commit 6d109965f3641056bb8164dc8450a7327e76e939
author giuros01 <giuseppe.rossini@arm.com> Mon Jan 07 17:47:19 2019 +0000
committer Giuseppe Rossini <giuseppe.rossini@arm.com> Wed Jan 30 16:22:47 2019 +0000
tree 45e40a75e7f2d80e403a33087284f08b2b2a0b6b
parent edc21e44313edea693700a6bdfa353edcfbe25be

COMPMID-1691: Optimize CLDepthwiseConvolutionKernel (QASYMM8/NHWC) for 3x3 kernels (stride=1 and stride=2)

Change-Id: I7d0d2dc350feeb40d253d17f9ffd5051a8fb42ef
Reviewed-on: https://review.mlplatform.org/511
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

arm_compute/core/CL/CLKernels.h

diff --git a/arm_compute/core/CL/CLKernels.h b/arm_compute/core/CL/CLKernels.h
index 07e214b..cc4888c 100644
--- a/arm_compute/core/CL/CLKernels.h
+++ b/arm_compute/core/CL/CLKernels.h
@@ -51,9 +51,10 @@
 #include "arm_compute/core/CL/kernels/CLDepthConvertLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h"
 #include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h"
+#include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsGenericKernel.h"
+#include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.h"
 #include "arm_compute/core/CL/kernels/CLDepthwiseIm2ColKernel.h"
 #include "arm_compute/core/CL/kernels/CLDepthwiseVectorToTensorKernel.h"
-#include "arm_compute/core/CL/kernels/CLDepthwiseWeightsReshapeKernel.h"
 #include "arm_compute/core/CL/kernels/CLDequantizationLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLDerivativeKernel.h"
 #include "arm_compute/core/CL/kernels/CLDilateKernel.h"