/github/workspace/src/StatisticsFunctions/kernels/plp_mean_i16s_rv32im.c

Functions

	Name
void	plp_mean_i16s_rv32im(const int16_t restrict pSrc, uint32_t blockSize, int16_t restrict pRes) Mean value of a 16-bit integer vector for RV32IM extension.

Functions Documentation

function plp_mean_i16s_rv32im

void plp_mean_i16s_rv32im(
    const int16_t *__restrict__ pSrc,
    uint32_t blockSize,
    int16_t *__restrict__ pRes
)

Mean value of a 16-bit integer vector for RV32IM extension.

Parameters:

• pSrc points to the input vector
• blockSize number of samples in input vector
• pRes mean value returned here

Return: none

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mean_i16s_rv32im.c
 * Description:  Kernel for calculation the mean of 16-Bit input vectors on RV32IM
 *
 * $Date:        01.07.2020
 *
 * Target Processor: PULP cores
 * ===================================================================== */
/*
 * Copyright (C) 2020 ETH Zurich and University of Bologna.
 *
 * Author: Moritz Scherer, ETH Zurich
 *
 * 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 "plp_math.h"

void plp_mean_i16s_rv32im(const int16_t *__restrict__ pSrc,
                          uint32_t blockSize,
                          int16_t *__restrict__ pRes) {

    int32_t blkCnt, tmpBS; /* Loop counter, temporal BlockSize */
    int32_t sum = 0;        /* Temporary return variable */

    int16_t x1, x2, x3, x4;

#if defined(PLP_MATH_LOOPUNROLL)

    if (blockSize > 3) {
        x1 = *pSrc++;
        x2 = *pSrc++;
        x3 = *pSrc++;
        x4 = *pSrc++;

        for(blkCnt = 0; blkCnt < (blockSize >> 2)-1; blkCnt++) {
            sum += x1;
            x1 = *pSrc++;
            sum += x2;
            x2 = *pSrc++;
            sum += x3;
            x3 = *pSrc++;
            sum += x4;
            x4 = *pSrc++;   
        }

        sum += x1;
        sum += x2;
        sum += x3;
        sum += x4;

        for(blkCnt = 0; blkCnt < (blockSize % 4); blkCnt++) {
            sum += (*pSrc++);
        }
    }
    else {
        for(blkCnt = 0; blkCnt < blockSize; blkCnt++) {
            sum += (*pSrc++);
        }
    }

#else // PLP_MATH_LOOPUNROLL

    for (blkCnt = 0; blkCnt < blockSize; blkCnt++) {
        sum += *pSrc++;
    }

#endif // PLP_MATH_LOOPUNROLL

    *pRes = ((sum) / (int32_t)blockSize);
}

---

Updated on 2023-03-01 at 16:16:33 +0000