1 /* ----------------------------------------------------------------------
2 * Copyright (C) 2010-2012 ARM Limited. All rights reserved.
3 *
4 * $Date: 17. January 2013
5 * $Revision: V1.4.0
6 *
7 * Project: CMSIS DSP Library
8 * Title: arm_dotproduct_example_f32.c
9 *
10 * Description: Example code computing dot product of two vectors.
11 *
12 * Target Processor: Cortex-M4/Cortex-M3
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 /**
42 * @addtogroup groupExamples
43 * @{
44 *
45 * @defgroup DotproductExample Dot Product Example
46 *
47 * \par Description:
48 * \par
49 * Demonstrates the use of the Multiply and Add functions to perform the dot product.
50 * The dot product of two vectors is obtained by multiplying corresponding elements
51 * and summing the products.
52
53 * \par Algorithm:
54 * \par
55 * The two input vectors \c A and \c B with length \c n, are multiplied element-by-element
56 * and then added to obtain dot product.
57 * \par
58 * This is denoted by the following equation:
59 * <pre> dotProduct = A[0] * B[0] + A[1] * B[1] + ... + A[n-1] * B[n-1]</pre>
60 *
61 * \par Block Diagram:
62 * \par
63 * \image html dotProduct.gif
64 *
65 * \par Variables Description:
66 * \par
67 * \li \c srcA_buf_f32 points to first input vector
68 * \li \c srcB_buf_f32 points to second input vector
69 * \li \c testOutput stores dot product of the two input vectors.
70 *
71 * \par CMSIS DSP Software Library Functions Used:
72 * \par
73 * - arm_mult_f32()
74 * - arm_add_f32()
75 *
76 * <b> Refer </b>
77 * \link arm_dotproduct_example_f32.c \endlink
78 *
79 * \example arm_dotproduct_example_f32.c
80 *
81 * @} */
82
83 #include <math.h>
84 #include "arm_math.h"
85
86 #if defined(SEMIHOSTING)
87 #include <stdio.h>
88 #endif
89
90 /* ----------------------------------------------------------------------
91 * Defines each of the tests performed
92 * ------------------------------------------------------------------- */
93 #define MAX_BLOCKSIZE 32
94 #define DELTA (0.000001f)
95
96 /* ----------------------------------------------------------------------
97 * Test input data for Floating point Dot Product example for 32-blockSize
98 * Generated by the MATLAB randn() function
99 * ------------------------------------------------------------------- */
100 /* ----------------------------------------------------------------------
101 ** Test input data of srcA for blockSize 32
102 ** ------------------------------------------------------------------- */
103 float32_t srcA_buf_f32[MAX_BLOCKSIZE] =
104 {
105 -0.4325648115282207, -1.6655843782380970, 0.1253323064748307,
106 0.2876764203585489, -1.1464713506814637, 1.1909154656429988,
107 1.1891642016521031, -0.0376332765933176, 0.3272923614086541,
108 0.1746391428209245, -0.1867085776814394, 0.7257905482933027,
109 -0.5883165430141887, 2.1831858181971011, -0.1363958830865957,
110 0.1139313135208096, 1.0667682113591888, 0.0592814605236053,
111 -0.0956484054836690, -0.8323494636500225, 0.2944108163926404,
112 -1.3361818579378040, 0.7143245518189522, 1.6235620644462707,
113 -0.6917757017022868, 0.8579966728282626, 1.2540014216025324,
114 -1.5937295764474768, -1.4409644319010200, 0.5711476236581780,
115 -0.3998855777153632, 0.6899973754643451
116 };
117
118 /* ----------------------------------------------------------------------
119 ** Test input data of srcB for blockSize 32
120 ** ------------------------------------------------------------------- */
121 float32_t srcB_buf_f32[MAX_BLOCKSIZE] =
122 {
123 1.7491401329284098, 0.1325982188803279, 0.3252281811989881,
124 -0.7938091410349637, 0.3149236145048914, -0.5272704888029532,
125 0.9322666565031119, 1.1646643544607362, -2.0456694357357357,
126 -0.6443728590041911, 1.7410657940825480, 0.4867684246821860,
127 1.0488288293660140, 1.4885752747099299, 1.2705014969484090,
128 -1.8561241921210170, 2.1343209047321410, 1.4358467535865909,
129 -0.9173023332875400, -1.1060770780029008, 0.8105708062681296,
130 0.6985430696369063, -0.4015827425012831, 1.2687512030669628,
131 -0.7836083053674872, 0.2132664971465569, 0.7878984786088954,
132 0.8966819356782295, -0.1869172943544062, 1.0131816724341454,
133 0.2484350696132857, 0.0596083377937976
134 };
135
136 /* Reference dot product output */
137 float32_t refDotProdOut = 5.9273644806352142;
138
139 /* ----------------------------------------------------------------------
140 * Declare Global variables
141 * ------------------------------------------------------------------- */
142 float32_t multOutput[MAX_BLOCKSIZE]; /* Intermediate output */
143 float32_t testOutput; /* Final ouput */
144
145 arm_status status; /* Status of the example */
146
main(void)147 int32_t main(void)
148 {
149 uint32_t i; /* Loop counter */
150 float32_t diff; /* Difference between reference and test outputs */
151
152 /* Multiplication of two input buffers */
153 arm_mult_f32(srcA_buf_f32, srcB_buf_f32, multOutput, MAX_BLOCKSIZE);
154
155 /* Accumulate the multiplication output values to
156 get the dot product of the two inputs */
157 for(i=0; i< MAX_BLOCKSIZE; i++)
158 {
159 arm_add_f32(&testOutput, &multOutput[i], &testOutput, 1);
160 }
161
162 /* absolute value of difference between ref and test */
163 diff = fabsf(refDotProdOut - testOutput);
164
165 /* Comparison of dot product value with reference */
166 status = (diff > DELTA) ? ARM_MATH_TEST_FAILURE : ARM_MATH_SUCCESS;
167
168 if (status != ARM_MATH_SUCCESS)
169 {
170 #if defined (SEMIHOSTING)
171 printf("FAILURE\n");
172 #else
173 while (1); /* main function does not return */
174 #endif
175 }
176 else
177 {
178 #if defined (SEMIHOSTING)
179 printf("SUCCESS\n");
180 #else
181 while (1); /* main function does not return */
182 #endif
183 }
184 }
185
186 /** \endlink */
187
