COMPMID-1710: Fix NEReductionOperation border values for QASYMM8.

Remove quantization information when setting the PixelValue on the
border as it will quantize the 0 value leading to invalid calculations.

Change-Id: I774156e7c9914105e319e8dc09f465a1b86d4b0b
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/749
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/runtime/NEON/functions/NEReductionOperation.cpp b/src/runtime/NEON/functions/NEReductionOperation.cpp
index 3ec8ef1..9f81a40 100644
--- a/src/runtime/NEON/functions/NEReductionOperation.cpp
+++ b/src/runtime/NEON/functions/NEReductionOperation.cpp
@@ -77,7 +77,7 @@
     {
         // Configure fill border kernel
         const BorderSize fill_border_size = _reduction_kernel.border_size();
-        const PixelValue pixelValue       = PixelValue((op == ReductionOperation::PROD) ? 1 : 0, input->info()->data_type(), input->info()->quantization_info());
+        const PixelValue pixelValue       = (op == ReductionOperation::PROD) ? PixelValue(1, input->info()->data_type(), input->info()->quantization_info()) : PixelValue(0, input->info()->data_type());
         _fill_border_kernel.configure(input, fill_border_size, BorderMode::CONSTANT, pixelValue);
     }
 }