提交 | 用户 | age
|
483170
|
1 |
/* ---------------------------------------------------------------------- |
Q |
2 |
* Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
|
3 |
* |
|
4 |
* $Date: 19. March 2015 |
|
5 |
* $Revision: V.1.4.5 |
|
6 |
* |
|
7 |
* Project: CMSIS DSP Library |
|
8 |
* Title: arm_cmplx_mult_cmplx_q15.c |
|
9 |
* |
|
10 |
* Description: Q15 complex-by-complex multiplication |
|
11 |
* |
|
12 |
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
|
13 |
* |
|
14 |
* Redistribution and use in source and binary forms, with or without |
|
15 |
* modification, are permitted provided that the following conditions |
|
16 |
* are met: |
|
17 |
* - Redistributions of source code must retain the above copyright |
|
18 |
* notice, this list of conditions and the following disclaimer. |
|
19 |
* - Redistributions in binary form must reproduce the above copyright |
|
20 |
* notice, this list of conditions and the following disclaimer in |
|
21 |
* the documentation and/or other materials provided with the |
|
22 |
* distribution. |
|
23 |
* - Neither the name of ARM LIMITED nor the names of its contributors |
|
24 |
* may be used to endorse or promote products derived from this |
|
25 |
* software without specific prior written permission. |
|
26 |
* |
|
27 |
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
28 |
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
29 |
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
|
30 |
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
|
31 |
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
|
32 |
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
|
33 |
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
34 |
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
|
35 |
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
|
36 |
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
|
37 |
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
38 |
* POSSIBILITY OF SUCH DAMAGE. |
|
39 |
* -------------------------------------------------------------------- */ |
|
40 |
|
|
41 |
#include "arm_math.h" |
|
42 |
|
|
43 |
/** |
|
44 |
* @ingroup groupCmplxMath |
|
45 |
*/ |
|
46 |
|
|
47 |
/** |
|
48 |
* @addtogroup CmplxByCmplxMult |
|
49 |
* @{ |
|
50 |
*/ |
|
51 |
|
|
52 |
/** |
|
53 |
* @brief Q15 complex-by-complex multiplication |
|
54 |
* @param[in] *pSrcA points to the first input vector |
|
55 |
* @param[in] *pSrcB points to the second input vector |
|
56 |
* @param[out] *pDst points to the output vector |
|
57 |
* @param[in] numSamples number of complex samples in each vector |
|
58 |
* @return none. |
|
59 |
* |
|
60 |
* <b>Scaling and Overflow Behavior:</b> |
|
61 |
* \par |
|
62 |
* The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format. |
|
63 |
*/ |
|
64 |
|
|
65 |
void arm_cmplx_mult_cmplx_q15( |
|
66 |
q15_t * pSrcA, |
|
67 |
q15_t * pSrcB, |
|
68 |
q15_t * pDst, |
|
69 |
uint32_t numSamples) |
|
70 |
{ |
|
71 |
q15_t a, b, c, d; /* Temporary variables to store real and imaginary values */ |
|
72 |
|
|
73 |
#ifndef ARM_MATH_CM0_FAMILY |
|
74 |
|
|
75 |
/* Run the below code for Cortex-M4 and Cortex-M3 */ |
|
76 |
uint32_t blkCnt; /* loop counters */ |
|
77 |
|
|
78 |
/* loop Unrolling */ |
|
79 |
blkCnt = numSamples >> 2u; |
|
80 |
|
|
81 |
/* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
|
82 |
** a second loop below computes the remaining 1 to 3 samples. */ |
|
83 |
while(blkCnt > 0u) |
|
84 |
{ |
|
85 |
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
|
86 |
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
|
87 |
a = *pSrcA++; |
|
88 |
b = *pSrcA++; |
|
89 |
c = *pSrcB++; |
|
90 |
d = *pSrcB++; |
|
91 |
|
|
92 |
/* store the result in 3.13 format in the destination buffer. */ |
|
93 |
*pDst++ = |
|
94 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
95 |
/* store the result in 3.13 format in the destination buffer. */ |
|
96 |
*pDst++ = |
|
97 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
98 |
|
|
99 |
a = *pSrcA++; |
|
100 |
b = *pSrcA++; |
|
101 |
c = *pSrcB++; |
|
102 |
d = *pSrcB++; |
|
103 |
|
|
104 |
/* store the result in 3.13 format in the destination buffer. */ |
|
105 |
*pDst++ = |
|
106 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
107 |
/* store the result in 3.13 format in the destination buffer. */ |
|
108 |
*pDst++ = |
|
109 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
110 |
|
|
111 |
a = *pSrcA++; |
|
112 |
b = *pSrcA++; |
|
113 |
c = *pSrcB++; |
|
114 |
d = *pSrcB++; |
|
115 |
|
|
116 |
/* store the result in 3.13 format in the destination buffer. */ |
|
117 |
*pDst++ = |
|
118 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
119 |
/* store the result in 3.13 format in the destination buffer. */ |
|
120 |
*pDst++ = |
|
121 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
122 |
|
|
123 |
a = *pSrcA++; |
|
124 |
b = *pSrcA++; |
|
125 |
c = *pSrcB++; |
|
126 |
d = *pSrcB++; |
|
127 |
|
|
128 |
/* store the result in 3.13 format in the destination buffer. */ |
|
129 |
*pDst++ = |
|
130 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
131 |
/* store the result in 3.13 format in the destination buffer. */ |
|
132 |
*pDst++ = |
|
133 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
134 |
|
|
135 |
/* Decrement the blockSize loop counter */ |
|
136 |
blkCnt--; |
|
137 |
} |
|
138 |
|
|
139 |
/* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
|
140 |
** No loop unrolling is used. */ |
|
141 |
blkCnt = numSamples % 0x4u; |
|
142 |
|
|
143 |
while(blkCnt > 0u) |
|
144 |
{ |
|
145 |
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
|
146 |
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
|
147 |
a = *pSrcA++; |
|
148 |
b = *pSrcA++; |
|
149 |
c = *pSrcB++; |
|
150 |
d = *pSrcB++; |
|
151 |
|
|
152 |
/* store the result in 3.13 format in the destination buffer. */ |
|
153 |
*pDst++ = |
|
154 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
155 |
/* store the result in 3.13 format in the destination buffer. */ |
|
156 |
*pDst++ = |
|
157 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
158 |
|
|
159 |
/* Decrement the blockSize loop counter */ |
|
160 |
blkCnt--; |
|
161 |
} |
|
162 |
|
|
163 |
#else |
|
164 |
|
|
165 |
/* Run the below code for Cortex-M0 */ |
|
166 |
|
|
167 |
while(numSamples > 0u) |
|
168 |
{ |
|
169 |
/* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
|
170 |
/* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
|
171 |
a = *pSrcA++; |
|
172 |
b = *pSrcA++; |
|
173 |
c = *pSrcB++; |
|
174 |
d = *pSrcB++; |
|
175 |
|
|
176 |
/* store the result in 3.13 format in the destination buffer. */ |
|
177 |
*pDst++ = |
|
178 |
(q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
|
179 |
/* store the result in 3.13 format in the destination buffer. */ |
|
180 |
*pDst++ = |
|
181 |
(q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
|
182 |
|
|
183 |
/* Decrement the blockSize loop counter */ |
|
184 |
numSamples--; |
|
185 |
} |
|
186 |
|
|
187 |
#endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
|
188 |
|
|
189 |
} |
|
190 |
|
|
191 |
/** |
|
192 |
* @} end of CmplxByCmplxMult group |
|
193 |
*/ |