1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_power_f32.c
* Description: Sum of the squares of the elements of a floating-point vector
*
* $Date: 23 April 2021
* $Revision: V1.9.0
*
* Target Processor: Cortex-M and Cortex-A cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved.
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the License); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an AS IS BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "dsp/statistics_functions.h"
/**
@ingroup groupStats
*/
/**
@defgroup power Power
Calculates the sum of the squares of the elements in the input vector.
The underlying algorithm is used:
<pre>
Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];
</pre>
There are separate functions for floating point, Q31, Q15, and Q7 data types.
Since the result is not divided by the length, those functions are in fact computing
something which is more an energy than a power.
*/
/**
@addtogroup power
@{
*/
/**
@brief Sum of the squares of the elements of a floating-point vector.
@param[in] pSrc points to the input vector
@param[in] blockSize number of samples in input vector
@param[out] pResult sum of the squares value returned here
@return none
*/
#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE)
#include "arm_helium_utils.h"
void arm_power_f32(
const float32_t * pSrc,
uint32_t blockSize,
float32_t * pResult)
{
uint32_t blkCnt; /* loop counters */
f32x4_t vecSrc;
f32x4_t sumVec = vdupq_n_f32(0.0f);
float32_t sum = 0.0f;
float32_t in;
/* Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
vecSrc = vldrwq_f32(pSrc);
/*
* sum lanes
*/
sumVec = vfmaq(sumVec, vecSrc, vecSrc);
blkCnt --;
pSrc += 4;
}
sum = vecAddAcrossF32Mve(sumVec);
/*
* tail
*/
blkCnt = blockSize & 0x3;
while (blkCnt > 0U)
{
/* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and store result in a temporary variable, sum. */
in = *pSrc++;
sum += in * in;
/* Decrement loop counter */
blkCnt--;
}
*pResult = sum;
}
#else
#if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE)
void arm_power_f32(
const float32_t * pSrc,
uint32_t blockSize,
float32_t * pResult)
{
float32_t sum = 0.0f; /* accumulator */
float32_t in; /* Temporary variable to store input value */
uint32_t blkCnt; /* loop counter */
float32x4_t sumV = vdupq_n_f32(0.0f); /* Temporary result storage */
float32x2_t sumV2;
float32x4_t inV;
blkCnt = blockSize >> 2U;
/* Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while (blkCnt > 0U)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and then store the result in a temporary variable, sum. */
inV = vld1q_f32(pSrc);
sumV = vmlaq_f32(sumV, inV, inV);
pSrc += 4;
/* Decrement the loop counter */
blkCnt--;
}
sumV2 = vpadd_f32(vget_low_f32(sumV),vget_high_f32(sumV));
sum = vget_lane_f32(sumV2, 0) + vget_lane_f32(sumV2, 1);
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4U;
while (blkCnt > 0U)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* compute power and then store the result in a temporary variable, sum. */
in = *pSrc++;
sum += in * in;
/* Decrement the loop counter */
blkCnt--;
}
/* Store the result to the destination */
*pResult = sum;
}
#else
void arm_power_f32(
const float32_t * pSrc,
uint32_t blockSize,
float32_t * pResult)
{
uint32_t blkCnt; /* Loop counter */
float32_t sum = 0.0f; /* Temporary result storage */
float32_t in; /* Temporary variable to store input value */
#if defined (ARM_MATH_LOOPUNROLL) && !defined(ARM_MATH_AUTOVECTORIZE)
/* Loop unrolling: Compute 4 outputs at a time */
blkCnt = blockSize >> 2U;
while (blkCnt > 0U)
{
/* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and store result in a temporary variable, sum. */
in = *pSrc++;
sum += in * in;
in = *pSrc++;
sum += in * in;
in = *pSrc++;
sum += in * in;
in = *pSrc++;
sum += in * in;
/* Decrement loop counter */
blkCnt--;
}
/* Loop unrolling: Compute remaining outputs */
blkCnt = blockSize % 0x4U;
#else
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
while (blkCnt > 0U)
{
/* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and store result in a temporary variable, sum. */
in = *pSrc++;
sum += in * in;
/* Decrement loop counter */
blkCnt--;
}
/* Store result to destination */
*pResult = sum;
}
#endif /* #if defined(ARM_MATH_NEON) */
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of power group
*/
|
