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
|
/*
* Copyright 2011-2013 Blender Foundation
*
* 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
*
* http://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.
*/
/* OpenCL kernel entry points - unfinished */
#include "../../kernel_compat_opencl.h"
#include "../../kernel_math.h"
#include "../../kernel_types.h"
#include "../../kernel_globals.h"
#include "../../kernel_film.h"
#include "../../kernel_path.h"
#include "../../kernel_path_branched.h"
#include "../../kernel_bake.h"
#ifdef __COMPILE_ONLY_MEGAKERNEL__
__kernel void kernel_ocl_path_trace(
ccl_constant KernelData *data,
ccl_global float *buffer,
ccl_global uint *rng_state,
#define KERNEL_TEX(type, ttype, name) \
ccl_global type *name,
#include "../../kernel_textures.h"
int sample,
int sx, int sy, int sw, int sh, int offset, int stride)
{
KernelGlobals kglobals, *kg = &kglobals;
kg->data = data;
#define KERNEL_TEX(type, ttype, name) \
kg->name = name;
#include "../../kernel_textures.h"
int x = sx + get_global_id(0);
int y = sy + get_global_id(1);
if(x < sx + sw && y < sy + sh)
kernel_path_trace(kg, buffer, rng_state, sample, x, y, offset, stride);
}
#else // __COMPILE_ONLY_MEGAKERNEL__
__kernel void kernel_ocl_shader(
ccl_constant KernelData *data,
ccl_global uint4 *input,
ccl_global float4 *output,
#define KERNEL_TEX(type, ttype, name) \
ccl_global type *name,
#include "../../kernel_textures.h"
int type, int sx, int sw, int offset, int sample)
{
KernelGlobals kglobals, *kg = &kglobals;
kg->data = data;
#define KERNEL_TEX(type, ttype, name) \
kg->name = name;
#include "../../kernel_textures.h"
int x = sx + get_global_id(0);
if(x < sx + sw)
kernel_shader_evaluate(kg, input, output, (ShaderEvalType)type, x, sample);
}
__kernel void kernel_ocl_bake(
ccl_constant KernelData *data,
ccl_global uint4 *input,
ccl_global float4 *output,
#define KERNEL_TEX(type, ttype, name) \
ccl_global type *name,
#include "../../kernel_textures.h"
int type, int sx, int sw, int offset, int sample)
{
KernelGlobals kglobals, *kg = &kglobals;
kg->data = data;
#define KERNEL_TEX(type, ttype, name) \
kg->name = name;
#include "../../kernel_textures.h"
int x = sx + get_global_id(0);
if(x < sx + sw) {
#if defined(__KERNEL_OPENCL_NVIDIA__) && __COMPUTE_CAPABILITY__ < 300
/* NVidia compiler is spending infinite amount of time trying
* to deal with kernel_bake_evaluate() on architectures prior
* to sm_30.
* For now we disable baking kernel for those devices, so at
* least rendering with split kernel could be compiled.
*/
output[x] = make_float4(0.0f, 0.0f, 0.0f, 0.0f);
#else
kernel_bake_evaluate(kg, input, output, (ShaderEvalType)type, x, offset, sample);
#endif
}
}
__kernel void kernel_ocl_convert_to_byte(
ccl_constant KernelData *data,
ccl_global uchar4 *rgba,
ccl_global float *buffer,
#define KERNEL_TEX(type, ttype, name) \
ccl_global type *name,
#include "../../kernel_textures.h"
float sample_scale,
int sx, int sy, int sw, int sh, int offset, int stride)
{
KernelGlobals kglobals, *kg = &kglobals;
kg->data = data;
#define KERNEL_TEX(type, ttype, name) \
kg->name = name;
#include "../../kernel_textures.h"
int x = sx + get_global_id(0);
int y = sy + get_global_id(1);
if(x < sx + sw && y < sy + sh)
kernel_film_convert_to_byte(kg, rgba, buffer, sample_scale, x, y, offset, stride);
}
__kernel void kernel_ocl_convert_to_half_float(
ccl_constant KernelData *data,
ccl_global uchar4 *rgba,
ccl_global float *buffer,
#define KERNEL_TEX(type, ttype, name) \
ccl_global type *name,
#include "../../kernel_textures.h"
float sample_scale,
int sx, int sy, int sw, int sh, int offset, int stride)
{
KernelGlobals kglobals, *kg = &kglobals;
kg->data = data;
#define KERNEL_TEX(type, ttype, name) \
kg->name = name;
#include "../../kernel_textures.h"
int x = sx + get_global_id(0);
int y = sy + get_global_id(1);
if(x < sx + sw && y < sy + sh)
kernel_film_convert_to_half_float(kg, rgba, buffer, sample_scale, x, y, offset, stride);
}
#endif // __COMPILE_ONLY_MEGAKERNEL__
|
