File size: 4,528 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 | #include "edge-impulse-sdk/dsp/config.hpp"
#if EIDSP_LOAD_CMSIS_DSP_SOURCES
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_copy_f32.c
* Description: Copies the elements of a floating-point 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 "edge-impulse-sdk/CMSIS/DSP/Include/dsp/support_functions.h"
/**
@ingroup groupSupport
*/
/**
@defgroup copy Vector Copy
Copies sample by sample from source vector to destination vector.
<pre>
pDst[n] = pSrc[n]; 0 <= n < blockSize.
</pre>
There are separate functions for floating point, Q31, Q15, and Q7 data types.
*/
/**
@addtogroup copy
@{
*/
/**
@brief Copies the elements of a floating-point vector.
@param[in] pSrc points to input vector
@param[out] pDst points to output vector
@param[in] blockSize number of samples in each vector
@return none
*/
#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_copy_f32(
const float32_t * pSrc,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt;
blkCnt = blockSize >> 2U;
/* Compute 4 outputs at a time */
while (blkCnt > 0U)
{
vstrwq_f32(pDst, vldrwq_f32(pSrc));
/*
* Decrement the blockSize loop counter
* Advance vector source and destination pointers
*/
pSrc += 4;
pDst += 4;
blkCnt --;
}
blkCnt = blockSize & 3;
while (blkCnt > 0U)
{
/* C = A */
/* Copy and store result in destination buffer */
*pDst++ = *pSrc++;
/* Decrement loop counter */
blkCnt--;
}
}
#else
#if defined(ARM_MATH_NEON_EXPERIMENTAL)
void arm_copy_f32(
const float32_t * pSrc,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
float32x4_t inV;
blkCnt = blockSize >> 2U;
/* Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while (blkCnt > 0U)
{
/* C = A */
/* Copy and then store the results in the destination buffer */
inV = vld1q_f32(pSrc);
vst1q_f32(pDst, inV);
pSrc += 4;
pDst += 4;
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize & 3;
while (blkCnt > 0U)
{
/* C = A */
/* Copy and then store the results in the destination buffer */
*pDst++ = *pSrc++;
/* Decrement the loop counter */
blkCnt--;
}
}
#else
void arm_copy_f32(
const float32_t * pSrc,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* Loop counter */
#if defined (ARM_MATH_LOOPUNROLL)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A */
/* Copy and store result in destination buffer */
*pDst++ = *pSrc++;
*pDst++ = *pSrc++;
*pDst++ = *pSrc++;
*pDst++ = *pSrc++;
/* Decrement 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 */
/* Copy and store result in destination buffer */
*pDst++ = *pSrc++;
/* Decrement loop counter */
blkCnt--;
}
}
#endif /* #if defined(ARM_MATH_NEON) */
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of BasicCopy group
*/
#endif // EIDSP_LOAD_CMSIS_DSP_SOURCES
|