summaryrefslogtreecommitdiff
path: root/Blink/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_std_f32.c
blob: e082fc60680e60b322eb1eddc919046cf6705e11 (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
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
185
186
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_std_f32.c
 * Description:  Standard deviation of the elements of a floating-point 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
 */

/**
 * @defgroup STD Standard deviation
 *
 * Calculates the standard deviation of the elements in the input vector.
 * The underlying algorithm is used:
 *
 * <pre>
 *   Result = sqrt((sumOfSquares - sum<sup>2</sup> / blockSize) / (blockSize - 1))
 *
 *     where, sumOfSquares = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]
 *
 *                     sum = pSrc[0] + pSrc[1] + pSrc[2] + ... + pSrc[blockSize-1]
 * </pre>
 *
 * There are separate functions for floating point, Q31, and Q15 data types.
 */

/**
 * @addtogroup STD
 * @{
 */


/**
 * @brief Standard deviation of the elements of a floating-point 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.
 */

void arm_std_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult)
{
  float32_t sum = 0.0f;                          /* Temporary result storage */
  float32_t sumOfSquares = 0.0f;                 /* Sum of squares */
  float32_t in;                                  /* input value */
  uint32_t blkCnt;                               /* loop counter */
#if defined (ARM_MATH_DSP)
  float32_t meanOfSquares, mean, squareOfMean;   /* Temporary variables */
#else
  float32_t squareOfSum;                         /* Square of Sum */
  float32_t var;                                 /* Temporary varaince storage */
#endif

  if (blockSize == 1U)
  {
    *pResult = 0;
    return;
  }

#if defined (ARM_MATH_DSP)
  /* 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 += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += 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 += in * in;

    /* Decrement the loop counter */
    blkCnt--;
  }

  /* Compute Mean of squares of the input samples
   * and then store the result in a temporary variable, meanOfSquares. */
  meanOfSquares = sumOfSquares / ((float32_t) blockSize - 1.0f);

  /* Compute mean of all input values */
  mean = sum / (float32_t) blockSize;

  /* Compute square of mean */
  squareOfMean = (mean * mean) * (((float32_t) blockSize) /
                                  ((float32_t) blockSize - 1.0f));

  /* Compute standard deviation and then store the result to the destination */
  arm_sqrt_f32((meanOfSquares - squareOfMean), pResult);

#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 += in * in;

    /* C = (A[0] + A[1] + ... + A[blockSize-1]) */
    /* Compute Sum of the input samples
     * and then store the result in a temporary variable, sum. */
    sum += in;

    /* Decrement the loop counter */
    blkCnt--;
  }

  /* Compute the square of sum */
  squareOfSum = ((sum * sum) / (float32_t) blockSize);

  /* Compute the variance */
  var = ((sumOfSquares - squareOfSum) / (float32_t) (blockSize - 1.0f));

  /* Compute standard deviation and then store the result to the destination */
  arm_sqrt_f32(var, pResult);

#endif /* #if defined (ARM_MATH_DSP) */
}

/**
 * @} end of STD group
 */