File size: 4,826 Bytes
25ade36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#include "edge-impulse-sdk/classifier/ei_classifier_config.h"
#if EI_CLASSIFIER_TFLITE_LOAD_CMSIS_NN_SOURCES
/*
 * Copyright (C) 2022 Arm Limited or its affiliates.
 *
 * 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.
 */

/* ----------------------------------------------------------------------
 * Project:      CMSIS NN Library
 * Title:        arm_elementwise_add_s16
 * Description:  Elementwise add
 *
 * $Date:        10 May 2022
 * $Revision:    V.2.1.0
 *
 * Target Processor:  Cortex-M CPUs
 *
 * -------------------------------------------------------------------- */

#include "edge-impulse-sdk/CMSIS/NN/Include/arm_nnfunctions.h"
#include "edge-impulse-sdk/CMSIS/NN/Include/arm_nnsupportfunctions.h"

/**
 *  @ingroup groupNN
 */

/**
 * @addtogroup BasicMath
 * @{
 */

/*
 * s16 elementwise add
 *
 * Refer header file for details.
 *
 */

/* Note: __SHIFT is expected to be <=0 */

arm_cmsis_nn_status arm_elementwise_add_s16(const int16_t *input_1_vect,
                                            const int16_t *input_2_vect,
                                            const int32_t input_1_offset,
                                            const int32_t input_1_mult,
                                            const int32_t input_1_shift,
                                            const int32_t input_2_offset,
                                            const int32_t input_2_mult,
                                            const int32_t input_2_shift,
                                            const int32_t left_shift,
                                            int16_t *output,
                                            const int32_t out_offset,
                                            const int32_t out_mult,
                                            const int32_t out_shift,
                                            const int32_t out_activation_min,
                                            const int32_t out_activation_max,
                                            const int32_t block_size)
{
    (void)input_1_offset;
    (void)input_2_offset;
    (void)out_offset;
    int32_t input_1;
    int32_t input_2;
    int32_t sum;
    int32_t two_halfword_1, two_halfword_2;
    int16_t sum_1, sum_2;
    int32_t loop_count = block_size / 2;

    while (loop_count > 0)
    {
        two_halfword_1 = arm_nn_read_q15x2_ia(&input_1_vect);
        two_halfword_2 = arm_nn_read_q15x2_ia(&input_2_vect);

        input_1 = (int16_t)(two_halfword_1 & 0xFFFF) << left_shift;
        input_1 = arm_nn_requantize(input_1, input_1_mult, input_1_shift);
        input_2 = (int16_t)(two_halfword_2 & 0xFFFF) << left_shift;
        input_2 = arm_nn_requantize(input_2, input_2_mult, input_2_shift);
        sum = input_1 + input_2;
        sum = arm_nn_requantize(sum, out_mult, out_shift);
        sum = MAX(sum, out_activation_min);
        sum = MIN(sum, out_activation_max);
        sum_1 = (int16_t)sum;

        input_1 = (int16_t)(two_halfword_1 >> 16) << left_shift;
        input_1 = arm_nn_requantize(input_1, input_1_mult, input_1_shift);
        input_2 = (int16_t)(two_halfword_2 >> 16) << left_shift;
        input_2 = arm_nn_requantize(input_2, input_2_mult, input_2_shift);
        sum = input_1 + input_2;
        sum = arm_nn_requantize(sum, out_mult, out_shift);
        sum = MAX(sum, out_activation_min);
        sum = MIN(sum, out_activation_max);
        sum_2 = (int16_t)sum;

        arm_nn_write_q15x2_ia(&output, PACK_Q15x2_32x1(sum_1, sum_2));

        loop_count--;
    }
    loop_count = block_size & 0x1;

    while (loop_count > 0)
    {
        /* C = A + B */
        input_1 = *input_1_vect++ << left_shift;
        input_2 = *input_2_vect++ << left_shift;

        input_1 = arm_nn_requantize(input_1, input_1_mult, input_1_shift);
        input_2 = arm_nn_requantize(input_2, input_2_mult, input_2_shift);

        sum = input_1 + input_2;
        sum = arm_nn_requantize(sum, out_mult, out_shift);

        sum = MAX(sum, out_activation_min);
        sum = MIN(sum, out_activation_max);

        *output++ = (int16_t)sum;

        /* Decrement loop counter */
        loop_count--;
    }

    return (ARM_CMSIS_NN_SUCCESS);
}

/**
 * @} end of BasicMath group
 */

#endif // EI_CLASSIFIER_TFLITE_LOAD_CMSIS_NN_SOURCES