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
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_std_q31.c
*
* Description: Standard deviation of an array of Q31 type.
*
* 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 STD
* @{
*/
/**
* @brief Standard deviation of the elements of a Q31 vector.
* @param[in] *pSrc points to the input vector
* @param[in] blockSize length of the input vector
* @param[out] *pResult standard deviation value returned here
* @return none.
* @details
* <b>Scaling and Overflow Behavior:</b>
*
*\par
* The function is implemented using an internal 64-bit accumulator.
* The input is represented in 1.31 format, and intermediate multiplication
* yields a 2.62 format.
* The accumulator maintains full precision of the intermediate multiplication results,
* but provides only a single guard bit.
* There is no saturation on intermediate additions.
* If the accumulator overflows it wraps around and distorts the result.
* In order to avoid overflows completely the input signal must be scaled down by
* log2(blockSize) bits, as a total of blockSize additions are performed internally.
* Finally, the 2.62 accumulator is right shifted by 31 bits to yield a 1.31 format value.
*
*/
void arm_std_q31(
q31_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q63_t sum = 0; /* Accumulator */
q31_t meanOfSquares, squareOfMean; /* square of mean and mean of square */
q31_t mean; /* mean */
q31_t in; /* input value */
q31_t t; /* Temporary variable */
uint32_t blkCnt; /* loop counter */
q63_t sumOfSquares = 0; /* Accumulator */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
/*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[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
/* Compute Sum of squares of the input samples
* and then store the result in a temporary variable, sum. */
in = *pSrc++;
sum += in;
sumOfSquares += ((q63_t) (in) * (in));
in = *pSrc++;
sum += in;
sumOfSquares += ((q63_t) (in) * (in));
in = *pSrc++;
sum += in;
sumOfSquares += ((q63_t) (in) * (in));
in = *pSrc++;
sum += in;
sumOfSquares += ((q63_t) (in) * (in));
/* 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;
while(blkCnt > 0u)
{
/* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
/* Compute Sum of squares of the input samples
* and then store the result in a temporary variable, sum. */
in = *pSrc++;
sum += in;
sumOfSquares += ((q63_t) (in) * (in));
/* Decrement the loop counter */
blkCnt--;
}
t = (q31_t) ((1.0f / (float32_t) (blockSize - 1u)) * 1073741824.0f);
/* Compute Mean of squares of the input samples
* and then store the result in a temporary variable, meanOfSquares. */
sumOfSquares = (sumOfSquares >> 31);
meanOfSquares = (q31_t) ((sumOfSquares * t) >> 30);
#else
/* Run the below code for Cortex-M0 */
/* Loop over blockSize number of values */
blkCnt = blockSize;
while(blkCnt > 0u)
{
/* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
/* Compute Sum of squares of the input samples
* and then store the result in a temporary variable, sumOfSquares. */
in = *pSrc++;
sumOfSquares += ((q63_t) (in) * (in));
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
/* Compute sum of all input values and then store the result in a temporary variable, sum. */
sum += in;
/* Decrement the loop counter */
blkCnt--;
}
/* Compute Mean of squares of the input samples
* and then store the result in a temporary variable, meanOfSquares. */
t = (q31_t) ((1.0f / (float32_t) (blockSize - 1u)) * 1073741824.0f);
sumOfSquares = (sumOfSquares >> 31);
meanOfSquares = (q31_t) ((sumOfSquares * t) >> 30);
#endif /* #ifndef ARM_MATH_CM0 */
/* Compute mean of all input values */
t = (q31_t) ((1.0f / (blockSize * (blockSize - 1u))) * 2147483648.0f);
mean = (q31_t) (sum);
/* Compute square of mean */
squareOfMean = (q31_t) (((q63_t) mean * mean) >> 31);
squareOfMean = (q31_t) (((q63_t) squareOfMean * t) >> 31);
/* Compute standard deviation and then store the result to the destination */
arm_sqrt_q31(meanOfSquares - squareOfMean, pResult);
}
/**
* @} end of STD group
*/
|
