diff --git a/src/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.cpp b/src/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.cpp
index d015ec3..6909082 100644
--- a/src/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.cpp
+++ b/src/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.cpp
@@ -187,6 +187,12 @@
     },
     ina, inb, out);
 #else  /* ARM_COMPUTE_ENABLE_FP16 */
+    ARM_COMPUTE_UNUSED(input0);
+    ARM_COMPUTE_UNUSED(input1);
+    ARM_COMPUTE_UNUSED(output);
+    ARM_COMPUTE_UNUSED(window);
+    ARM_COMPUTE_UNUSED(info);
+    ARM_COMPUTE_UNUSED(alpha);
     ARM_COMPUTE_ERROR("Not implemented");
 #endif /* ARM_COMPUTE_ENABLE_FP16 */
 }
@@ -1046,6 +1052,11 @@
     },
     ina, inb, out);
 #else  /* ARM_COMPUTE_ENABLE_FP16 */
+    ARM_COMPUTE_UNUSED(input0);
+    ARM_COMPUTE_UNUSED(input1);
+    ARM_COMPUTE_UNUSED(output);
+    ARM_COMPUTE_UNUSED(window);
+    ARM_COMPUTE_UNUSED(alpha);
     ARM_COMPUTE_ERROR("Not implemented");
 #endif /* ARM_COMPUTE_ENABLE_FP16 */
 }
diff --git a/src/core/NEON/kernels/NELocallyConnectedMatrixMultiplyKernel.cpp b/src/core/NEON/kernels/NELocallyConnectedMatrixMultiplyKernel.cpp
index a02ebf6..1b2942c 100644
--- a/src/core/NEON/kernels/NELocallyConnectedMatrixMultiplyKernel.cpp
+++ b/src/core/NEON/kernels/NELocallyConnectedMatrixMultiplyKernel.cpp
@@ -165,6 +165,7 @@
     ARM_COMPUTE_UNUSED(input1);
     ARM_COMPUTE_UNUSED(output);
     ARM_COMPUTE_UNUSED(window);
+    ARM_COMPUTE_UNUSED(info);
     ARM_COMPUTE_ERROR("Not supported, recompile with -march=armv8.2-a+fp16+simd.");
 #endif /* ARM_COMPUTE_ENABLE_FP16 */
 }
diff --git a/src/core/NEON/kernels/NENormalizationLayerKernel.cpp b/src/core/NEON/kernels/NENormalizationLayerKernel.cpp
index b444c9d..fc3f5f2 100644
--- a/src/core/NEON/kernels/NENormalizationLayerKernel.cpp
+++ b/src/core/NEON/kernels/NENormalizationLayerKernel.cpp
@@ -70,6 +70,7 @@
     _border_size   = BorderSize(0, border_width);
 
     unsigned int num_elems_processed_per_iteration = 16 / input->info()->element_size();
+    ARM_COMPUTE_UNUSED(num_elems_processed_per_iteration);
 
     switch(_input->info()->data_type())
     {
diff --git a/src/core/NEON/kernels/NEPixelWiseMultiplicationKernel.cpp b/src/core/NEON/kernels/NEPixelWiseMultiplicationKernel.cpp
index 40dcc71..19d45e2 100644
--- a/src/core/NEON/kernels/NEPixelWiseMultiplicationKernel.cpp
+++ b/src/core/NEON/kernels/NEPixelWiseMultiplicationKernel.cpp
@@ -335,9 +335,6 @@
 template <bool is_scale255, bool is_sat>
 void mul_F16_F16_F16_n(const void *__restrict input1_ptr, const void *__restrict input2_ptr, void *__restrict output_ptr, float scale)
 {
-    ARM_COMPUTE_UNUSED(input1_ptr);
-    ARM_COMPUTE_UNUSED(input2_ptr);
-    ARM_COMPUTE_UNUSED(output_ptr);
 #ifdef ARM_COMPUTE_ENABLE_FP16
     const auto          input1    = static_cast<const float16_t *__restrict>(input1_ptr);
     const auto          input2    = static_cast<const float16_t *__restrict>(input2_ptr);
@@ -354,6 +351,10 @@
     };
     vst2q_f16(output, result);
 #else  /* ARM_COMPUTE_ENABLE_FP16 */
+    ARM_COMPUTE_UNUSED(input1_ptr);
+    ARM_COMPUTE_UNUSED(input2_ptr);
+    ARM_COMPUTE_UNUSED(output_ptr);
+    ARM_COMPUTE_UNUSED(scale);
     ARM_COMPUTE_ERROR("Not supported. Recompile the library with arch=arm64-v8.2-a.");
 #endif /* ARM_COMPUTE_ENABLE_FP16 */
 }