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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_power_f16.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_f16.h"
#if defined(ARM_FLOAT16_SUPPORTED)
/**
@ingroup groupStats
*/
/**
@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_MVE_FLOAT16) && !defined(ARM_MATH_AUTOVECTORIZE)
#include "arm_helium_utils.h"
void arm_power_f16(
const float16_t * pSrc,
uint32_t blockSize,
float16_t * pResult)
{
int32_t blkCnt; /* loop counters */
f16x8_t vecSrc;
f16x8_t sumVec = vdupq_n_f16(0.0f);
blkCnt = blockSize;
do {
mve_pred16_t p = vctp16q(blkCnt);
vecSrc = vldrhq_z_f16((float16_t const *) pSrc, p);
/*
* sum lanes
*/
sumVec = vfmaq_m(sumVec, vecSrc, vecSrc, p);
blkCnt -= 8;
pSrc += 8;
}
while (blkCnt > 0);
*pResult = vecAddAcrossF16Mve(sumVec);
}
#else
void arm_power_f16(
const float16_t * pSrc,
uint32_t blockSize,
float16_t * pResult)
{
uint32_t blkCnt; /* Loop counter */
_Float16 sum = 0.0f16; /* Temporary result storage */
_Float16 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 /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of power group
*/
#endif /* #if defined(ARM_FLOAT16_SUPPORTED) */
|
