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
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010-2014 ARM Limited. All rights reserved.
*
* $Date: 12. March 2014
* $Revision: V1.4.4
*
* Project: CMSIS DSP Library
* Title: arm_rms_q15.c
*
* Description: Root Mean Square of the elements of a Q15 vector.
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
* - Neither the name of ARM LIMITED nor the names of its contributors
* may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
* ---------------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @addtogroup RMS
* @{
*/
/**
* @brief Root Mean Square 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 rms 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_rms_q15(
q15_t * pSrc,
uint32_t blockSize,
q15_t * pResult)
{
q63_t sum = 0; /* accumulator */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in; /* temporary variable to store the input value */
q15_t in1; /* temporary variable to store the input value */
uint32_t blkCnt; /* loop counter */
/* 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 the squares and then store the results in a temporary variable, sum */
in = *__SIMD32(pSrc)++;
sum = __SMLALD(in, in, sum);
in = *__SIMD32(pSrc)++;
sum = __SMLALD(in, in, sum);
/* 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 the squares and then store the results in a temporary variable, sum */
in1 = *pSrc++;
sum = __SMLALD(in1, in1, sum);
/* Decrement the loop counter */
blkCnt--;
}
/* Truncating and saturating the accumulator to 1.15 format */
/* Store the result in the destination */
arm_sqrt_q15(__SSAT((sum / (q63_t)blockSize) >> 15, 16), pResult);
#else
/* Run the below code for Cortex-M0 */
q15_t in; /* temporary variable to store the input value */
uint32_t blkCnt; /* loop counter */
/* 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 the squares and then store the results in a temporary variable, sum */
in = *pSrc++;
sum += ((q31_t) in * in);
/* Decrement the loop counter */
blkCnt--;
}
/* Truncating and saturating the accumulator to 1.15 format */
/* Store the result in the destination */
arm_sqrt_q15(__SSAT((sum / (q63_t)blockSize) >> 15, 16), pResult);
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
/**
* @} end of RMS group
*/
|
