COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM8 NHWC
The NCHW case is supported at function level by permuting the
inputs/outputs to NHWC.
This patch also removes CLDirectConvolutionLayerOutputStageKernel which
is deprecated and some kernels which were only used in the generic case
of depthwise convolution.
Change-Id: I91e0f02d0a2f4a4a352e08c248e648944137fe68
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2056
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel.cpp b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel.cpp
index 2967a73..ae096f2 100644
--- a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel.cpp
@@ -35,8 +35,6 @@
#include "support/ToolchainSupport.h"
-using namespace arm_compute;
-
namespace arm_compute
{
namespace
@@ -101,8 +99,6 @@
} // namespace
class Coordinates;
-} // namespace arm_compute
-
CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel::CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloatKernel()
: _input(nullptr), _bias(nullptr), _output(nullptr)
{
@@ -177,3 +173,4 @@
}
while(collapsed.slide_window_slice_3D(slice));
}
+} // namespace arm_compute