diff options
| author | Gian Marco <gianmarco.iodice@arm.com> | 2018-01-12 10:21:40 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:44:21 +0000 |
| commit | 36a0a4608bf413fc1fd65eb335bfb736ef602149 (patch) | |
| tree | 2ff0e35dc9e16fedd601b1f24bdc13d25d075b90 /arm_compute/runtime/CL/functions/CLGEMM.h | |
| parent | 46edf63bd630f5e3f3eb31b7d4602caa317da075 (diff) | |
| download | ComputeLibrary-36a0a4608bf413fc1fd65eb335bfb736ef602149.tar.gz | |
COMPMID-748 - Integrating optimized SGEMM for bifrost
This patch introduces a new GEMM capable to improve the mac utilisation
of 10% compared to the GEMM without reshape. However this implementation
is not faster in all cases as we need to take into account the time for
reshaping the matrices. For this reason an heuristic solution to select
the optimal GEMM to use has been added to the function. More information
about the heuristic implementation can be found at COMPMID-852.
With this new patch, GoogleNet, MobileNet, VGG16 and SqueezeNet can
improved the performance of 1.5x.
More information about the performance uplift can be found here:
https://confluence.arm.com/display/MLENG/GEMM+FP32+performance%3A+ACL+18.02
Change-Id: I024563c06b9aed02a211a974e452bae5c233b04c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/117140
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLGEMM.h')
| -rw-r--r-- | arm_compute/runtime/CL/functions/CLGEMM.h | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/arm_compute/runtime/CL/functions/CLGEMM.h b/arm_compute/runtime/CL/functions/CLGEMM.h index bf41226bda..0f144915d7 100644 --- a/arm_compute/runtime/CL/functions/CLGEMM.h +++ b/arm_compute/runtime/CL/functions/CLGEMM.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016, 2017 ARM Limited. + * Copyright (c) 2016-2018 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -68,7 +68,8 @@ public: * @param[in] alpha Weight of the matrix product * @param[in] beta Weight of matrix C * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and - * if the reshape of matrix B should happen only for the first run + * if the reshape of matrix B should happen only for the first run. GEMMInfo also contains information about the reshaping + * in case matrix A and matrix B have been already transformed. */ void configure(const ICLTensor *a, const ICLTensor *b, const ICLTensor *c, ICLTensor *output, float alpha, float beta, const GEMMInfo &gemm_info = GEMMInfo()); |