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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_cmplx_mult_cmplx_f32.c
* Description: Floating-point complex-by-complex multiplication
*
* $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 CmplxByCmplxMult Complex-by-Complex Multiplication
Multiplies a complex vector by another complex vector and generates a complex result.
The data in the complex arrays is stored in an interleaved fashion
(real, imag, real, imag, ...).
The parameter <code>numSamples</code> represents the number of complex
samples processed. The complex arrays have a total of <code>2*numSamples</code>
real values.
The underlying algorithm is used:
<pre>
for (n = 0; n < numSamples; n++) {
pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];
pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];
}
</pre>
There are separate functions for floating-point, Q15, and Q31 data types.
*/
/**
@addtogroup CmplxByCmplxMult
@{
*/
/**
@brief Floating-point complex-by-complex multiplication.
@param[in] pSrcA points to first input vector
@param[in] pSrcB points to second input vector
@param[out] pDst points to output vector
@param[in] numSamples number of samples in each vector
@return none
*/
void arm_cmplx_mult_cmplx_f32(
const float32_t * pSrcA,
const float32_t * pSrcB,
float32_t * pDst,
uint32_t numSamples)
{
uint32_t blkCnt; /* Loop counter */
float32_t a, b, c, d; /* Temporary variables to store real and imaginary values */
#if defined(ARM_MATH_NEON)
float32x4x2_t va, vb;
float32x4_t real, imag;
float32x4x2_t outCplx;
/* Compute 4 outputs at a time */
blkCnt = numSamples >> 2U;
while (blkCnt > 0U)
{
va = vld2q_f32(pSrcA); // load & separate real/imag pSrcA (de-interleave 2)
vb = vld2q_f32(pSrcB); // load & separate real/imag pSrcB
/* Increment pointers */
pSrcA += 8;
pSrcB += 8;
/* Re{C} = Re{A}*Re{B} - Im{A}*Im{B} */
outCplx.val[0] = vmulq_f32(va.val[0], vb.val[0]);
outCplx.val[0] = vmlsq_f32(outCplx.val[0], va.val[1], vb.val[1]);
/* Im{C} = Re{A}*Im{B} + Im{A}*Re{B} */
outCplx.val[1] = vmulq_f32(va.val[0], vb.val[1]);
outCplx.val[1] = vmlaq_f32(outCplx.val[1], va.val[1], vb.val[0]);
vst2q_f32(pDst, outCplx);
/* Increment pointer */
pDst += 8;
/* Decrement the loop counter */
blkCnt--;
}
/* Tail */
blkCnt = numSamples & 3;
#else
#if defined (ARM_MATH_LOOPUNROLL)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = numSamples >> 2U;
while (blkCnt > 0U)
{
/* C[2 * i ] = A[2 * i] * B[2 * i ] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i ]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
/* store result in destination buffer. */
*pDst++ = (a * c) - (b * d);
*pDst++ = (a * d) + (b * c);
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
*pDst++ = (a * c) - (b * d);
*pDst++ = (a * d) + (b * c);
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
*pDst++ = (a * c) - (b * d);
*pDst++ = (a * d) + (b * c);
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
*pDst++ = (a * c) - (b * d);
*pDst++ = (a * d) + (b * c);
/* 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[2 * i ] = A[2 * i] * B[2 * i ] - A[2 * i + 1] * B[2 * i + 1]. */
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i ]. */
a = *pSrcA++;
b = *pSrcA++;
c = *pSrcB++;
d = *pSrcB++;
/* store result in destination buffer. */
*pDst++ = (a * c) - (b * d);
*pDst++ = (a * d) + (b * c);
/* Decrement loop counter */
blkCnt--;
}
}
/**
@} end of CmplxByCmplxMult group
*/
|
