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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_and_u16.c
* Description: uint16_t bitwise AND
*
* $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 And Vector bitwise AND
Compute the logical bitwise AND.
There are separate functions for uint32_t, uint16_t, and uint7_t data types.
*/
/**
@addtogroup And
@{
*/
/**
@brief Compute the logical bitwise AND of two fixed-point vectors.
@param[in] pSrcA points to input vector A
@param[in] pSrcB points to input vector B
@param[out] pDst points to output vector
@param[in] blockSize number of samples in each vector
@return none
*/
void arm_and_u16(
const uint16_t * pSrcA,
const uint16_t * pSrcB,
uint16_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* Loop counter */
#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
uint16x8_t vecSrcA, vecSrcB;
/* Compute 8 outputs at a time */
blkCnt = blockSize >> 3;
while (blkCnt > 0U)
{
vecSrcA = vld1q(pSrcA);
vecSrcB = vld1q(pSrcB);
vst1q(pDst, vandq_u16(vecSrcA, vecSrcB) );
pSrcA += 8;
pSrcB += 8;
pDst += 8;
/* Decrement the loop counter */
blkCnt--;
}
/* Tail */
blkCnt = blockSize & 7;
if (blkCnt > 0U)
{
mve_pred16_t p0 = vctp16q(blkCnt);
vecSrcA = vld1q(pSrcA);
vecSrcB = vld1q(pSrcB);
vstrhq_p(pDst, vandq_u16(vecSrcA, vecSrcB), p0);
}
#else
#if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE)
uint16x8_t vecA, vecB;
/* Compute 8 outputs at a time */
blkCnt = blockSize >> 3U;
while (blkCnt > 0U)
{
vecA = vld1q_u16(pSrcA);
vecB = vld1q_u16(pSrcB);
vst1q_u16(pDst, vandq_u16(vecA, vecB) );
pSrcA += 8;
pSrcB += 8;
pDst += 8;
/* Decrement the loop counter */
blkCnt--;
}
/* Tail */
blkCnt = blockSize & 7;
#else
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif
while (blkCnt > 0U)
{
*pDst++ = (*pSrcA++)&(*pSrcB++);
/* Decrement the loop counter */
blkCnt--;
}
#endif /* if defined(ARM_MATH_MVEI) */
}
/**
@} end of And group
*/
|