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
|
/*
* 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.
*/
#pragma once
CCL_NAMESPACE_BEGIN
/* Ray offset to avoid self intersection.
*
* This function should be used to compute a modified ray start position for
* rays leaving from a surface. */
ccl_device_inline float3 ray_offset(float3 P, float3 Ng)
{
#ifdef __INTERSECTION_REFINE__
const float epsilon_f = 1e-5f;
/* ideally this should match epsilon_f, but instancing and motion blur
* precision makes it problematic */
const float epsilon_test = 1.0f;
const int epsilon_i = 32;
float3 res;
/* x component */
if (fabsf(P.x) < epsilon_test) {
res.x = P.x + Ng.x * epsilon_f;
}
else {
uint ix = __float_as_uint(P.x);
ix += ((ix ^ __float_as_uint(Ng.x)) >> 31) ? -epsilon_i : epsilon_i;
res.x = __uint_as_float(ix);
}
/* y component */
if (fabsf(P.y) < epsilon_test) {
res.y = P.y + Ng.y * epsilon_f;
}
else {
uint iy = __float_as_uint(P.y);
iy += ((iy ^ __float_as_uint(Ng.y)) >> 31) ? -epsilon_i : epsilon_i;
res.y = __uint_as_float(iy);
}
/* z component */
if (fabsf(P.z) < epsilon_test) {
res.z = P.z + Ng.z * epsilon_f;
}
else {
uint iz = __float_as_uint(P.z);
iz += ((iz ^ __float_as_uint(Ng.z)) >> 31) ? -epsilon_i : epsilon_i;
res.z = __uint_as_float(iz);
}
return res;
#else
const float epsilon_f = 1e-4f;
return P + epsilon_f * Ng;
#endif
}
#if defined(__VOLUME_RECORD_ALL__) || (defined(__SHADOW_RECORD_ALL__) && defined(__KERNEL_CPU__))
/* TODO: Move to another file? */
ccl_device int intersections_compare(const void *a, const void *b)
{
const Intersection *isect_a = (const Intersection *)a;
const Intersection *isect_b = (const Intersection *)b;
if (isect_a->t < isect_b->t)
return -1;
else if (isect_a->t > isect_b->t)
return 1;
else
return 0;
}
#endif
#if defined(__SHADOW_RECORD_ALL__)
ccl_device_inline void sort_intersections(ccl_private Intersection *hits, uint num_hits)
{
kernel_assert(num_hits > 0);
# ifdef __KERNEL_GPU__
/* Use bubble sort which has more friendly memory pattern on GPU. */
bool swapped;
do {
swapped = false;
for (int j = 0; j < num_hits - 1; ++j) {
if (hits[j].t > hits[j + 1].t) {
struct Intersection tmp = hits[j];
hits[j] = hits[j + 1];
hits[j + 1] = tmp;
swapped = true;
}
}
--num_hits;
} while (swapped);
# else
qsort(hits, num_hits, sizeof(Intersection), intersections_compare);
# endif
}
#endif /* __SHADOW_RECORD_ALL__ | __VOLUME_RECORD_ALL__ */
/* For subsurface scattering, only sorting a small amount of intersections
* so bubble sort is fine for CPU and GPU. */
ccl_device_inline void sort_intersections_and_normals(ccl_private Intersection *hits,
ccl_private float3 *Ng,
uint num_hits)
{
bool swapped;
do {
swapped = false;
for (int j = 0; j < num_hits - 1; ++j) {
if (hits[j].t > hits[j + 1].t) {
struct Intersection tmp_hit = hits[j];
struct float3 tmp_Ng = Ng[j];
hits[j] = hits[j + 1];
Ng[j] = Ng[j + 1];
hits[j + 1] = tmp_hit;
Ng[j + 1] = tmp_Ng;
swapped = true;
}
}
--num_hits;
} while (swapped);
}
/* Utility to quickly get flags from an intersection. */
ccl_device_forceinline int intersection_get_shader_flags(KernelGlobals kg,
const int prim,
const int type)
{
int shader = 0;
#ifdef __HAIR__
if (type & PRIMITIVE_ALL_TRIANGLE)
#endif
{
shader = kernel_tex_fetch(__tri_shader, prim);
}
#ifdef __HAIR__
else {
shader = kernel_tex_fetch(__curves, prim).shader_id;
}
#endif
return kernel_tex_fetch(__shaders, (shader & SHADER_MASK)).flags;
}
ccl_device_forceinline int intersection_get_shader_from_isect_prim(KernelGlobals kg,
const int prim,
const int isect_type)
{
int shader = 0;
#ifdef __HAIR__
if (isect_type & PRIMITIVE_ALL_TRIANGLE)
#endif
{
shader = kernel_tex_fetch(__tri_shader, prim);
}
#ifdef __HAIR__
else {
shader = kernel_tex_fetch(__curves, prim).shader_id;
}
#endif
return shader & SHADER_MASK;
}
ccl_device_forceinline int intersection_get_shader(
KernelGlobals kg, ccl_private const Intersection *ccl_restrict isect)
{
return intersection_get_shader_from_isect_prim(kg, isect->prim, isect->type);
}
ccl_device_forceinline int intersection_get_object_flags(
KernelGlobals kg, ccl_private const Intersection *ccl_restrict isect)
{
return kernel_tex_fetch(__object_flag, isect->object);
}
/* TODO: find a better (faster) solution for this. Maybe store offset per object for
* attributes needed in intersection? */
ccl_device_inline int intersection_find_attribute(KernelGlobals kg,
const int object,
const uint id)
{
uint attr_offset = kernel_tex_fetch(__objects, object).attribute_map_offset;
uint4 attr_map = kernel_tex_fetch(__attributes_map, attr_offset);
while (attr_map.x != id) {
if (UNLIKELY(attr_map.x == ATTR_STD_NONE)) {
if (UNLIKELY(attr_map.y == 0)) {
return (int)ATTR_STD_NOT_FOUND;
}
else {
/* Chain jump to a different part of the table. */
attr_offset = attr_map.z;
}
}
else {
attr_offset += ATTR_PRIM_TYPES;
}
attr_map = kernel_tex_fetch(__attributes_map, attr_offset);
}
/* return result */
return (attr_map.y == ATTR_ELEMENT_NONE) ? (int)ATTR_STD_NOT_FOUND : (int)attr_map.z;
}
CCL_NAMESPACE_END
|