blob: a34c011bc1445f4cdfbeacaf659ec6df1f2dab84 (
plain) (
blame)
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
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_mean_q7.c
*
* Description: Mean value of a Q7 vector.
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Version 1.1.0 2012/02/15
* Updated with more optimizations, bug fixes and minor API changes.
*
* Version 1.0.10 2011/7/15
* Big Endian support added and Merged M0 and M3/M4 Source code.
*
* Version 1.0.3 2010/11/29
* Re-organized the CMSIS folders and updated documentation.
*
* Version 1.0.2 2010/11/11
* Documentation updated.
*
* Version 1.0.1 2010/10/05
* Production release and review comments incorporated.
*
* Version 1.0.0 2010/09/20
* Production release and review comments incorporated.
* -------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupStats
*/
/**
* @addtogroup mean
* @{
*/
/**
* @brief Mean value of a Q7 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 32-bit internal accumulator.
* The input is represented in 1.7 format and is accumulated in a 32-bit
* accumulator in 25.7 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 1.7 format.
*
*/
void arm_mean_q7(
q7_t * pSrc,
uint32_t blockSize,
q7_t * pResult)
{
q31_t sum = 0; /* Temporary result storage */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in;
/*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]) */
in = *__SIMD32(pSrc)++;
sum += ((in << 24) >> 24);
sum += ((in << 16) >> 24);
sum += ((in << 8) >> 24);
sum += (in >> 24);
/* 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 /* #ifndef ARM_MATH_CM0 */
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 = (q7_t) (sum / (int32_t) blockSize);
}
/**
* @} end of mean group
*/
|