arm_mean_q15.c 4.1 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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_mean_q15.c
 * Description:  Mean value of a Q15 vector
 *
 * $Date:        23 April 2021
 * $Revision:    V1.9.0
 *
 * Target Processor: Cortex-M and Cortex-A cores
 * -------------------------------------------------------------------- */
/*
 * Copyright (C) 2010-2021 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.
 */

#include "dsp/statistics_functions.h"

/**
  @ingroup groupStats
 */

/**
  @addtogroup mean
  @{
 */

/**
  @brief         Mean value of a Q15 vector.
  @param[in]     pSrc       points to the input vector
  @param[in]     blockSize  number of samples in input vector
  @param[out]    pResult    mean value returned here
  @return        none

  @par           Scaling and Overflow Behavior
                   The function is implemented using a 32-bit internal accumulator.
                   The input is represented in 1.15 format and is accumulated in a 32-bit
                   accumulator in 17.15 format.
                   There is no risk of internal overflow with this approach, and the
                   full precision of intermediate result is preserved.
                   Finally, the accumulator is truncated to yield a result of 1.15 format.
 */

#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_mean_q15(
  const q15_t * pSrc,
        uint32_t blockSize,
        q15_t * pResult)
{
    uint32_t  blkCnt;           /* loop counters */
    q15x8_t  vecSrc;
    q31_t     sum = 0L;

    /* Compute 8 outputs at a time */
    blkCnt = blockSize >> 3U;
    while (blkCnt > 0U)
    {
        vecSrc = vldrhq_s16(pSrc);
        /*
         * sum lanes
         */
        sum = vaddvaq(sum, vecSrc);

        blkCnt--;
        pSrc += 8;
    }

    /* Tail */
    blkCnt = blockSize & 0x7;

    while (blkCnt > 0U)
    {
       /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
       sum += *pSrc++;

       /* Decrement loop counter */
       blkCnt--;
    }

    /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize  */
    /* Store the result to the destination */
    *pResult = (q15_t) (sum / (int32_t) blockSize);
}
#else
void arm_mean_q15(
  const q15_t * pSrc,
        uint32_t blockSize,
        q15_t * pResult)
{
        uint32_t blkCnt;                               /* Loop counter */
        q31_t sum = 0;                                 /* Temporary result storage */

#if defined (ARM_MATH_LOOPUNROLL)
        q31_t in;
#endif

#if defined (ARM_MATH_LOOPUNROLL)

  /* Loop unrolling: Compute 4 outputs at a time */
  blkCnt = blockSize >> 2U;

  while (blkCnt > 0U)
  {
    /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
    in = read_q15x2_ia ((q15_t **) &pSrc);
    sum += ((in << 16U) >> 16U);
    sum +=  (in >> 16U);

    in = read_q15x2_ia ((q15_t **) &pSrc);
    sum += ((in << 16U) >> 16U);
    sum +=  (in >> 16U);

    /* Decrement the loop counter */
    blkCnt--;
  }

  /* Loop unrolling: Compute remaining outputs */
  blkCnt = blockSize % 0x4U;

#else

  /* Initialize blkCnt with number of samples */
  blkCnt = blockSize;

#endif /* #if defined (ARM_MATH_LOOPUNROLL) */

  while (blkCnt > 0U)
  {
    /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
    sum += *pSrc++;

    /* Decrement loop counter */
    blkCnt--;
  }

  /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize  */
  /* Store result to destination */
  *pResult = (q15_t) (sum / (int32_t) blockSize);
}
#endif /* defined(ARM_MATH_MVEI) */

/**
  @} end of mean group
 */