/github/workspace/src/BasicMathFunctions/mult/kernels/plp_mult_i32s_xpulpv2.c

Functions

	Name
void	plp_mult_i32s_xpulpv2(const int32_t * pSrcA, const int32_t * pSrcB, int32_t * pDst, uint32_t blockSize) Element-by-element multiplication of 32-bit integer vectors kernel for XPULPV2 extension.

Functions Documentation

function plp_mult_i32s_xpulpv2

void plp_mult_i32s_xpulpv2(
    const int32_t * pSrcA,
    const int32_t * pSrcB,
    int32_t * pDst,
    uint32_t blockSize
)

Element-by-element multiplication of 32-bit integer vectors kernel for XPULPV2 extension.

Parameters:

• pSrcA points to first input vector
• pSrcB points to second input vector
• pDst points to output vector
• blockSize number of samples in each vector

Return: none

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mult_i32s_xpulpv2.c
 * Description:  32-bit integer vector multiplication kernel for XPULPV2
 *
 * $Date:        30. July 2020
 * $Revision:    V0
 *
 * Target Processor: PULP cores
 * ===================================================================== */
/*
 * Copyright (C) 2020 ETH Zurich and University of Bologna. 
 *
 * Author: Xiaying Wang, 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.
 *
 * Notice: project inspired by ARM CMSIS DSP and parts of source code
 * ported and adopted for RISC-V PULP platform from ARM CMSIS DSP
 * released under Copyright (C) 2010-2019 ARM Limited or its affiliates
 * with Apache-2.0.
 */


#include "plp_math.h"

void plp_mult_i32s_xpulpv2(const int32_t * pSrcA,
                 const int32_t * pSrcB,
                 int32_t * pDst,
                 uint32_t blockSize) {
  uint32_t blkCnt; /* Loop counter */

#if defined(PLP_MATH_LOOPUNROLL)

  /* Loop unrolling: Compute 2 outputs at a time */
  blkCnt = blockSize >> 1U;

  while (blkCnt > 0U)
    {
      /* C = A + B */

      /* Add and store result in destination buffer. */
      *pDst++ = (*pSrcA++) * (*pSrcB++);
      *pDst++ = (*pSrcA++) * (*pSrcB++);

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

  /* Loop unrolling: Compute remaining outputs */
  blkCnt = blockSize % 0x2U;

#else // PLP_MATH_LOOPUNROLL

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

#endif // PLP_MATH_LOOPUNROLL

  while (blkCnt > 0U)
    {
      /* C = A + B */

      /* Add and store result in destination buffer. */
      *pDst++ = (*pSrcA++) * (*pSrcB++);

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

}

---

Updated on 2023-03-01 at 16:16:32 +0000