|
2
|
1 /* ----------------------------------------------------------------------
|
|
|
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_mult_f32.c
|
|
|
9 *
|
|
|
10 * Description: Floating-point vector 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 groupMath
|
|
|
45 */
|
|
|
46
|
|
|
47 /**
|
|
|
48 * @defgroup BasicMult Vector Multiplication
|
|
|
49 *
|
|
|
50 * Element-by-element multiplication of two vectors.
|
|
|
51 *
|
|
|
52 * <pre>
|
|
|
53 * pDst[n] = pSrcA[n] * pSrcB[n], 0 <= n < blockSize.
|
|
|
54 * </pre>
|
|
|
55 *
|
|
|
56 * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
|
|
57 */
|
|
|
58
|
|
|
59 /**
|
|
|
60 * @addtogroup BasicMult
|
|
|
61 * @{
|
|
|
62 */
|
|
|
63
|
|
|
64 /**
|
|
|
65 * @brief Floating-point vector multiplication.
|
|
|
66 * @param[in] *pSrcA points to the first input vector
|
|
|
67 * @param[in] *pSrcB points to the second input vector
|
|
|
68 * @param[out] *pDst points to the output vector
|
|
|
69 * @param[in] blockSize number of samples in each vector
|
|
|
70 * @return none.
|
|
|
71 */
|
|
|
72
|
|
|
73 void arm_mult_f32(
|
|
|
74 float32_t * pSrcA,
|
|
|
75 float32_t * pSrcB,
|
|
|
76 float32_t * pDst,
|
|
|
77 uint32_t blockSize)
|
|
|
78 {
|
|
|
79 uint32_t blkCnt; /* loop counters */
|
|
|
80 #ifndef ARM_MATH_CM0_FAMILY
|
|
|
81
|
|
|
82 /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
|
83 float32_t inA1, inA2, inA3, inA4; /* temporary input variables */
|
|
|
84 float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
|
|
|
85 float32_t out1, out2, out3, out4; /* temporary output variables */
|
|
|
86
|
|
|
87 /* loop Unrolling */
|
|
|
88 blkCnt = blockSize >> 2u;
|
|
|
89
|
|
|
90 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
|
|
91 ** a second loop below computes the remaining 1 to 3 samples. */
|
|
|
92 while(blkCnt > 0u)
|
|
|
93 {
|
|
|
94 /* C = A * B */
|
|
|
95 /* Multiply the inputs and store the results in output buffer */
|
|
|
96 /* read sample from sourceA */
|
|
|
97 inA1 = *pSrcA;
|
|
|
98 /* read sample from sourceB */
|
|
|
99 inB1 = *pSrcB;
|
|
|
100 /* read sample from sourceA */
|
|
|
101 inA2 = *(pSrcA + 1);
|
|
|
102 /* read sample from sourceB */
|
|
|
103 inB2 = *(pSrcB + 1);
|
|
|
104
|
|
|
105 /* out = sourceA * sourceB */
|
|
|
106 out1 = inA1 * inB1;
|
|
|
107
|
|
|
108 /* read sample from sourceA */
|
|
|
109 inA3 = *(pSrcA + 2);
|
|
|
110 /* read sample from sourceB */
|
|
|
111 inB3 = *(pSrcB + 2);
|
|
|
112
|
|
|
113 /* out = sourceA * sourceB */
|
|
|
114 out2 = inA2 * inB2;
|
|
|
115
|
|
|
116 /* read sample from sourceA */
|
|
|
117 inA4 = *(pSrcA + 3);
|
|
|
118
|
|
|
119 /* store result to destination buffer */
|
|
|
120 *pDst = out1;
|
|
|
121
|
|
|
122 /* read sample from sourceB */
|
|
|
123 inB4 = *(pSrcB + 3);
|
|
|
124
|
|
|
125 /* out = sourceA * sourceB */
|
|
|
126 out3 = inA3 * inB3;
|
|
|
127
|
|
|
128 /* store result to destination buffer */
|
|
|
129 *(pDst + 1) = out2;
|
|
|
130
|
|
|
131 /* out = sourceA * sourceB */
|
|
|
132 out4 = inA4 * inB4;
|
|
|
133 /* store result to destination buffer */
|
|
|
134 *(pDst + 2) = out3;
|
|
|
135 /* store result to destination buffer */
|
|
|
136 *(pDst + 3) = out4;
|
|
|
137
|
|
|
138
|
|
|
139 /* update pointers to process next samples */
|
|
|
140 pSrcA += 4u;
|
|
|
141 pSrcB += 4u;
|
|
|
142 pDst += 4u;
|
|
|
143
|
|
|
144 /* Decrement the blockSize loop counter */
|
|
|
145 blkCnt--;
|
|
|
146 }
|
|
|
147
|
|
|
148 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|
|
149 ** No loop unrolling is used. */
|
|
|
150 blkCnt = blockSize % 0x4u;
|
|
|
151
|
|
|
152 #else
|
|
|
153
|
|
|
154 /* Run the below code for Cortex-M0 */
|
|
|
155
|
|
|
156 /* Initialize blkCnt with number of samples */
|
|
|
157 blkCnt = blockSize;
|
|
|
158
|
|
|
159 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
|
|
|
160
|
|
|
161 while(blkCnt > 0u)
|
|
|
162 {
|
|
|
163 /* C = A * B */
|
|
|
164 /* Multiply the inputs and store the results in output buffer */
|
|
|
165 *pDst++ = (*pSrcA++) * (*pSrcB++);
|
|
|
166
|
|
|
167 /* Decrement the blockSize loop counter */
|
|
|
168 blkCnt--;
|
|
|
169 }
|
|
|
170 }
|
|
|
171
|
|
|
172 /**
|
|
|
173 * @} end of BasicMult group
|
|
|
174 */
|
