commit bf9731edfa0439cad4d70efc3065e71e199c62b8
author Gian Marco Iodice <gianmarco.iodice@arm.com> Wed Dec 12 10:18:04 2018 +0000
committer Gian Marco Iodice <gianmarco.iodice@arm.com> Fri Dec 14 14:57:48 2018 +0000
tree 71340a3d04a6294744c642ed6e4a56c0e8a77592
parent 92e278d5f462c930af1947883a5f48c10586ae9c

COMPMID-1687: Optimize CLGEMMMatrixMultiplyKernel for Mali-G76 - Part1

The current implementation is limited just to FP32

Change-Id: I185ab57e483e879d7c301e9cc3033efc8b41e244
Reviewed-on: https://review.mlplatform.org/389
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@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 37b92f2..d89426d 100644
--- a/arm_compute/core/CL/CLKernels.h
+++ b/arm_compute/core/CL/CLKernels.h
@@ -78,6 +78,7 @@
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixAccumulateBiasesKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h"
+#include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.h"