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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mean_q31.c
* Description: Mean value of a Q31 vector
*
* $Date: 27. January 2017
* $Revision: V.1.5.1
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2017 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 "arm_math.h"
/**
* @ingroup groupStats
*/
/**
* @addtogroup mean
* @{
*/
/**
* @brief Mean value of a Q31 vector.
* @param[in] *pSrc points to the input vector
* @param[in] blockSize length of the input vector
* @param[out] *pResult mean value returned here
* @return none.
*
* @details
* <b>Scaling and Overflow Behavior:</b>
*\par
* The function is implemented using a 64-bit internal accumulator.
* The input is represented in 1.31 format and is accumulated in a 64-bit
* accumulator in 33.31 format.
* There is no risk of internal overflow with this approach, and the
* full precision of intermediate result is preserved.
* Finally, the accumulator is truncated to yield a result of 1.31 format.
*
*/
void arm_mean_q31(
q31_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q63_t sum = 0; /* Temporary result storage */
uint32_t blkCnt; /* loop counter */
#if defined (ARM_MATH_DSP)
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in1, in2, in3, in4;
/*loop Unrolling */
blkCnt = blockSize >> 2U;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while (blkCnt > 0U)
{
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
in1 = *pSrc++;
in2 = *pSrc++;
in3 = *pSrc++;
in4 = *pSrc++;
sum += in1;
sum += in2;
sum += in3;
sum += in4;
/* 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 % 0x4U;
#else
/* Run the below code for Cortex-M0 */
/* Loop over blockSize number of values */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_DSP) */
while (blkCnt > 0U)
{
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
sum += *pSrc++;
/* Decrement the loop counter */
blkCnt--;
}
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize */
/* Store the result to the destination */
*pResult = (q31_t) (sum / (int32_t) blockSize);
}
/**
* @} end of mean group
*/
|
