COMPMID-746 Allow NEDirectConvolution to work without biases for QS.

Renamed BiasAccumulateKernel to OutputStage. If no bias is provided
when the input is quantized, the kernel simply downscales the input.
Throw error if no bias is provided and input is floating point.

Change-Id: I645a4ee9c6014b0547778fdd92c9ec72ef2f0aab
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114158
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
diff --git a/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp b/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp
index 4575c7a..298101a 100644
--- a/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp
@@ -32,7 +32,7 @@
 using namespace arm_compute;
 
 NEDepthwiseConvolutionLayer3x3::NEDepthwiseConvolutionLayer3x3()
-    : _kernel(), _bias_kernel(), _border_handler(), _has_bias(false)
+    : _kernel(), _output_stage_kernel(), _border_handler(), _has_bias(false)
 {
 }
 
@@ -46,7 +46,7 @@
     _border_handler.configure(input, _kernel.border_size(), BorderMode::CONSTANT, PixelValue(static_cast<float>(0.f)));
     if(biases != nullptr)
     {
-        _bias_kernel.configure(output, biases);
+        _output_stage_kernel.configure(output, biases);
         _has_bias = true;
     }
 }
@@ -57,7 +57,7 @@
     NEScheduler::get().schedule(&_kernel, Window::DimX);
     if(_has_bias)
     {
-        NEScheduler::get().schedule(&_bias_kernel, Window::DimX);
+        NEScheduler::get().schedule(&_output_stage_kernel, Window::DimX);
     }
 }