|
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_q15.c
|
|
|
9 *
|
|
|
10 * Description: Sum of the squares of the elements of a Q15 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 * @addtogroup power
|
|
|
49 * @{
|
|
|
50 */
|
|
|
51
|
|
|
52 /**
|
|
|
53 * @brief Sum of the squares of the elements of a Q15 vector.
|
|
|
54 * @param[in] *pSrc points to the input vector
|
|
|
55 * @param[in] blockSize length of the input vector
|
|
|
56 * @param[out] *pResult sum of the squares value returned here
|
|
|
57 * @return none.
|
|
|
58 *
|
|
|
59 * @details
|
|
|
60 * <b>Scaling and Overflow Behavior:</b>
|
|
|
61 *
|
|
|
62 * \par
|
|
|
63 * The function is implemented using a 64-bit internal accumulator.
|
|
|
64 * The input is represented in 1.15 format.
|
|
|
65 * Intermediate multiplication yields a 2.30 format, and this
|
|
|
66 * result is added without saturation to a 64-bit accumulator in 34.30 format.
|
|
|
67 * With 33 guard bits in the accumulator, there is no risk of overflow, and the
|
|
|
68 * full precision of the intermediate multiplication is preserved.
|
|
|
69 * Finally, the return result is in 34.30 format.
|
|
|
70 *
|
|
|
71 */
|
|
|
72
|
|
|
73 void arm_power_q15(
|
|
|
74 q15_t * pSrc,
|
|
|
75 uint32_t blockSize,
|
|
|
76 q63_t * pResult)
|
|
|
77 {
|
|
|
78 q63_t sum = 0; /* Temporary result storage */
|
|
|
79
|
|
|
80 #ifndef ARM_MATH_CM0_FAMILY
|
|
|
81
|
|
|
82 /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
|
83
|
|
|
84 q31_t in32; /* Temporary variable to store input value */
|
|
|
85 q15_t in16; /* Temporary variable to store input value */
|
|
|
86 uint32_t blkCnt; /* loop counter */
|
|
|
87
|
|
|
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 in32 = *__SIMD32(pSrc)++;
|
|
|
99 sum = __SMLALD(in32, in32, sum);
|
|
|
100 in32 = *__SIMD32(pSrc)++;
|
|
|
101 sum = __SMLALD(in32, in32, sum);
|
|
|
102
|
|
|
103 /* Decrement the loop counter */
|
|
|
104 blkCnt--;
|
|
|
105 }
|
|
|
106
|
|
|
107 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|
|
108 ** No loop unrolling is used. */
|
|
|
109 blkCnt = blockSize % 0x4u;
|
|
|
110
|
|
|
111 while(blkCnt > 0u)
|
|
|
112 {
|
|
|
113 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
|
|
|
114 /* Compute Power and then store the result in a temporary variable, sum. */
|
|
|
115 in16 = *pSrc++;
|
|
|
116 sum = __SMLALD(in16, in16, sum);
|
|
|
117
|
|
|
118 /* Decrement the loop counter */
|
|
|
119 blkCnt--;
|
|
|
120 }
|
|
|
121
|
|
|
122 #else
|
|
|
123
|
|
|
124 /* Run the below code for Cortex-M0 */
|
|
|
125
|
|
|
126 q15_t in; /* Temporary variable to store input value */
|
|
|
127 uint32_t blkCnt; /* loop counter */
|
|
|
128
|
|
|
129
|
|
|
130 /* Loop over blockSize number of values */
|
|
|
131 blkCnt = blockSize;
|
|
|
132
|
|
|
133 while(blkCnt > 0u)
|
|
|
134 {
|
|
|
135 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
|
|
|
136 /* Compute Power and then store the result in a temporary variable, sum. */
|
|
|
137 in = *pSrc++;
|
|
|
138 sum += ((q31_t) in * in);
|
|
|
139
|
|
|
140 /* Decrement the loop counter */
|
|
|
141 blkCnt--;
|
|
|
142 }
|
|
|
143
|
|
|
144 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
|
|
|
145
|
|
|
146 /* Store the results in 34.30 format */
|
|
|
147 *pResult = sum;
|
|
|
148 }
|
|
|
149
|
|
|
150 /**
|
|
|
151 * @} end of power group
|
|
|
152 */
|
