From 2d7e683e79c8ad328d4930c1f82a46827313faf4 Mon Sep 17 00:00:00 2001 From: George Wort Date: Fri, 22 Feb 2019 16:37:41 +0000 Subject: COMPMID-1694: Fuse offset contribution with the output stage when we use NEGEMMLowpMatrixMultiplyCore Change-Id: Ic1a681e4cc03e1eba3bf8485d9cdb17b3e926047 Signed-off-by: giuros01 Reviewed-on: https://review.mlplatform.org/c/561 Reviewed-by: Gian Marco Iodice Tested-by: Arm Jenkins --- arm_compute/core/NEON/NEKernels.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arm_compute/core/NEON/NEKernels.h') diff --git a/arm_compute/core/NEON/NEKernels.h b/arm_compute/core/NEON/NEKernels.h index f1d94c89db..5b1b701a9d 100644 --- a/arm_compute/core/NEON/NEKernels.h +++ b/arm_compute/core/NEON/NEKernels.h @@ -73,6 +73,7 @@ #include "arm_compute/core/NEON/kernels/NEGEMMInterleave4x4Kernel.h" #include "arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h" #include "arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h" +#include "arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionOutputStageKernel.h" #include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h" #include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h" #include "arm_compute/core/NEON/kernels/NEGEMMLowpReductionKernel.h" -- cgit v1.2.1