kernels/NEFillBorderKernel.h"
 #include "arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h"
 #include "arm_compute/core/Types.h"
-#include "arm_compute/runtime/CPP/functions/CPPPermute.h"
 #include "arm_compute/runtime/IFunction.h"
 #include "arm_compute/runtime/IMemoryManager.h"
 #include "arm_compute/runtime/MemoryGroup.h"
+#include "arm_compute/runtime/NEON/functions/NEPermute.h"
 #include "arm_compute/runtime/Tensor.h"
 
 namespace arm_compute
@@ -71,9 +71,9 @@ private:
     NEDepthwiseConvolutionLayer3x3Kernel      _dwc_kernel;
     NEDirectConvolutionLayerOutputStageKernel _output_stage_kernel;
     NEFillBorderKernel                        _border_handler;
-    CPPPermute                                _permute_input;
-    CPPPermute                                _permute_weights;
-    CPPPermute                                _permute_output;
+    NEPermute                                 _permute_input;
+    NEPermute                                 _permute_weights;
+    NEPermute                                 _permute_output;
     Tensor                                    _accumulator;
     Tensor                                    _input_nhwc;
     Tensor                                    _weights_hwio;