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
|
/*
* Copyright 2011, Blender Foundation.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
#include <stdlib.h>
#include <string.h>
#include "device.h"
#include "device_intern.h"
#include "util_cuda.h"
#include "util_debug.h"
#include "util_foreach.h"
#include "util_math.h"
#include "util_opencl.h"
#include "util_opengl.h"
#include "util_types.h"
#include "util_vector.h"
CCL_NAMESPACE_BEGIN
/* Device Task */
DeviceTask::DeviceTask(Type type_)
: type(type_), x(0), y(0), w(0), h(0), rng_state(0), rgba(0), buffer(0),
sample(0), resolution(0),
shader_input(0), shader_output(0),
shader_eval_type(0), shader_x(0), shader_w(0)
{
}
void DeviceTask::split_max_size(list<DeviceTask>& tasks, int max_size)
{
int num;
if(type == SHADER) {
num = (shader_w + max_size - 1)/max_size;
}
else {
max_size = max(1, max_size/w);
num = (h + max_size - 1)/max_size;
}
split(tasks, num);
}
void DeviceTask::split(ThreadQueue<DeviceTask>& queue, int num)
{
list<DeviceTask> tasks;
split(tasks, num);
foreach(DeviceTask& task, tasks)
queue.push(task);
}
void DeviceTask::split(list<DeviceTask>& tasks, int num)
{
if(type == SHADER) {
num = min(shader_w, num);
for(int i = 0; i < num; i++) {
int tx = shader_x + (shader_w/num)*i;
int tw = (i == num-1)? shader_w - i*(shader_w/num): shader_w/num;
DeviceTask task = *this;
task.shader_x = tx;
task.shader_w = tw;
tasks.push_back(task);
}
}
else {
num = min(h, num);
for(int i = 0; i < num; i++) {
int ty = y + (h/num)*i;
int th = (i == num-1)? h - i*(h/num): h/num;
DeviceTask task = *this;
task.y = ty;
task.h = th;
tasks.push_back(task);
}
}
}
/* Device */
void Device::pixels_alloc(device_memory& mem)
{
mem_alloc(mem, MEM_READ_WRITE);
}
void Device::pixels_copy_from(device_memory& mem, int y, int w, int h)
{
mem_copy_from(mem, sizeof(uint8_t)*4*y*w, sizeof(uint8_t)*4*w*h);
}
void Device::pixels_free(device_memory& mem)
{
mem_free(mem);
}
void Device::draw_pixels(device_memory& rgba, int y, int w, int h, int dy, int width, int height, bool transparent)
{
pixels_copy_from(rgba, y, w, h);
if(transparent) {
glEnable(GL_BLEND);
glBlendFunc(GL_ONE, GL_ONE_MINUS_SRC_ALPHA);
}
glPixelZoom((float)width/(float)w, (float)height/(float)h);
glRasterPos2f(0, dy);
uint8_t *pixels = (uint8_t*)rgba.data_pointer;
/* for multi devices, this assumes the ineffecient method that we allocate
all pixels on the device even though we only render to a subset */
pixels += 4*y*w;
glDrawPixels(w, h, GL_RGBA, GL_UNSIGNED_BYTE, pixels);
glRasterPos2f(0.0f, 0.0f);
glPixelZoom(1.0f, 1.0f);
if(transparent)
glDisable(GL_BLEND);
}
Device *Device::create(DeviceInfo& info, bool background, int threads)
{
Device *device;
switch(info.type) {
case DEVICE_CPU:
device = device_cpu_create(info, threads);
break;
#ifdef WITH_CUDA
case DEVICE_CUDA:
if(cuLibraryInit())
device = device_cuda_create(info, background);
else
device = NULL;
break;
#endif
#ifdef WITH_MULTI
case DEVICE_MULTI:
device = device_multi_create(info, background);
break;
#endif
#ifdef WITH_NETWORK
case DEVICE_NETWORK:
device = device_network_create(info, "127.0.0.1");
break;
#endif
#ifdef WITH_OPENCL
case DEVICE_OPENCL:
if(clLibraryInit())
device = device_opencl_create(info, background);
else
device = NULL;
break;
#endif
default:
return NULL;
}
return device;
}
DeviceType Device::type_from_string(const char *name)
{
if(strcmp(name, "cpu") == 0)
return DEVICE_CPU;
else if(strcmp(name, "cuda") == 0)
return DEVICE_CUDA;
else if(strcmp(name, "opencl") == 0)
return DEVICE_OPENCL;
else if(strcmp(name, "network") == 0)
return DEVICE_NETWORK;
else if(strcmp(name, "multi") == 0)
return DEVICE_MULTI;
return DEVICE_NONE;
}
string Device::string_from_type(DeviceType type)
{
if(type == DEVICE_CPU)
return "cpu";
else if(type == DEVICE_CUDA)
return "cuda";
else if(type == DEVICE_OPENCL)
return "opencl";
else if(type == DEVICE_NETWORK)
return "network";
else if(type == DEVICE_MULTI)
return "multi";
return "";
}
vector<DeviceType>& Device::available_types()
{
static vector<DeviceType> types;
static bool types_init = false;
if(!types_init) {
types.push_back(DEVICE_CPU);
#ifdef WITH_CUDA
if(cuLibraryInit())
types.push_back(DEVICE_CUDA);
#endif
#ifdef WITH_OPENCL
if(clLibraryInit())
types.push_back(DEVICE_OPENCL);
#endif
#ifdef WITH_NETWORK
types.push_back(DEVICE_NETWORK);
#endif
#ifdef WITH_MULTI
types.push_back(DEVICE_MULTI);
#endif
types_init = true;
}
return types;
}
vector<DeviceInfo>& Device::available_devices()
{
static vector<DeviceInfo> devices;
static bool devices_init = false;
if(!devices_init) {
device_cpu_info(devices);
#ifdef WITH_CUDA
if(cuLibraryInit())
device_cuda_info(devices);
#endif
#ifdef WITH_OPENCL
if(clLibraryInit())
device_opencl_info(devices);
#endif
#ifdef WITH_MULTI
device_multi_info(devices);
#endif
#ifdef WITH_NETWORK
device_network_info(devices);
#endif
devices_init = true;
}
return devices;
}
CCL_NAMESPACE_END
|