arm_concatenation_s8_z.c 2.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74
/*
 * Copyright (C) 2010-2019 Arm Limited or its affiliates. All rights reserved.
 *
 * SPDX-License-Identifier: Apache-2.0
 *
 * Licensed under the Apache License, Version 2.0 (the License); you may
 * not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

/* ----------------------------------------------------------------------
 * Project:      CMSIS NN Library
 * Title:        arm_concatenation_s8_z.c
 * Description:  s8 version of concatenation along the Z axis
 *
 * $Date:        October 2019
 * $Revision:    V.1.0.0
 *
 * Target Processor:  Cortex-M cores
 *
 * -------------------------------------------------------------------- */

#include "cmsis/CMSIS/NN/Include/arm_nnfunctions.h"

/**
 *  @ingroup groupNN
 */

/**
 * @addtogroup Concatenation
 * @{
 */

  /*
   *  s8 version of concatenation along the Z axis
   *
   * Refer to header file for details.
   *
   */
void arm_concatenation_s8_z(const int8_t *input,
                            const uint16_t input_x,
                            const uint16_t input_y,
                            const uint16_t input_z,
                            const uint16_t input_w,
                            int8_t *output,
                            const uint16_t output_z,
                            const uint32_t offset_z)
{
    const uint32_t input_copy_size = input_x * input_y * input_z;
    const uint32_t output_stride   = input_x * input_y * output_z;

    output += offset_z * (input_x * input_y);

    uint32_t i;

    for (i = 0; i < input_w; ++i)
    {
        memcpy(output, input, input_copy_size);
        input  += input_copy_size;
        output += output_stride;
    }
}

/**
 * @} end of Concatenation group
 */