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/NELSTMLayerQuantized.cpp b/src/runtime/NEON/functions/NELSTMLayerQuantized.cpp
index 7610d15..e439293 100644
--- a/src/runtime/NEON/functions/NELSTMLayerQuantized.cpp
+++ b/src/runtime/NEON/functions/NELSTMLayerQuantized.cpp
@@ -26,6 +26,16 @@
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/NEON/kernels/NEConvertFullyConnectedWeightsKernel.h"
+#include "src/core/NEON/kernels/NEConvertQuantizedSignednessKernel.h"
+#include "src/core/NEON/kernels/NEGEMMInterleave4x4Kernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpOffsetContributionOutputStageKernel.h"
+#include "src/core/NEON/kernels/NEGEMMLowpReductionKernel.h"
+#include "src/core/NEON/kernels/NEGEMMMatrixAdditionKernel.h"
+#include "src/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h"
+#include "src/core/NEON/kernels/NEGEMMTranspose1xWKernel.h"
 #include "src/core/helpers/AutoConfiguration.h"
 
 #include <cmath>
@@ -42,6 +52,7 @@
 const QuantizationInfo qsymm_4(16.f / 32768.f, 0); // qsymm16 with 4 integer bit
 const QuantizationInfo qsymm_0(1.f / 32768.f, 0);  // qsymm16 with 0 integer bit
 } // namespace
+NELSTMLayerQuantized::~NELSTMLayerQuantized() = default;
 
 NELSTMLayerQuantized::NELSTMLayerQuantized(std::shared_ptr<IMemoryManager> memory_manager)
     : _memory_group(std::move(memory_manager)), _gemmlowp(), _output_stage(), _transpose_weights(), _concat_input_weights(), _concat_recurrent_weights(), _concat_weights(), _concat_inputs(),