Skip to content
Navigation Menu
{{ message }}
forked from AnswerDotAI/gpu.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy patharray_utils.h
More file actions
300 lines (279 loc) · 8.92 KB
/
Copy patharray_utils.h
File metadata and controls
300 lines (279 loc) · 8.92 KB
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
/*
* array_utils.h
*
* This file contains utility functions for working with arrays. These are
* mostly convenience functions for setting up and inspecting data for testing.
* They are not optimized and are not intended for use in performance-critical
* code.
*
*/
#ifndef ARRAY_UTILS_H
#define ARRAY_UTILS_H
#include <algorithm> // std::max_element
#include <array>
#include <cmath>
#include <random>
#include <stdexcept>
#include <string>
#include <utility>
#include "utils/logging.h"
namespace gpu {
static constexpr int kShowMaxRows = 8;
static constexpr int kShowMaxCols = 8;
/**
* @brief Show a 2D array as a string, base implementation.
*
* @param a The array to show.
* @param rows The number of rows in the array.
* @param cols The number of columns in the array.
* @param name The name of the array to show.
* @return std::string The string representation of the array.
* @code
* std::array<float, 4> a = {1.0, 2.0, 3.0, 4.0};
* printf("%s", show<float>(a.data(), 2, 2, "a").c_str());
* @endcode
*/
template <typename numtype>
std::string show(const numtype *a, size_t rows, size_t cols,
const std::string &name = "") {
std::string output = "\n";
if (name != "") {
output += "\n" + name + " (" + std::to_string(rows) + ", " +
std::to_string(cols) + ")\n\n";
} else {
output +=
"\n(" + std::to_string(rows) + ", " + std::to_string(cols) + ")\n\n";
}
// spacing as log10 of max value
int spacing = 1;
numtype max = *std::max_element(a, a + rows * cols);
if constexpr (std::is_same<numtype, int>::value) {
spacing = std::max(0, (int)log10(max + .01)) + 2;
} else if constexpr (std::is_same<numtype, float>::value) {
// spacing = std::max(0, (int)log10(max + .01)) + 1;
spacing = 8; // scientific notation
} else {
throw std::runtime_error("Unsupported number type for show()");
}
// print to stdout line break for each row
for (size_t i = 0; i < rows; i++) {
if (i == kShowMaxRows / 2 && rows > kShowMaxRows) {
output += "...\n";
i = rows - kShowMaxRows / 2;
}
for (size_t j = 0; j < cols; j++) {
if (j == kShowMaxCols / 2 && cols > kShowMaxCols) {
output += " ..";
j = cols - kShowMaxCols / 2;
}
char buffer[50];
if constexpr (std::is_same<numtype, int>::value) {
snprintf(buffer, spacing, "%*d", spacing, a[i * cols + j]);
} else if constexpr (std::is_same<numtype, float>::value) {
if (std::abs(a[i * cols + j]) < 1000 &&
std::abs(a[i * cols + j]) > 0.01 ||
a[i * cols + j] == 0.0) {
snprintf(buffer, 16, "%9.2f", a[i * cols + j]);
} else
snprintf(buffer, 16, "%10.2e", a[i * cols + j]);
} else {
throw std::runtime_error("Unsupported number type for show()");
}
output += buffer;
}
output += "\n";
}
output += "\n";
return output;
}
/**
* @brief Overload of `show()` for std::array.
*
* @param a The array to show.
* @param name The name of the array to show.
* @return std::string The string representation of the array.
* @code
* std::array<float, 4> a = {1.0, 2.0, 3.0, 4.0};
* printf("%s", show<float>(a, "a").c_str());
* @endcode
*/
template <typename numtype, size_t rows, size_t cols>
std::string show(const std::array<numtype, rows * cols> &a,
const std::string &name = "") {
return show<numtype>(a.data(), rows, cols, name);
}
/**
* @brief Overload of `show()` for float std::array.
* @param a The array to show.
* @param name The name of the array to show.
* @return std::string The string representation of the array.
*
* @code
* std::array<float, 4> a = {1.0, 2.0, 3.0, 4.0};
* printf("%s", show(a, "a").c_str());
* @endcode
@
*/
template <size_t rows, size_t cols>
std::string show(const std::array<float, rows * cols> &a,
const std::string &name = "") {
return show<float, rows, cols>(a, name);
}
/**
* @brief Populate the array with a range of values. This is mostly for testing
* purposes.
* @param input The array to populate.
* @param N The number of elements in the array.
* @param start The starting value.
* @param step The step size.
*/
void range(float *input, size_t N, float start = 0.0, float step = 1.0) {
// TODO(avh): currently unused - check
float curr = start;
for (size_t i = 0; i < N; i++) {
input[i] = curr;
curr += step;
}
}
/**
* @brief Overload of `range()` for std::array.
* @param input The array to populate.
* @param start The starting value.
* @param step The step size.
*/
template <size_t N>
void range(std::array<float, N> &input, float start = 0.0, float step = 1.0) {
float curr = start;
for (size_t i = start; i < N; i++) {
input[i] = curr;
curr += step;
}
}
/**
* @brief Populate the array with random integers.
* @param a The array to populate.
* @param N The number of elements in the array.
* @param gen The random number generator.
* @param min The minimum value for the random integers.
* @param max The maximum value for the random integers.
*/
void randint(float *a, size_t N, std::mt19937 &gen, int min = -1, int max = 1) {
std::uniform_int_distribution<> dist(min, max);
for (int i = 0; i < N; i++) {
a[i] = static_cast<float>(dist(gen));
}
}
/**
* @brief Overload of `randint()` for std::array.
* @param a The array to populate.
* @param gen The random number generator.
* @param min The minimum value for the random integers.
* @param max The maximum value for the random integers.
*/
template <typename numtype, size_t size>
void randint(std::array<numtype, size> &a, std::mt19937 &gen, int min = -1,
int max = 1) {
std::uniform_int_distribution<> dist(min, max);
for (int i = 0; i < size; i++) {
a[i] = static_cast<numtype>(dist(gen));
}
}
/**
* @brief Populate the array with random floats, generated from a Gaussian distribution.
* @param a The array to populate.
* @param N The number of elements in the array.
* @param gen The random number generator.
* @param mean The mean of the Gaussian distribution.
* @param std The standard deviation of the Gaussian distribution.
*/
void randn(float *a, size_t N, std::mt19937 &gen, float mean = 0.0,
float std = 1.0) {
std::normal_distribution<float> dist(mean, std);
for (int i = 0; i < N; i++) {
a[i] = static_cast<float>(dist(gen));
}
}
/**
* @brief Overload of `randn()` for std::array.
* @param a The array to populate.
* @param gen The random number generator.
* @param mean The mean of the Gaussian distribution.
* @param std The standard deviation of the Gaussian distribution.
*/
template <size_t size>
void randn(std::array<float, size> &a, std::mt19937 &gen, float mean = 0.0,
float std = 1.0) {
std::normal_distribution<float> dist(mean, std);
for (int i = 0; i < size; i++) {
a[i] = static_cast<float>(dist(gen));
}
}
/**
* @brief Populate a square matrix with the identity matrix.
* @param a The array to populate.
* @param N The number of rows and columns in the square matrix.
*/
inline void eye(float *a, size_t N) {
for (size_t i = 0; i < N; i++) {
for (size_t j = 0; j < N; j++) {
a[i * N + j] = (i == j) ? 1.0 : 0.0;
}
}
}
// Note transformation operations here are purely for testing - they are not
// optimized to be used in hot paths.
/**
* @brief Transpose a matrix.
* @param input The input matrix.
* @param output The output matrix.
* @param M The number of rows in the input matrix.
* @param N The number of columns in the input matrix.
*/
inline void transpose(float *input, float *output, size_t M, size_t N) {
for (size_t i = 0; i < M; i++) {
for (size_t j = 0; j < N; j++) {
output[j * M + i] = input[i * N + j];
}
}
}
/**
* @brief Flip a matrix horizontally or vertically.
* @param a The matrix to flip.
* @param R The number of rows in the matrix.
* @param C The number of columns in the matrix.
* @param horizontal Whether to flip horizontally (true) or vertically (false).
*/
inline void flip(float *a, size_t R, size_t C, bool horizontal = true) {
if (horizontal) {
for (size_t i = 0; i < R; i++) {
for (size_t j = 0; j < C / 2; j++) {
std::swap(a[i * C + j], a[i * C + C - j - 1]);
}
}
} else {
for (size_t i = 0; i < R / 2; i++) {
for (size_t j = 0; j < C; j++) {
std::swap(a[i * C + j], a[(R - i - 1) * C + j]);
}
}
}
}
/**
* @brief Determine if the values of two arrays are close to each other.
* @param a The first array.
* @param b The second array.
* @param n The number of elements in the arrays.
* @param tol The tolerance for closeness.
* @return bool True if the arrays are close, false otherwise.
*/
bool isclose(float *a, float *b, size_t n, float tol = 1e-3) {
for (size_t i = 0; i < n; i++) {
if (std::abs(a[i] - b[i]) > tol || std::isnan(a[i]) || std::isnan(b[i])) {
LOG(kDefLog, kError, "Mismatch at index %d: %f != %f", i, a[i], b[i]);
return false;
}
}
return true;
}
} // namespace gpu
#endif
You can’t perform that action at this time.