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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_cmplx_mag_squared_f32.c
* Description: Floating-point complex magnitude squared
*
* $Date: 18. March 2019
* $Revision: V1.6.0
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2019 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 groupCmplxMath
*/
/**
@defgroup cmplx_mag_squared Complex Magnitude Squared
Computes the magnitude squared of the elements of a complex data vector.
The <code>pSrc</code> points to the source data and
<code>pDst</code> points to the where the result should be written.
<code>numSamples</code> specifies the number of complex samples
in the input array and the data is stored in an interleaved fashion
(real, imag, real, imag, ...).
The input array has a total of <code>2*numSamples</code> values;
the output array has a total of <code>numSamples</code> values.
The underlying algorithm is used:
<pre>
for (n = 0; n < numSamples; n++) {
pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2;
}
</pre>
There are separate functions for floating-point, Q15, and Q31 data types.
*/
/**
@addtogroup cmplx_mag_squared
@{
*/
/**
@brief Floating-point complex magnitude squared.
@param[in] pSrc points to input vector
@param[out] pDst points to output vector
@param[in] numSamples number of samples in each vector
@return none
*/
void arm_cmplx_mag_squared_f32(
const float32_t * pSrc,
float32_t * pDst,
uint32_t numSamples)
{
uint32_t blkCnt; /* Loop counter */
float32_t real, imag; /* Temporary input variables */
#if defined(ARM_MATH_NEON)
float32x4x2_t vecA;
float32x4_t vRealA;
float32x4_t vImagA;
float32x4_t vMagSqA;
float32x4x2_t vecB;
float32x4_t vRealB;
float32x4_t vImagB;
float32x4_t vMagSqB;
/* Loop unrolling: Compute 8 outputs at a time */
blkCnt = numSamples >> 3;
while (blkCnt > 0U)
{
/* out = sqrt((real * real) + (imag * imag)) */
vecA = vld2q_f32(pSrc);
pSrc += 8;
vRealA = vmulq_f32(vecA.val[0], vecA.val[0]);
vImagA = vmulq_f32(vecA.val[1], vecA.val[1]);
vMagSqA = vaddq_f32(vRealA, vImagA);
vecB = vld2q_f32(pSrc);
pSrc += 8;
vRealB = vmulq_f32(vecB.val[0], vecB.val[0]);
vImagB = vmulq_f32(vecB.val[1], vecB.val[1]);
vMagSqB = vaddq_f32(vRealB, vImagB);
/* Store the result in the destination buffer. */
vst1q_f32(pDst, vMagSqA);
pDst += 4;
vst1q_f32(pDst, vMagSqB);
pDst += 4;
/* Decrement the loop counter */
blkCnt--;
}
blkCnt = numSamples & 7;
#else
#if defined (ARM_MATH_LOOPUNROLL)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = numSamples >> 2U;
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
real = *pSrc++;
imag = *pSrc++;
*pDst++ = (real * real) + (imag * imag);
/* Decrement loop counter */
blkCnt--;
}
/* Loop unrolling: Compute remaining outputs */
blkCnt = numSamples % 0x4U;
#else
/* Initialize blkCnt with number of samples */
blkCnt = numSamples;
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
#endif /* #if defined(ARM_MATH_NEON) */
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
real = *pSrc++;
imag = *pSrc++;
/* store result in destination buffer. */
*pDst++ = (real * real) + (imag * imag);
/* Decrement loop counter */
blkCnt--;
}
}
/**
@} end of cmplx_mag_squared group
*/
|
