1 /* 2 * Copyright (c) 2017-2022 Arm Limited. 3 * 4 * SPDX-License-Identifier: MIT 5 * 6 * Permission is hereby granted, free of charge, to any person obtaining a copy 7 * of this software and associated documentation files (the "Software"), to 8 * deal in the Software without restriction, including without limitation the 9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or 10 * sell copies of the Software, and to permit persons to whom the Software is 11 * furnished to do so, subject to the following conditions: 12 * 13 * The above copyright notice and this permission notice shall be included in all 14 * copies or substantial portions of the Software. 15 * 16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 22 * SOFTWARE. 23 */ 24 25 #ifndef ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H 26 #define ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H 27 28 #include "src/core/common/Macros.h" 29 #include "src/cpu/ICpuKernel.h" 30 31 namespace arm_compute 32 { 33 // Forward declarations 34 class ITensor; 35 36 namespace cpu 37 { 38 namespace kernels 39 { 40 /** Interface for the depth concatenate kernel. 41 * The input tensor will be concatenated into the output tensor. 42 */ 43 class CpuConcatenateDepthKernel : public ICpuKernel<CpuConcatenateDepthKernel> 44 { 45 public: 46 CpuConcatenateDepthKernel() = default; 47 ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuConcatenateDepthKernel); 48 /** Configure kernel for a given list of arguments 49 * 50 * @param[in] src Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. 51 * @param[in] depth_offset The offset on the Z axis. 52 * @param[in,out] dst Destination tensor info. Data types supported: Same as @p src. 53 * 54 * @note: The output tensor's low two dimensions can't be smaller than the input one's. 55 * @note: The gaps between the two lowest dimensions of input and output need to be divisible by 2. 56 * 57 */ 58 void configure(const ITensorInfo *src, unsigned int depth_offset, ITensorInfo *dst); 59 /** Static function to check if given info will lead to a valid configuration 60 * 61 * Similar to @ref CpuConcatenateDepthKernel::configure() 62 * 63 * @return a status 64 */ 65 static Status validate(const ITensorInfo *src, unsigned int depth_offset, const ITensorInfo *dst); 66 67 // Inherited methods overridden: 68 void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override; 69 const char *name() const override; 70 71 private: 72 using DepthConcatFunction = void(const ITensor *, ITensor *, unsigned int, const Window &); 73 74 private: 75 DepthConcatFunction *_func{ nullptr }; 76 unsigned int _depth_offset{ 0 }; 77 }; 78 } // namespace kernels 79 } // namespace cpu 80 } // namespace arm_compute 81 #endif /* ARM_COMPUTE_CPU_CONCATENATE_DEPTH_KERNEL_H */ 82