|
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_power_f32.c
|
|
|
9 *
|
|
|
10 * Description: Sum of the squares of the elements of a floating-point vector.
|
|
|
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 groupStats
|
|
|
45 */
|
|
|
46
|
|
|
47 /**
|
|
|
48 * @defgroup power Power
|
|
|
49 *
|
|
|
50 * Calculates the sum of the squares of the elements in the input vector.
|
|
|
51 * The underlying algorithm is used:
|
|
|
52 *
|
|
|
53 * <pre>
|
|
|
54 * Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];
|
|
|
55 * </pre>
|
|
|
56 *
|
|
|
57 * There are separate functions for floating point, Q31, Q15, and Q7 data types.
|
|
|
58 */
|
|
|
59
|
|
|
60 /**
|
|
|
61 * @addtogroup power
|
|
|
62 * @{
|
|
|
63 */
|
|
|
64
|
|
|
65
|
|
|
66 /**
|
|
|
67 * @brief Sum of the squares of the elements of a floating-point vector.
|
|
|
68 * @param[in] *pSrc points to the input vector
|
|
|
69 * @param[in] blockSize length of the input vector
|
|
|
70 * @param[out] *pResult sum of the squares value returned here
|
|
|
71 * @return none.
|
|
|
72 *
|
|
|
73 */
|
|
|
74
|
|
|
75
|
|
|
76 void arm_power_f32(
|
|
|
77 float32_t * pSrc,
|
|
|
78 uint32_t blockSize,
|
|
|
79 float32_t * pResult)
|
|
|
80 {
|
|
|
81 float32_t sum = 0.0f; /* accumulator */
|
|
|
82 float32_t in; /* Temporary variable to store input value */
|
|
|
83 uint32_t blkCnt; /* loop counter */
|
|
|
84
|
|
|
85 #ifndef ARM_MATH_CM0_FAMILY
|
|
|
86
|
|
|
87 /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
|
88
|
|
|
89 /*loop Unrolling */
|
|
|
90 blkCnt = blockSize >> 2u;
|
|
|
91
|
|
|
92 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
|
|
93 ** a second loop below computes the remaining 1 to 3 samples. */
|
|
|
94 while(blkCnt > 0u)
|
|
|
95 {
|
|
|
96 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
|
|
|
97 /* Compute Power and then store the result in a temporary variable, sum. */
|
|
|
98 in = *pSrc++;
|
|
|
99 sum += in * in;
|
|
|
100 in = *pSrc++;
|
|
|
101 sum += in * in;
|
|
|
102 in = *pSrc++;
|
|
|
103 sum += in * in;
|
|
|
104 in = *pSrc++;
|
|
|
105 sum += in * in;
|
|
|
106
|
|
|
107 /* Decrement the loop counter */
|
|
|
108 blkCnt--;
|
|
|
109 }
|
|
|
110
|
|
|
111 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|
|
112 ** No loop unrolling is used. */
|
|
|
113 blkCnt = blockSize % 0x4u;
|
|
|
114
|
|
|
115
|
|
|
116 #else
|
|
|
117
|
|
|
118 /* Run the below code for Cortex-M0 */
|
|
|
119
|
|
|
120 /* Loop over blockSize number of values */
|
|
|
121 blkCnt = blockSize;
|
|
|
122
|
|
|
123 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
|
|
|
124
|
|
|
125
|
|
|
126 while(blkCnt > 0u)
|
|
|
127 {
|
|
|
128 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
|
|
|
129 /* compute power and then store the result in a temporary variable, sum. */
|
|
|
130 in = *pSrc++;
|
|
|
131 sum += in * in;
|
|
|
132
|
|
|
133 /* Decrement the loop counter */
|
|
|
134 blkCnt--;
|
|
|
135 }
|
|
|
136
|
|
|
137 /* Store the result to the destination */
|
|
|
138 *pResult = sum;
|
|
|
139 }
|
|
|
140
|
|
|
141 /**
|
|
|
142 * @} end of power group
|
|
|
143 */
|
