summaryrefslogtreecommitdiff
path: root/hid-dials/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_var_q15.c
blob: ff9972aa4d9a7d0e4d5e90855aa8b9e601bb19e9 (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
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_var_q15.c
 * Description:  Variance of an array of Q15 type
 *
 * $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 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,
  q15_t * pResult)
{
  q31_t sum = 0;                                 /* Accumulator */
  q31_t meanOfSquares, squareOfMean;             /* square of mean and mean of square */
  uint32_t blkCnt;                               /* loop counter */
  q63_t sumOfSquares = 0;                        /* Accumulator */
#if defined (ARM_MATH_DSP)
  q31_t in;                                      /* input value */
  q15_t in1;                                     /* input value */
#else
  q15_t in;                                      /* input value */
#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 = *__SIMD32(pSrc)++;
    sum += ((in << 16U) >> 16U);
    sum +=  (in >> 16U);
    sumOfSquares = __SMLALD(in, in, sumOfSquares);
    in = *__SIMD32(pSrc)++;
    sum += ((in << 16U) >> 16U);
    sum +=  (in >> 16U);
    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++;
    sumOfSquares = __SMLALD(in1, in1, sumOfSquares);
    sum += in1;

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

  /* Compute Mean of squares of the input samples
   * and then store the result in a temporary variable, meanOfSquares. */
  meanOfSquares = (q31_t)(sumOfSquares / (q63_t)(blockSize - 1U));

  /* Compute square of mean */
  squareOfMean = (q31_t)((q63_t)sum * sum / (q63_t)(blockSize * (blockSize - 1U)));

  /* mean of the squares minus the square of the mean. */
  *pResult = (meanOfSquares - squareOfMean) >> 15U;

#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[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. */
  meanOfSquares = (q31_t)(sumOfSquares / (q63_t)(blockSize - 1U));

  /* Compute square of mean */
  squareOfMean = (q31_t)((q63_t)sum * sum / (q63_t)(blockSize * (blockSize - 1U)));

  /* mean of the squares minus the square of the mean. */
  *pResult = (meanOfSquares - squareOfMean) >> 15;

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

/**
 * @} end of variance group
 */