blob: d441332a828d9a7ca06d5ef4bb2f00de6148db8c (
plain)
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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_copy_f16.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 "dsp/support_functions_f16.h"
#if defined(ARM_FLOAT16_SUPPORTED)
/**
@ingroup groupSupport
*/
/**
@addtogroup copy
@{
*/
/**
@brief Copies the elements of a f16 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_MVE_FLOAT16) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_copy_f16(
const float16_t * pSrc,
float16_t * pDst,
uint32_t blockSize)
{
do {
mve_pred16_t p = vctp16q(blockSize);
vstrhq_p_f16(pDst,
vldrhq_z_f16((float16_t const *) pSrc, p), p);
/*
* Decrement the blockSize loop counter
* Advance vector source and destination pointers
*/
pSrc += 8;
pDst += 8;
blockSize -= 8;
}
while ((int32_t) blockSize > 0);
}
#else
void arm_copy_f16(
const float16_t * pSrc,
float16_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 /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of BasicCopy group
*/
#endif /* #if defined(ARM_FLOAT16_SUPPORTED) */
|
