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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_clip_f32.c
* Description: Floating-point vector addition
*
* $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/basic_math_functions.h"
/**
@ingroup groupMath
*/
/**
@defgroup BasicClip Elementwise clipping
Element-by-element clipping of a value.
The value is constrained between 2 bounds.
There are separate functions for floating-point, Q7, Q15, and Q31 data types.
*/
/**
@addtogroup BasicClip
@{
*/
/**
@brief Elementwise floating-point clipping
@param[in] pSrc points to input values
@param[out] pDst points to output clipped values
@param[in] low lower bound
@param[in] high higher bound
@param[in] numSamples number of samples to clip
@return none
*/
#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE)
#include "arm_helium_utils.h"
void arm_clip_f32(const float32_t * pSrc,
float32_t * pDst,
float32_t low,
float32_t high,
uint32_t numSamples)
{
uint32_t blkCnt;
f32x4_t curVec0, curVec1;
f32x4_t vecLow, vecHigh;
vecLow = vdupq_n_f32(low);
vecHigh = vdupq_n_f32(high);
curVec0 = vld1q(pSrc);
pSrc += 4;
/*
* unrolled x 2 to allow
* vldr/vstr/vmin/vmax
* stall free interleaving
*/
blkCnt = numSamples >> 3;
while (blkCnt--)
{
curVec0 = vmaxnmq(curVec0, vecLow);
curVec1 = vld1q(pSrc);
pSrc += 4;
curVec0 = vminnmq(curVec0, vecHigh);
vst1q(pDst, curVec0);
pDst += 4;
curVec1 = vmaxnmq(curVec1, vecLow);
curVec0 = vld1q(pSrc);
pSrc += 4;
curVec1 = vminnmq(curVec1, vecHigh);
vst1q(pDst, curVec1);
pDst += 4;
}
/*
* Tail handling
*/
blkCnt = numSamples - ((numSamples >> 3) << 3);
if (blkCnt >= 4)
{
curVec0 = vmaxnmq(curVec0, vecLow);
curVec0 = vminnmq(curVec0, vecHigh);
vst1q(pDst, curVec0);
pDst += 4;
curVec0 = vld1q(pSrc);
pSrc += 4;
}
if (blkCnt > 0)
{
mve_pred16_t p0 = vctp32q(blkCnt & 3);
curVec0 = vmaxnmq(curVec0, vecLow);
curVec0 = vminnmq(curVec0, vecHigh);
vstrwq_p(pDst, curVec0, p0);
}
}
#else
void arm_clip_f32(const float32_t * pSrc,
float32_t * pDst,
float32_t low,
float32_t high,
uint32_t numSamples)
{
uint32_t i;
for (i = 0; i < numSamples; i++)
{
if (pSrc[i] > high)
pDst[i] = high;
else if (pSrc[i] < low)
pDst[i] = low;
else
pDst[i] = pSrc[i];
}
}
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
/**
@} end of BasicClip group
*/
|
