blob: 6fe99bcdcf0779231b230344c23b7a4e5e66e224 (
plain)
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
|
/*
* Copyright 2020 Birte Kristina Friesel
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#include "arch.h"
#include "driver/gpio.h"
#include "driver/stdout.h"
#include "driver/counter.h"
#include <stdlib.h>
#define XSTR(x) STR(x)
#define STR(x) #x
static const auto input_size = CONFIG_app_stream_n_elements;
static const auto stride = CONFIG_app_stream_stride;
typedef CONFIG_app_stream_type T;
static T A[input_size];
static T B[input_size];
static T scale;
static T X[input_size];
static T check;
int main(void)
{
uint16_t i;
arch.setup();
gpio.setup();
kout.setup();
scale = rand();
for (i = 0; i < input_size; i++) {
A[i] = (T)rand();
B[i] = (T)rand();
X[i] = (T)0;
}
while (1) {
check = 0;
/*
* Copy
*/
counter.start();
for (i = 0; i < input_size; i += stride) {
X[i] = A[i];
}
counter.stop();
kout << "[::] STREAM COPY";
kout << " | n_elements=" << input_size << " e_type=" << XSTR(CONFIG_app_stream_type) << " elem_B=" << sizeof(T) << " n_stride=" << stride;
kout << " | latency_us=" << counter.value << "/" << counter.overflow;
kout << endl;
for (i = 0; i < input_size; i++) {
check = (uint16_t)check ^ (uint16_t)X[i];
}
/*
* Scale
*/
counter.start();
for (i = 0; i < input_size; i += stride) {
X[i] = scale * A[i];
}
counter.stop();
kout << "[::] STREAM SCALE";
kout << " | n_elements=" << input_size << " e_type=" << XSTR(CONFIG_app_stream_type) << " elem_B=" << sizeof(T) << " n_stride=" << stride;
kout << " | latency_us=" << counter.value << "/" << counter.overflow;
kout << endl;
for (i = 0; i < input_size; i++) {
check = (uint16_t)check ^ (uint16_t)X[i];
}
/*
* Add
*/
counter.start();
for (i = 0; i < input_size; i += stride) {
X[i] = A[i] + B[i];
}
counter.stop();
kout << "[::] STREAM ADD";
kout << " | n_elements=" << input_size << " e_type=" << XSTR(CONFIG_app_stream_type) << " elem_B=" << sizeof(T) << " n_stride=" << stride;
kout << " | latency_us=" << counter.value << "/" << counter.overflow;
kout << endl;
for (i = 0; i < input_size; i++) {
check = (uint16_t)check ^ (uint16_t)X[i];
}
/*
* Triad
*/
counter.start();
for (i = 0; i < input_size; i += stride) {
X[i] = A[i] + scale * B[i];
}
counter.stop();
kout << "[::] STREAM TRIAD";
kout << " | n_elements=" << input_size << " e_type=" << XSTR(CONFIG_app_stream_type) << " elem_B=" << sizeof(T) << " n_stride=" << stride;
kout << " | latency_us=" << counter.value << "/" << counter.overflow;
kout << endl;
for (i = 0; i < input_size; i++) {
check = (uint16_t)check ^ (uint16_t)X[i];
}
/*
* Avoid optimizations
*/
kout << "// " << check << endl;
}
return 0;
}
|
