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
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_var_q15.c
*
* Description: Variance of an array of Q15 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 variance
* @{
*/
/**
* @brief Variance of the elements of a Q15 vector.
* @param[in] *pSrc points to the input vector
* @param[in] blockSize length of the input vector
* @param[out] *pResult variance 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 1.15 format.
* Intermediate multiplication yields a 2.30 format, and this
* result is added without saturation to a 64-bit accumulator in 34.30 format.
* With 33 guard bits in the accumulator, there is no risk of overflow, and the
* full precision of the intermediate multiplication is preserved.
* Finally, the 34.30 result is truncated to 34.15 format by discarding the lower
* 15 bits, and then saturated to yield a result in 1.15 format.
*
*/
void arm_var_q15(
q15_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q31_t sum = 0; /* Accumulator */
q31_t meanOfSquares, squareOfMean; /* Mean of square and square of mean */
q15_t mean; /* mean */
uint32_t blkCnt; /* loop counter */
q15_t t; /* Temporary variable */
q63_t sumOfSquares = 0; /* Accumulator */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in; /* Input variable */
q15_t in1; /* Temporary variable */
/*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 = *__SIMD32(pSrc)++;
sum += ((in << 16) >> 16);
sum += (in >> 16);
sumOfSquares = __SMLALD(in, in, sumOfSquares);
in = *__SIMD32(pSrc)++;
sum += ((in << 16) >> 16);
sum += (in >> 16);
sumOfSquares = __SMLALD(in, in, sumOfSquares);
/* 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. */
in1 = *pSrc++;
sum += in1;
sumOfSquares = __SMLALD(in1, in1, sumOfSquares);
/* Decrement the loop counter */
blkCnt--;
}
/* Compute Mean of squares of the input samples
* and then store the result in a temporary variable, meanOfSquares. */
t = (q15_t) ((1.0f / (float32_t) (blockSize - 1u)) * 16384);
sumOfSquares = __SSAT((sumOfSquares >> 15u), 16u);
meanOfSquares = (q31_t) ((sumOfSquares * t) >> 14u);
#else
/* Run the below code for Cortex-M0 */
q15_t in; /* Temporary variable */
/* 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 += (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 = (q15_t) ((1.0f / (float32_t) (blockSize - 1u)) * 16384);
sumOfSquares = __SSAT((sumOfSquares >> 15u), 16u);
meanOfSquares = (q31_t) ((sumOfSquares * t) >> 14u);
#endif /* #ifndef ARM_MATH_CM0 */
/* Compute mean of all input values */
t = (q15_t) ((1.0f / (float32_t) (blockSize * (blockSize - 1u))) * 32768);
mean = __SSAT(sum, 16u);
/* Compute square of mean */
squareOfMean = ((q31_t) mean * mean) >> 15;
squareOfMean = (q31_t) (((q63_t) squareOfMean * t) >> 15);
/* Compute variance and then store the result to the destination */
*pResult = (meanOfSquares - squareOfMean);
}
/**
* @} end of variance group
*/
|
