Skip to content

/github/workspace/src/DistanceFunctions/plp_cosine_distance/kernels/plp_cosine_distance_f32s_rv32im.c

Functions

Name
void plp_cosine_distance_f32s_rv32im(const float32_t restrict pSrcA, const float32_t restrict pSrcB, uint32_t blockSize, float32_t *restrict pRes)
32-bit floating point cosine distance between two vectors

Functions Documentation

function plp_cosine_distance_f32s_rv32im

void plp_cosine_distance_f32s_rv32im(
    const float32_t *__restrict__ pSrcA,
    const float32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    float32_t *__restrict__ pRes
)

32-bit floating point cosine distance between two vectors

Parameters:

  • pA First vector
  • pB Second vector
  • blockSize vector length
  • pRes output result returned here

Return: none

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_cosine_distance_f32s_rv32im.c
 * Description:  32-bit floating point cosine_distance kernel for RV32IM
 *
 * $Date:        21 Mar 2022
 * $Revision:    V0
 *
 * Target Processor: PULP cores
 * ===================================================================== */
/*
 * Copyright (C) 2022 ETH Zurich and University of Bologna.
 *
 * Author: Marco Bertuletti 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_cosine_distance_f32s_rv32im(   const float32_t *__restrict__ pSrcA,
                                        const float32_t *__restrict__ pSrcB,
                                        uint32_t blockSize,
                                        float32_t *__restrict__ pRes) {
  float32_t pwrA, pwrB;
  float32_t dot, tmp;
  plp_power_f32s_rv32im(pSrcA, blockSize, &pwrA);
  plp_power_f32s_rv32im(pSrcB, blockSize, &pwrB);
  tmp = pwrA*pwrB;

  plp_dot_prod_f32s_rv32im(pSrcA, pSrcB, blockSize, &dot);
  plp_sqrt_f32s_rv32im(&tmp, &tmp);
  *pRes = 1.0f - dot/tmp;

}

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