File size: 3,437 Bytes
25ade36 | 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 | #include "edge-impulse-sdk/dsp/config.hpp"
#if EIDSP_LOAD_CMSIS_DSP_SOURCES
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_accumulate_f64.c
* Description: Accumulation value of a floating-point vector
*
* $Date: 14 July 2022
* $Revision: V1.0.0
*
* 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 "edge-impulse-sdk/CMSIS/DSP/Include/dsp/basic_math_functions.h"
/**
@ingroup groupStats
*/
/**
@addtogroup Accumulation
@{
*/
/**
@brief Accumulation value of a floating-point vector.
@param[in] pSrc points to the input vector.
@param[in] blockSize number of samples in input vector.
@param[out] pResult sum of values in input vector.
@return none
*/
#if defined(ARM_MATH_NEON) && defined(__aarch64__)
void arm_accumulate_f64(
const float64_t * pSrc,
uint32_t blockSize,
float64_t * pResult)
{
uint32_t blkCnt; /* Loop counter */
/*Neon buffers*/
float64x2_t vSum = vdupq_n_f64(0.0);
float64x2_t afterLoad ;
float64_t sum = 0.; /* Temporary result storage */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize >> 1U;
while (blkCnt > 0U)
{
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
afterLoad = vld1q_f64(pSrc);
vSum = vaddq_f64(vSum, afterLoad);
/* Decrement loop counter */
blkCnt--;
pSrc += 2;
}
sum = vaddvq_f64(vSum);
/* Tail */
blkCnt = blockSize & 1 ;
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]) */
/* Store result to destination */
*pResult = sum;
}
#else
void arm_accumulate_f64(
const float64_t * pSrc,
uint32_t blockSize,
float64_t * pResult)
{
uint32_t blkCnt; /* Loop counter */
float64_t sum = 0.; /* Temporary result storage */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
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]) */
/* Store result to destination */
*pResult = sum;
}
#endif
/**
@} end of Accumulation group
*/
#endif // EIDSP_LOAD_CMSIS_DSP_SOURCES
|