forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvulkan-shaders-gen.cpp
519 lines (416 loc) · 20.6 KB
/
vulkan-shaders-gen.cpp
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
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
#include <iostream>
#include <fstream>
#include <sstream>
#include <string>
#include <stdexcept>
#include <array>
#include <vector>
#include <map>
#include <thread>
#include <mutex>
#include <future>
#include <queue>
#include <condition_variable>
#include <cstdio>
#include <cstring>
#include <cstdlib>
#include <cassert>
#include <sys/stat.h>
#include <sys/types.h>
#ifdef _WIN32
#include <windows.h>
#include <direct.h> // For _mkdir on Windows
#include <algorithm> // For std::replace on w64devkit
#else
#include <unistd.h>
#include <sys/wait.h>
#include <fcntl.h>
#endif
#define ASYNCIO_CONCURRENCY 64
std::mutex lock;
std::vector<std::pair<std::string, std::string>> shader_fnames;
std::string GLSLC = "glslc";
std::string input_dir = "vulkan-shaders";
std::string output_dir = "/tmp";
std::string target_hpp = "ggml-vulkan-shaders.hpp";
std::string target_cpp = "ggml-vulkan-shaders.cpp";
bool no_clean = false;
const std::vector<std::string> type_names = {
"f32",
"f16",
"q4_0",
"q4_1",
"q5_0",
"q5_1",
"q8_0",
"q2_k",
"q3_k",
"q4_k",
"q5_k",
"q6_k",
"iq4_nl"
};
void execute_command(const std::string& command, std::string& stdout_str, std::string& stderr_str) {
#ifdef _WIN32
HANDLE stdout_read, stdout_write;
HANDLE stderr_read, stderr_write;
SECURITY_ATTRIBUTES sa = { sizeof(SECURITY_ATTRIBUTES), NULL, TRUE };
if (!CreatePipe(&stdout_read, &stdout_write, &sa, 0) ||
!SetHandleInformation(stdout_read, HANDLE_FLAG_INHERIT, 0)) {
throw std::runtime_error("Failed to create stdout pipe");
}
if (!CreatePipe(&stderr_read, &stderr_write, &sa, 0) ||
!SetHandleInformation(stderr_read, HANDLE_FLAG_INHERIT, 0)) {
throw std::runtime_error("Failed to create stderr pipe");
}
PROCESS_INFORMATION pi;
STARTUPINFOA si = { sizeof(STARTUPINFOA) };
si.dwFlags = STARTF_USESTDHANDLES;
si.hStdOutput = stdout_write;
si.hStdError = stderr_write;
std::vector<char> cmd(command.begin(), command.end());
cmd.push_back('\0');
if (!CreateProcessA(NULL, cmd.data(), NULL, NULL, TRUE, 0, NULL, NULL, &si, &pi)) {
throw std::runtime_error("Failed to create process");
}
CloseHandle(stdout_write);
CloseHandle(stderr_write);
std::array<char, 128> buffer;
DWORD bytes_read;
while (ReadFile(stdout_read, buffer.data(), (DWORD)buffer.size(), &bytes_read, NULL) && bytes_read > 0) {
stdout_str.append(buffer.data(), bytes_read);
}
while (ReadFile(stderr_read, buffer.data(), (DWORD)buffer.size(), &bytes_read, NULL) && bytes_read > 0) {
stderr_str.append(buffer.data(), bytes_read);
}
CloseHandle(stdout_read);
CloseHandle(stderr_read);
WaitForSingleObject(pi.hProcess, INFINITE);
CloseHandle(pi.hProcess);
CloseHandle(pi.hThread);
#else
int stdout_pipe[2];
int stderr_pipe[2];
if (pipe(stdout_pipe) != 0 || pipe(stderr_pipe) != 0) {
throw std::runtime_error("Failed to create pipes");
}
pid_t pid = fork();
if (pid < 0) {
throw std::runtime_error("Failed to fork process");
}
if (pid == 0) {
close(stdout_pipe[0]);
close(stderr_pipe[0]);
dup2(stdout_pipe[1], STDOUT_FILENO);
dup2(stderr_pipe[1], STDERR_FILENO);
close(stdout_pipe[1]);
close(stderr_pipe[1]);
execl("/bin/sh", "sh", "-c", command.c_str(), (char*) nullptr);
_exit(EXIT_FAILURE);
} else {
close(stdout_pipe[1]);
close(stderr_pipe[1]);
std::array<char, 128> buffer;
ssize_t bytes_read;
while ((bytes_read = read(stdout_pipe[0], buffer.data(), buffer.size())) > 0) {
stdout_str.append(buffer.data(), bytes_read);
}
while ((bytes_read = read(stderr_pipe[0], buffer.data(), buffer.size())) > 0) {
stderr_str.append(buffer.data(), bytes_read);
}
close(stdout_pipe[0]);
close(stderr_pipe[0]);
waitpid(pid, nullptr, 0);
}
#endif
}
bool directory_exists(const std::string& path) {
struct stat info;
if (stat(path.c_str(), &info) != 0) {
return false; // Path doesn't exist or can't be accessed
}
return (info.st_mode & S_IFDIR) != 0; // Check if it is a directory
}
bool create_directory(const std::string& path) {
#ifdef _WIN32
return _mkdir(path.c_str()) == 0 || errno == EEXIST; // EEXIST means the directory already exists
#else
return mkdir(path.c_str(), 0755) == 0 || errno == EEXIST; // 0755 is the directory permissions
#endif
}
std::string to_uppercase(const std::string& input) {
std::string result = input;
for (char& c : result) {
c = std::toupper(c);
}
return result;
}
bool string_ends_with(const std::string& str, const std::string& suffix) {
if (suffix.size() > str.size()) {
return false;
}
return std::equal(suffix.rbegin(), suffix.rend(), str.rbegin());
}
static const char path_separator = '/';
std::string join_paths(const std::string& path1, const std::string& path2) {
return path1 + path_separator + path2;
}
std::string basename(const std::string &path) {
return path.substr(path.find_last_of("/\\") + 1);
}
// variables to track number of compiles in progress
static uint32_t compile_count = 0;
static std::mutex compile_count_mutex;
static std::condition_variable compile_count_cond;
void string_to_spv_func(const std::string& _name, const std::string& in_fname, const std::map<std::string, std::string>& defines, bool fp16 = true) {
std::string name = _name + (fp16 ? "" : "_fp32");
std::string out_fname = join_paths(output_dir, name + ".spv");
std::string in_path = join_paths(input_dir, in_fname);
#ifdef _WIN32
std::vector<std::string> cmd = {GLSLC, "-fshader-stage=compute", "--target-env=vulkan1.2", "-O", "\"" + in_path + "\"", "-o", "\"" + out_fname + "\""};
#else
std::vector<std::string> cmd = {GLSLC, "-fshader-stage=compute", "--target-env=vulkan1.2", "-O", in_path, "-o", out_fname};
#endif
#ifdef GGML_VULKAN_SHADER_DEBUG_INFO
cmd.push_back("-g");
#endif
for (const auto& define : defines) {
cmd.push_back("-D" + define.first + "=" + define.second);
}
std::string command;
for (const auto& part : cmd) {
command += part + " ";
}
std::string stdout_str, stderr_str;
try {
// std::cout << "Executing command: ";
// for (const auto& part : cmd) {
// std::cout << part << " ";
// }
// std::cout << std::endl;
execute_command(command, stdout_str, stderr_str);
if (!stderr_str.empty()) {
std::cerr << "cannot compile " << name << "\n\n" << command << "\n\n" << stderr_str << std::endl;
return;
}
std::lock_guard<std::mutex> guard(lock);
shader_fnames.push_back(std::make_pair(name, out_fname));
} catch (const std::exception& e) {
std::cerr << "Error executing command for " << name << ": " << e.what() << std::endl;
}
{
std::lock_guard<std::mutex> guard(compile_count_mutex);
assert(compile_count > 0);
compile_count--;
}
compile_count_cond.notify_all();
}
std::map<std::string, std::string> merge_maps(const std::map<std::string, std::string>& a, const std::map<std::string, std::string>& b) {
std::map<std::string, std::string> result = a;
result.insert(b.begin(), b.end());
return result;
}
static std::vector<std::future<void>> compiles;
void string_to_spv(const std::string& _name, const std::string& in_fname, const std::map<std::string, std::string>& defines, bool fp16 = true) {
{
// wait until fewer than N compiles are in progress.
// 16 is an arbitrary limit, the goal is to avoid "failed to create pipe" errors.
uint32_t N = 16;
std::unique_lock<std::mutex> guard(compile_count_mutex);
while (compile_count >= N) {
compile_count_cond.wait(guard);
}
compile_count++;
}
compiles.push_back(std::async(string_to_spv_func, _name, in_fname, defines, fp16));
}
void matmul_shaders(bool fp16, bool matmul_id) {
std::string load_vec = fp16 ? "8" : "4";
std::string aligned_b_type_f32 = fp16 ? "mat2x4" : "vec4";
std::string aligned_b_type_f16 = fp16 ? "f16mat2x4" : "f16vec4";
std::map<std::string, std::string> base_dict = {{"FLOAT_TYPE", fp16 ? "float16_t" : "float"}};
std::string shader_name = "matmul";
if (matmul_id) {
base_dict["MUL_MAT_ID"] = "1";
shader_name = "matmul_id";
}
if (fp16) {
base_dict["FLOAT16"] = "1";
}
// Shaders with f16 B_TYPE
string_to_spv(shader_name + "_f32_f16", "mul_mm.comp", merge_maps(base_dict, {{"DATA_A_F32", "1"}, {"B_TYPE", "float16_t"}, {"D_TYPE", "float"}}), fp16);
string_to_spv(shader_name + "_f32_f16_aligned", "mul_mm.comp", merge_maps(base_dict, {{"DATA_A_F32", "1"}, {"LOAD_VEC_A", load_vec}, {"LOAD_VEC_B", load_vec}, {"B_TYPE", aligned_b_type_f16}, {"D_TYPE", "float"}}), fp16);
string_to_spv(shader_name + "_f16", "mul_mm.comp", merge_maps(base_dict, {{"DATA_A_F16", "1"}, {"B_TYPE", "float16_t"}, {"D_TYPE", "float"}}), fp16);
string_to_spv(shader_name + "_f16_aligned", "mul_mm.comp", merge_maps(base_dict, {{"DATA_A_F16", "1"}, {"LOAD_VEC_A", load_vec}, {"LOAD_VEC_B", load_vec}, {"B_TYPE", aligned_b_type_f16}, {"D_TYPE", "float"}}), fp16);
for (const auto& tname : type_names) {
std::string data_a_key = "DATA_A_" + to_uppercase(tname);
// For unaligned, load one at a time for f32/f16, or two at a time for quants
std::string load_vec_a_unaligned = (tname == "f32" || tname == "f16") ? "1" : "2";
// For aligned matmul loads
std::string load_vec_a = (tname == "f32" || tname == "f16") ? load_vec : "2";
string_to_spv(shader_name + "_" + tname + "_f32", "mul_mm.comp", merge_maps(base_dict, {{data_a_key, "1"}, {"LOAD_VEC_A", load_vec_a_unaligned}, {"B_TYPE", "float"}, {"D_TYPE", "float"}}), fp16);
string_to_spv(shader_name + "_" + tname + "_f32_aligned", "mul_mm.comp", merge_maps(base_dict, {{data_a_key, "1"}, {"LOAD_VEC_A", load_vec_a}, {"LOAD_VEC_B", load_vec}, {"B_TYPE", aligned_b_type_f32}, {"D_TYPE", "float"}}), fp16);
}
}
void process_shaders() {
std::cout << "ggml_vulkan: Generating and compiling shaders to SPIR-V" << std::endl;
std::map<std::string, std::string> base_dict = {{"FLOAT_TYPE", "float"}};
for (const auto& fp16 : {false, true}) {
matmul_shaders(fp16, false);
matmul_shaders(fp16, true);
}
for (const auto& tname : type_names) {
// mul mat vec
std::string data_a_key = "DATA_A_" + to_uppercase(tname);
std::string shader = (string_ends_with(tname, "_k")) ? "mul_mat_vec_" + tname + ".comp" : "mul_mat_vec.comp";
string_to_spv("mul_mat_vec_" + tname + "_f32_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}}));
string_to_spv("mul_mat_vec_" + tname + "_f16_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float16_t"}, {"B_TYPE_VEC4", "f16vec4"}, {"D_TYPE", "float"}}));
string_to_spv("mul_mat_vec_id_" + tname + "_f32", shader, merge_maps(base_dict, {{"MUL_MAT_ID", "1"}, {data_a_key, "1"}, {"B_TYPE", "float"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}}));
// Dequant shaders
if (tname != "f16") {
string_to_spv("dequant_" + tname, "dequant_" + tname + ".comp", merge_maps(base_dict, {{data_a_key, "1"}, {"D_TYPE", "float16_t"}}));
}
if (!string_ends_with(tname, "_k")) {
shader = (tname == "f32" || tname == "f16") ? "get_rows.comp" : "get_rows_quant.comp";
if (tname == "f16") {
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}}));
} else {
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}}));
}
string_to_spv("get_rows_" + tname + "_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float"}}));
}
}
string_to_spv("mul_mat_vec_p021_f16_f32", "mul_mat_vec_p021.comp", {{"A_TYPE", "float16_t"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("mul_mat_vec_nc_f16_f32", "mul_mat_vec_nc.comp", {{"A_TYPE", "float16_t"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}});
// Norms
string_to_spv("norm_f32", "norm.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("group_norm_f32", "group_norm.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("rms_norm_f32", "rms_norm.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("cpy_f32_f32", "copy.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("cpy_f32_f16", "copy.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float16_t"}});
string_to_spv("cpy_f16_f16", "copy.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}});
string_to_spv("contig_cpy_f32_f32", "contig_copy.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("contig_cpy_f32_f16", "contig_copy.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float16_t"}});
string_to_spv("contig_cpy_f16_f16", "contig_copy.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}});
string_to_spv("add_f32", "add.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("add_f16_f32_f16", "add.comp", {{"A_TYPE", "float16_t"}, {"B_TYPE", "float"}, {"D_TYPE", "float16_t"}, {"FLOAT_TYPE", "float"}});
string_to_spv("acc_f32", "acc.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("split_k_reduce", "mul_mat_split_k_reduce.comp", {});
string_to_spv("mul_f32", "mul.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("div_f32", "div.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("repeat_f32", "repeat.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("scale_f32", "scale.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("sqr_f32", "square.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("sin_f32", "sin.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("cos_f32", "cos.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("clamp_f32", "clamp.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("pad_f32", "pad.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("concat_f32", "concat.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("concat_f16", "concat.comp", {{"A_TYPE", "float16_t"}, {"B_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}});
string_to_spv("concat_i32", "concat.comp", {{"A_TYPE", "int"}, {"B_TYPE", "int"}, {"D_TYPE", "int"}});
string_to_spv("upscale_f32", "upscale.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("gelu_f32", "gelu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("gelu_quick_f32", "gelu_quick.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("silu_f32", "silu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("relu_f32", "relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("leaky_relu_f32", "leaky_relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("tanh_f32", "tanh.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("diag_mask_inf_f32", "diag_mask_inf.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("soft_max_f32", "soft_max.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("soft_max_f32_f16", "soft_max.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"B_TYPE", "float16_t"}, {"D_TYPE", "float"}}));
string_to_spv("rope_norm_f32", "rope_norm.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("rope_norm_f16", "rope_norm.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}});
string_to_spv("rope_neox_f32", "rope_neox.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("rope_neox_f16", "rope_neox.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}});
string_to_spv("argsort_f32", "argsort.comp", {{"A_TYPE", "float"}});
string_to_spv("sum_rows_f32", "sum_rows.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("im2col_f32", "im2col.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("im2col_f32_f16", "im2col.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float16_t"}}));
string_to_spv("timestep_embedding_f32", "timestep_embedding.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
string_to_spv("pool2d_f32", "pool2d.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}}));
for (auto &c : compiles) {
c.wait();
}
}
void write_output_files() {
FILE* hdr = fopen(target_hpp.c_str(), "w");
FILE* src = fopen(target_cpp.c_str(), "w");
fprintf(hdr, "#include <cstdint>\n\n");
fprintf(src, "#include \"%s\"\n\n", basename(target_hpp).c_str());
for (const auto& pair : shader_fnames) {
const std::string& name = pair.first;
#ifdef _WIN32
std::string path = pair.second;
std::replace(path.begin(), path.end(), '/', '\\' );
#else
const std::string& path = pair.second;
#endif
FILE* spv = fopen(path.c_str(), "rb");
if (!spv) {
std::cerr << "Error opening SPIR-V file: " << path << " (" << strerror(errno) << ")\n";
continue;
}
fseek(spv, 0, SEEK_END);
size_t size = ftell(spv);
fseek(spv, 0, SEEK_SET);
std::vector<unsigned char> data(size);
size_t read_size = fread(data.data(), 1, size, spv);
fclose(spv);
if (read_size != size) {
std::cerr << "Error reading SPIR-V file: " << path << " (" << strerror(errno) << ")\n";
continue;
}
fprintf(hdr, "extern unsigned char %s_data[%zu];\n", name.c_str(), size);
fprintf(hdr, "const uint64_t %s_len = %zu;\n\n", name.c_str(), size);
fprintf(src, "unsigned char %s_data[%zu] = {\n", name.c_str(), size);
for (size_t i = 0; i < size; ++i) {
fprintf(src, "0x%02x,", data[i]);
if ((i + 1) % 12 == 0) fprintf(src, "\n");
}
fprintf(src, "\n};\n\n");
if (!no_clean) {
std::remove(path.c_str());
}
}
fclose(hdr);
fclose(src);
}
int main(int argc, char** argv) {
std::map<std::string, std::string> args;
for (int i = 1; i < argc; i += 2) {
if (i + 1 < argc) {
args[argv[i]] = argv[i + 1];
}
}
if (args.find("--glslc") != args.end()) {
GLSLC = args["--glslc"]; // Path to glslc
}
if (args.find("--input-dir") != args.end()) {
input_dir = args["--input-dir"]; // Directory containing shader sources
}
if (args.find("--output-dir") != args.end()) {
output_dir = args["--output-dir"]; // Directory for containing SPIR-V output
}
if (args.find("--target-hpp") != args.end()) {
target_hpp = args["--target-hpp"]; // Path to generated header file
}
if (args.find("--target-cpp") != args.end()) {
target_cpp = args["--target-cpp"]; // Path to generated cpp file
}
if (args.find("--no-clean") != args.end()) {
no_clean = true; // Keep temporary SPIR-V files in output-dir after build
}
if (!directory_exists(input_dir)) {
std::cerr << "\"" << input_dir << "\" must be a valid directory containing shader sources" << std::endl;
return EXIT_FAILURE;
}
if (!directory_exists(output_dir)) {
if (!create_directory(output_dir)) {
std::cerr << "Error creating output directory: " << output_dir << "\n";
return EXIT_FAILURE;
}
}
process_shaders();
write_output_files();
return EXIT_SUCCESS;
}