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
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_cmplx_mag_q31.c
*
* Description: Q31 complex magnitude
*
* 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 groupCmplxMath
*/
/**
* @addtogroup cmplx_mag
* @{
*/
/**
* @brief Q31 complex magnitude
* @param *pSrc points to the complex input vector
* @param *pDst points to the real output vector
* @param numSamples number of complex samples in the input vector
* @return none.
*
* <b>Scaling and Overflow Behavior:</b>
* \par
* The function implements 1.31 by 1.31 multiplications and finally output is converted into 2.30 format.
* Input down scaling is not required.
*/
void arm_cmplx_mag_q31(
q31_t * pSrc,
q31_t * pDst,
uint32_t numSamples)
{
q31_t real, imag; /* Temporary variables to hold input values */
q31_t acc0, acc1; /* Accumulators */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t real1, real2, imag1, imag2; /* Temporary variables to hold input values */
q31_t out1, out2, out3, out4; /* Accumulators */
q63_t mul1, mul2, mul3, mul4; /* Temporary variables */
/*loop Unrolling */
blkCnt = numSamples >> 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)
{
/* read complex input from source buffer */
real1 = pSrc[0];
imag1 = pSrc[1];
real2 = pSrc[2];
imag2 = pSrc[3];
/* calculate power of input values */
mul1 = (q63_t) real1 *real1;
mul2 = (q63_t) imag1 *imag1;
mul3 = (q63_t) real2 *real2;
mul4 = (q63_t) imag2 *imag2;
/* get the result to 3.29 format */
out1 = (q31_t) (mul1 >> 33);
out2 = (q31_t) (mul2 >> 33);
out3 = (q31_t) (mul3 >> 33);
out4 = (q31_t) (mul4 >> 33);
/* add real and imaginary accumulators */
out1 = out1 + out2;
out3 = out3 + out4;
/* read complex input from source buffer */
real1 = pSrc[4];
imag1 = pSrc[5];
real2 = pSrc[6];
imag2 = pSrc[7];
/* calculate square root */
arm_sqrt_q31(out1, &pDst[0]);
/* calculate power of input values */
mul1 = (q63_t) real1 *real1;
/* calculate square root */
arm_sqrt_q31(out3, &pDst[1]);
/* calculate power of input values */
mul2 = (q63_t) imag1 *imag1;
mul3 = (q63_t) real2 *real2;
mul4 = (q63_t) imag2 *imag2;
/* get the result to 3.29 format */
out1 = (q31_t) (mul1 >> 33);
out2 = (q31_t) (mul2 >> 33);
out3 = (q31_t) (mul3 >> 33);
out4 = (q31_t) (mul4 >> 33);
/* add real and imaginary accumulators */
out1 = out1 + out2;
out3 = out3 + out4;
/* calculate square root */
arm_sqrt_q31(out1, &pDst[2]);
/* increment destination by 8 to process next samples */
pSrc += 8u;
/* calculate square root */
arm_sqrt_q31(out3, &pDst[3]);
/* increment destination by 4 to process next samples */
pDst += 4u;
/* Decrement the loop counter */
blkCnt--;
}
/* If the numSamples is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = numSamples % 0x4u;
#else
/* Run the below code for Cortex-M0 */
blkCnt = numSamples;
#endif /* #ifndef ARM_MATH_CM0 */
while(blkCnt > 0u)
{
/* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
real = *pSrc++;
imag = *pSrc++;
acc0 = (q31_t) (((q63_t) real * real) >> 33);
acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
/* store the result in 2.30 format in the destination buffer. */
arm_sqrt_q31(acc0 + acc1, pDst++);
/* Decrement the loop counter */
blkCnt--;
}
}
/**
* @} end of cmplx_mag group
*/
|
