diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2018-11-16 16:04:25 +0000 |
---|---|---|
committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-02-07 09:44:08 +0000 |
commit | ebc3a90721fe4a41b8e141466894d4d7185c01b7 (patch) | |
tree | 9149764caa37edbdc6bb6c69d503d37dbb28449f /arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h | |
parent | 4632e5e44e9a78b15884d0947007bb030fde0aea (diff) | |
download | ComputeLibrary-ebc3a90721fe4a41b8e141466894d4d7185c01b7.tar.gz |
COMPMID-1706: Fuse the bias addition within CLGEMM
Change-Id: I378f2023f4fa010f195f76716ac07aa86279bfae
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/280
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h')
-rw-r--r-- | arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h b/arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h index d6d88cec55..e800dd7cbb 100644 --- a/arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h +++ b/arm_compute/runtime/CL/functions/CLFullyConnectedLayer.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2018 ARM Limited. + * Copyright (c) 2017-2019 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -136,7 +136,7 @@ private: CLGEMM _mm_gemm; CLGEMMLowpMatrixMultiplyCore _mm_gemmlowp; CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint _gemmlowp_output_stage; - CLGEMMMatrixAccumulateBiasesKernel _accumulate_biases_kernel; + CLGEMMMatrixAccumulateBiasesKernel _accumulate_biases_kernel; // TODO(COMPMID-1889): Use CLGEMM to add bias in CLFullyConnectedLayer CLTensor _flatten_output; CLTensor _gemmlowp_output; CLTensor _converted_weights_output; |