From 181e65145d153210ec5587a42d2938e27e1d5b01 Mon Sep 17 00:00:00 2001 From: Pablo Tello Date: Wed, 15 Nov 2017 13:28:27 +0000 Subject: COMPMID-675: NEGEMMLowp Assembly Integration Added support for S8 input in NEGEMMLowp Matrix Multiply Kernel. Added a new function to run assembly kernels such that A*B=C (no offsets involved) Added new tests for the assembly gemmlowp kernels (no offsets) Integrated the assembly kernel for the A57 Change-Id: Ib3e39c1f3f7f1baa0d39be69485f61cd18e3c9b3 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95864 Tested-by: Kaizen Reviewed-by: Anthony Barbier --- arm_compute/runtime/NEON/NEFunctions.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arm_compute/runtime/NEON/NEFunctions.h') diff --git a/arm_compute/runtime/NEON/NEFunctions.h b/arm_compute/runtime/NEON/NEFunctions.h index 118603b20b..203df33692 100644 --- a/arm_compute/runtime/NEON/NEFunctions.h +++ b/arm_compute/runtime/NEON/NEFunctions.h @@ -60,6 +60,7 @@ #include "arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h" #include "arm_compute/runtime/NEON/functions/NEGEMM.h" #include "arm_compute/runtime/NEON/functions/NEGEMMInterleave4x4.h" +#include "arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h" #include "arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h" #include "arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h" #include "arm_compute/runtime/NEON/functions/NEGEMMTranspose1xW.h" -- cgit v1.2.1