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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_mult_f32.c
* Description: Floating-point vector multiplication
*
* $Date: 27. January 2017
* $Revision: V.1.5.1
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2017 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 groupMath
*/
/**
* @defgroup BasicMult Vector Multiplication
*
* Element-by-element multiplication of two vectors.
*
* <pre>
* pDst[n] = pSrcA[n] * pSrcB[n], 0 <= n < blockSize.
* </pre>
*
* There are separate functions for floating-point, Q7, Q15, and Q31 data types.
*/
/**
* @addtogroup BasicMult
* @{
*/
/**
* @brief Floating-point vector multiplication.
* @param[in] *pSrcA points to the first input vector
* @param[in] *pSrcB points to the second input vector
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in each vector
* @return none.
*/
void arm_mult_f32(
float32_t * pSrcA,
float32_t * pSrcB,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counters */
#if defined (ARM_MATH_DSP)
/* Run the below code for Cortex-M4 and Cortex-M3 */
float32_t inA1, inA2, inA3, inA4; /* temporary input variables */
float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
float32_t out1, out2, out3, out4; /* temporary output variables */
/* loop Unrolling */
blkCnt = blockSize >> 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)
{
/* C = A * B */
/* Multiply the inputs and store the results in output buffer */
/* read sample from sourceA */
inA1 = *pSrcA;
/* read sample from sourceB */
inB1 = *pSrcB;
/* read sample from sourceA */
inA2 = *(pSrcA + 1);
/* read sample from sourceB */
inB2 = *(pSrcB + 1);
/* out = sourceA * sourceB */
out1 = inA1 * inB1;
/* read sample from sourceA */
inA3 = *(pSrcA + 2);
/* read sample from sourceB */
inB3 = *(pSrcB + 2);
/* out = sourceA * sourceB */
out2 = inA2 * inB2;
/* read sample from sourceA */
inA4 = *(pSrcA + 3);
/* store result to destination buffer */
*pDst = out1;
/* read sample from sourceB */
inB4 = *(pSrcB + 3);
/* out = sourceA * sourceB */
out3 = inA3 * inB3;
/* store result to destination buffer */
*(pDst + 1) = out2;
/* out = sourceA * sourceB */
out4 = inA4 * inB4;
/* store result to destination buffer */
*(pDst + 2) = out3;
/* store result to destination buffer */
*(pDst + 3) = out4;
/* update pointers to process next samples */
pSrcA += 4U;
pSrcB += 4U;
pDst += 4U;
/* Decrement the blockSize loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4U;
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_DSP) */
while (blkCnt > 0U)
{
/* C = A * B */
/* Multiply the inputs and store the results in output buffer */
*pDst++ = (*pSrcA++) * (*pSrcB++);
/* Decrement the blockSize loop counter */
blkCnt--;
}
}
/**
* @} end of BasicMult group
*/
|
