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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_cmplx_mag_squared_q15.c
* Description: Q15 complex magnitude squared
*
* $Date: 23 April 2021
* $Revision: V1.9.0
*
* Target Processor: Cortex-M and Cortex-A cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2021 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 "dsp/complex_math_functions.h"
/**
@ingroup groupCmplxMath
*/
/**
@addtogroup cmplx_mag_squared
@{
*/
/**
@brief Q15 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
@par Scaling and Overflow Behavior
The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.
*/
#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_cmplx_mag_squared_q15(
const q15_t * pSrc,
q15_t * pDst,
uint32_t numSamples)
{
int32_t blockSize = numSamples; /* loop counters */
uint32_t blkCnt; /* loop counters */
q31_t in;
q31_t acc0; /* Accumulators */
q15x8x2_t vecSrc;
q15x8_t vReal, vImag;
q15x8_t vMagSq;
blkCnt = blockSize >> 3;
while (blkCnt > 0U)
{
vecSrc = vld2q(pSrc);
vReal = vmulhq(vecSrc.val[0], vecSrc.val[0]);
vImag = vmulhq(vecSrc.val[1], vecSrc.val[1]);
vMagSq = vqaddq(vReal, vImag);
vMagSq = vshrq(vMagSq, 1);
vst1q(pDst, vMagSq);
pSrc += 16;
pDst += 8;
/*
* Decrement the blkCnt loop counter
* Advance vector source and destination pointers
*/
blkCnt --;
}
/*
* tail
*/
blkCnt = blockSize & 7;
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
in = read_q15x2_ia ((q15_t **) &pSrc);
acc0 = __SMUAD(in, in);
/* store result in 3.13 format in destination buffer. */
*pDst++ = (q15_t) (acc0 >> 17);
/* Decrement loop counter */
blkCnt--;
}
}
#else
void arm_cmplx_mag_squared_q15(
const q15_t * pSrc,
q15_t * pDst,
uint32_t numSamples)
{
uint32_t blkCnt; /* Loop counter */
#if defined (ARM_MATH_DSP)
q31_t in;
q31_t acc0; /* Accumulators */
#else
q15_t real, imag; /* Temporary input variables */
q31_t acc0, acc1; /* Accumulators */
#endif
#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]) */
#if defined (ARM_MATH_DSP)
in = read_q15x2_ia (&pSrc);
acc0 = __SMUAD(in, in);
/* store result in 3.13 format in destination buffer. */
*pDst++ = (q15_t) (acc0 >> 17);
in = read_q15x2_ia (&pSrc);
acc0 = __SMUAD(in, in);
*pDst++ = (q15_t) (acc0 >> 17);
in = read_q15x2_ia (&pSrc);
acc0 = __SMUAD(in, in);
*pDst++ = (q15_t) (acc0 >> 17);
in = read_q15x2_ia (&pSrc);
acc0 = __SMUAD(in, in);
*pDst++ = (q15_t) (acc0 >> 17);
#else
real = *pSrc++;
imag = *pSrc++;
acc0 = ((q31_t) real * real);
acc1 = ((q31_t) imag * imag);
/* store result in 3.13 format in destination buffer. */
*pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
real = *pSrc++;
imag = *pSrc++;
acc0 = ((q31_t) real * real);
acc1 = ((q31_t) imag * imag);
*pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
real = *pSrc++;
imag = *pSrc++;
acc0 = ((q31_t) real * real);
acc1 = ((q31_t) imag * imag);
*pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
real = *pSrc++;
imag = *pSrc++;
acc0 = ((q31_t) real * real);
acc1 = ((q31_t) imag * imag);
*pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
#endif /* #if defined (ARM_MATH_DSP) */
/* 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) */
while (blkCnt > 0U)
{
/* C[0] = (A[0] * A[0] + A[1] * A[1]) */
#if defined (ARM_MATH_DSP)
in = read_q15x2_ia (&pSrc);
acc0 = __SMUAD(in, in);
/* store result in 3.13 format in destination buffer. */
*pDst++ = (q15_t) (acc0 >> 17);
#else
real = *pSrc++;
imag = *pSrc++;
acc0 = ((q31_t) real * real);
acc1 = ((q31_t) imag * imag);
/* store result in 3.13 format in destination buffer. */
*pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
#endif
/* Decrement loop counter */
blkCnt--;
}
}
#endif /* defined(ARM_MATH_MVEI) */
/**
@} end of cmplx_mag_squared group
*/
|
