diff options
author | Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> | 2019-06-28 14:09:53 +0100 |
---|---|---|
committer | VidhyaSudhan Loganathan <vidhyasudhan.loganathan@arm.com> | 2019-06-28 14:15:30 +0000 |
commit | 338595bca8ab60492f10626860acb1ab3722b1ce (patch) | |
tree | 03504ec3a2973e30c80f9bf56b77b4a4c7c9d83c /arm_compute/core/CL | |
parent | 7026b303d636e7639f8877ae8d5eff54f39c1121 (diff) | |
download | ComputeLibrary-338595bca8ab60492f10626860acb1ab3722b1ce.tar.gz |
COMPMID-2234 : Add support for axis 3 in NE/CLConcatenateLayer
Change-Id: Ic86f89ece3afe72809bc69c6de6fee7d21daa1d4
Signed-off-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1440
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CL')
-rw-r--r-- | arm_compute/core/CL/CLKernels.h | 1 | ||||
-rw-r--r-- | arm_compute/core/CL/kernels/CLBatchConcatenateLayerKernel.h | 83 |
2 files changed, 84 insertions, 0 deletions
diff --git a/arm_compute/core/CL/CLKernels.h b/arm_compute/core/CL/CLKernels.h index cd5612c9ae..8fbc4770b0 100644 --- a/arm_compute/core/CL/CLKernels.h +++ b/arm_compute/core/CL/CLKernels.h @@ -28,6 +28,7 @@ #include "arm_compute/core/CL/kernels/CLAbsoluteDifferenceKernel.h" #include "arm_compute/core/CL/kernels/CLAccumulateKernel.h" #include "arm_compute/core/CL/kernels/CLActivationLayerKernel.h" +#include "arm_compute/core/CL/kernels/CLBatchConcatenateLayerKernel.h" #include "arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h" #include "arm_compute/core/CL/kernels/CLBatchToSpaceLayerKernel.h" #include "arm_compute/core/CL/kernels/CLBitwiseAndKernel.h" diff --git a/arm_compute/core/CL/kernels/CLBatchConcatenateLayerKernel.h b/arm_compute/core/CL/kernels/CLBatchConcatenateLayerKernel.h new file mode 100644 index 0000000000..69571ad499 --- /dev/null +++ b/arm_compute/core/CL/kernels/CLBatchConcatenateLayerKernel.h @@ -0,0 +1,83 @@ +/* + * Copyright (c) 2019 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_CLBATCHCONCATENATEKERNEL_H__ +#define __ARM_COMPUTE_CLBATCHCONCATENATEKERNEL_H__ + +#include "arm_compute/core/CL/ICLKernel.h" +#include "arm_compute/core/Types.h" + +namespace arm_compute +{ +class ICLTensor; + +/** Interface for the batch concatenate kernel. + * The input tensor will be concatenated into the output tensor. + */ +class CLBatchConcatenateLayerKernel : public ICLKernel +{ +public: + /** Default constructor */ + CLBatchConcatenateLayerKernel(); + /** Prevent instances of this class from being copied (As this class contains pointers) */ + CLBatchConcatenateLayerKernel(const CLBatchConcatenateLayerKernel &) = delete; + /** Prevent instances of this class from being copied (As this class contains pointers) */ + CLBatchConcatenateLayerKernel &operator=(const CLBatchConcatenateLayerKernel &) = delete; + /** Allow instances of this class to be moved */ + CLBatchConcatenateLayerKernel(CLBatchConcatenateLayerKernel &&) = default; + /** Allow instances of this class to be moved */ + CLBatchConcatenateLayerKernel &operator=(CLBatchConcatenateLayerKernel &&) = default; + /** Default destructor */ + ~CLBatchConcatenateLayerKernel() = default; + /** Initialise the kernel's inputs and output + * + * @param[in] input Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32. + * @param[in] batch_offset The offset on axis # 3. + * @param[in,out] output Output tensor. Data types supported: Same as @p input. + * + * @note: The output tensor's low two dimensions can't be smaller than the input one's. + * @note: The gaps between the two lowest dimensions of input and output need to be divisible by 2. + * + */ + void configure(const ICLTensor *input, unsigned int batch_offset, ICLTensor *output); + /** Static function to check if given info will lead to a valid configuration of @ref CLBatchConcatenateLayerKernel + * + * @param[in] input Input tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32 + * @param[in] batch_offset The offset on axis # 3. + * @param[in] output Output tensor info. Data types supported: Same as @p input. + * + * @return a status + */ + static Status validate(const ITensorInfo *input, unsigned int batch_offset, const ITensorInfo *output); + + // Inherited methods overridden: + void run(const Window &window, cl::CommandQueue &queue) override; + +private: + const ICLTensor *_input; + ICLTensor *_output; + unsigned int _batch_offset; +}; +} // namespace arm_compute +#endif /* __ARM_COMPUTE_CLBATCHCONCATENATEKERNEL_H__ */ |