COMPMID-3034: Add NERequantizationLayerKernel

Change-Id: I3f098c3c2c2031d8cbe7326eab88a4e78bda867f
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2704
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
diff --git a/arm_compute/core/NEON/NEMath.inl b/arm_compute/core/NEON/NEMath.inl
index 5d8b82c..49870d0 100644
--- a/arm_compute/core/NEON/NEMath.inl
+++ b/arm_compute/core/NEON/NEMath.inl
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2019 ARM Limited.
+ * Copyright (c) 2016-2020 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -345,6 +345,18 @@
     return out;
 }
 
+template <>
+inline float32x4x4_t convert_to_float32x4x4(const uint8x16_t &in)
+{
+    return convert_uint8x16_to_float32x4x4(in);
+}
+
+template <>
+inline float32x4x4_t convert_to_float32x4x4(const int8x16_t &in)
+{
+    return convert_int8x16_to_float32x4x4(in);
+}
+
 inline void convert_float32x4x3_to_uint8x8x3(const float32x4x3_t &in1, const float32x4x3_t &in2, uint8x8x3_t &out)
 {
     out.val[0] = vqmovn_u16(vcombine_u16(vqmovn_u32(vcvtq_u32_f32(in1.val[0])),