提交 | 用户 | age
|
8b51c7
|
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_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 |
*/ |