diff options
author | Michalis Spyrou <michalis.spyrou@arm.com> | 2017-11-23 12:10:21 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:41:04 +0000 |
commit | b7b31538eb9137e4d3e8de6d381dcbe9fc58df94 (patch) | |
tree | 7cca8c388cfb15867b9d92c6fd793ca1588b6526 /arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h | |
parent | 02bf80d4554cfc824a76008905921cb564bee999 (diff) | |
download | ComputeLibrary-b7b31538eb9137e4d3e8de6d381dcbe9fc58df94.tar.gz |
COMPMID-464 Implement Depthwise separable convolution on NEON
Change-Id: Iccd686be18381e96bcf09b14c7017c6dda0f38d8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/109824
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h')
-rw-r--r-- | arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h | 63 |
1 files changed, 63 insertions, 0 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h new file mode 100644 index 0000000000..d844af5d54 --- /dev/null +++ b/arm_compute/core/NEON/kernels/NEGEMMMatrixVectorMultiplyKernel.h @@ -0,0 +1,63 @@ +/* + * Copyright (c) 2016, 2017 ARM Limited. + * + * SPDX-License-Identifier: MIT + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in all + * copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __ARM_COMPUTE_NEGEMMMATRIXVECTORMULTIPLYKERNEL_H_ +#define __ARM_COMPUTE_NEGEMMMATRIXVECTORMULTIPLYKERNEL_H_ + +#include "arm_compute/core/NEON/INESimpleKernel.h" + +namespace arm_compute +{ +class ITensor; + +class NEGEMMMatrixVectorMultiplyKernel : public INESimpleKernel +{ +public: + /** Default constructor */ + NEGEMMMatrixVectorMultiplyKernel(); + /** Prevent instances of this class from being copied (As this class contains pointers) */ + NEGEMMMatrixVectorMultiplyKernel(const NEGEMMMatrixVectorMultiplyKernel &) = delete; + /** Prevent instances of this class from being copied (As this class contains pointers) */ + NEGEMMMatrixVectorMultiplyKernel &operator=(const NEGEMMMatrixVectorMultiplyKernel &) = delete; + /** Allow instances of this class to be moved */ + NEGEMMMatrixVectorMultiplyKernel(NEGEMMMatrixVectorMultiplyKernel &&) = default; + /** Allow instances of this class to be moved */ + NEGEMMMatrixVectorMultiplyKernel &operator=(NEGEMMMatrixVectorMultiplyKernel &&) = default; + /** Initialise the kernel's input and output. + * + * @param[in] input0 First Input tensor. Data types supported: F16/F32 + * @param[in] input1 Second Input tensor. Data types supported: same as @p input. + * @param[out] output Output tensor which stores the interleaved matrix. Data type supported: same as @p input. + */ + void configure(const ITensor *input0, const ITensor *input1, ITensor *output); + + // Inherited methods overridden: + void run(const Window &window, const ThreadInfo &info) override; + +private: + const ITensor *_input0; + const ITensor *_input1; + ITensor *_output; +}; +} // namespace arm_compute +#endif /*__ARM_COMPUTE_NEGEMMMATRIXVECTORMULTIPLYKERNEL_H_*/ |