COMPMID-3638: Move NEON kernels

Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Change-Id: Ieed3e4bc8be7fef80c90c5094599b477a56fc473
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4285
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp b/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
index 239a8e6..9fb8851 100644
--- a/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
+++ b/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
@@ -24,15 +24,17 @@
 #include "arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h"
 
 #include "arm_compute/core/ITensor.h"
-#include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ScaleKernel.h"
-#include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h"
-#include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h"
-#include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ScaleKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h"
 #include "support/MemorySupport.h"
 
 namespace arm_compute
 {
+NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::~NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint() = default;
+
 void NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::configure(const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift,
                                                                     int result_offset_after_shift, int min, int max)
 {
@@ -46,6 +48,8 @@
     return NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::validate(input, bias, output, min, max);
 }
 
+NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint::~NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint() = default;
+
 void NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint::configure(const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift,
                                                                    int result_offset_after_shift, int min, int max)
 {
@@ -59,6 +63,8 @@
     return NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::validate(input, bias, output, min, max);
 }
 
+NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint::~NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint() = default;
+
 void NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint::configure(const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift, int min, int max)
 {
     auto k = arm_compute::support::cpp14::make_unique<NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel>();
@@ -71,6 +77,8 @@
     return NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel::validate(input, bias, output, min, max);
 }
 
+NEGEMMLowpOutputStage::~NEGEMMLowpOutputStage() = default;
+
 void NEGEMMLowpOutputStage::configure(const ITensor *input, const ITensor *bias, ITensor *output, const GEMMLowpOutputStageInfo &info)
 {
     // Perform validate step