diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2018-02-02 12:52:07 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:47:18 +0000 |
| commit | de5a1cc7e5c929b19fb1d3ed7d0d8783b9ac6860 (patch) | |
| tree | a1787371cdaf4976d8781bd453551a85d2fc274a /arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h | |
| parent | f36ac355e050a4714a951d04a72896e02cf5e2a1 (diff) | |
| download | ComputeLibrary-de5a1cc7e5c929b19fb1d3ed7d0d8783b9ac6860.tar.gz | |
COMPMID-856: CL Depthwise Convolution QASYMM8 support
Change-Id: Ic6097e7cf160e8b829fb521b7b99d9a57d9799d3
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118774
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h')
| -rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h index 580322fb51..c27307e63b 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017 ARM Limited. + * Copyright (c) 2017-2018 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -46,8 +46,8 @@ public: CLGEMMMatrixVectorMultiplyKernel &operator=(CLGEMMMatrixVectorMultiplyKernel &&) = default; /** Set the input and output of the kernel. * - * @param[in] input0 The reshaped input tensor. Data types supported: F16/F32 - * @param[in] input1 The 2D reshaped weights tensor. Data type supported: Same as @p input. + * @param[in] input0 The reshaped input tensor. Data types supported: QASYMM8/F16/F32 + * @param[in] input1 The 2D reshaped weights tensor. Data type supported: Same as @p input, S32 for QASYMM8 input. * @param[out] output The output 2D tensor. Data types supported: Same as @p input */ void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output); |