Welcome to mirror list, hosted at ThFree Co, Russian Federation.

kernel.cpp « cpu « kernels « kernel « cycles « intern - git.blender.org/blender.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
blob: 72dbbd9a416ca8de7a8b83b9675cbb36ecb5f5a1 (plain)
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
/*
 * 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.
 */

/* CPU kernel entry points */

/* On x86-64, we can assume SSE2, so avoid the extra kernel and compile this
 * one with SSE2 intrinsics.
 */
#if defined(__x86_64__) || defined(_M_X64)
#  define __KERNEL_SSE2__
#endif

/* When building kernel for native machine detect kernel features from the flags
 * set by compiler.
 */
#ifdef WITH_KERNEL_NATIVE
#  ifdef __SSE2__
#    ifndef __KERNEL_SSE2__
#      define __KERNEL_SSE2__
#    endif
#  endif
#  ifdef __SSE3__
#    define __KERNEL_SSE3__
#  endif
#  ifdef __SSSE3__
#    define __KERNEL_SSSE3__
#  endif
#  ifdef __SSE4_1__
#    define __KERNEL_SSE41__
#  endif
#  ifdef __AVX__
#    define __KERNEL_SSE__
#    define __KERNEL_AVX__
#  endif
#  ifdef __AVX2__
#    define __KERNEL_SSE__
#    define __KERNEL_AVX2__
#  endif
#endif

/* quiet unused define warnings */
#if defined(__KERNEL_SSE2__)
    /* do nothing */
#endif

#include "kernel.h"
#define KERNEL_ARCH cpu
#include "kernel_cpu_impl.h"

CCL_NAMESPACE_BEGIN

/* Memory Copy */

void kernel_const_copy(KernelGlobals *kg, const char *name, void *host, size_t size)
{
	if(strcmp(name, "__data") == 0)
		memcpy(&kg->__data, host, size);
	else
		assert(0);
}

void kernel_tex_copy(KernelGlobals *kg,
                     const char *name,
                     device_ptr mem,
                     size_t width,
                     size_t height,
                     size_t depth,
                     InterpolationType interpolation,
                     ExtensionType extension)
{
	if(0) {
	}

#define KERNEL_TEX(type, ttype, tname) \
	else if(strcmp(name, #tname) == 0) { \
		kg->tname.data = (type*)mem; \
		kg->tname.width = width; \
	}
#define KERNEL_IMAGE_TEX(type, ttype, tname)
#include "kernel_textures.h"

	else if(strstr(name, "__tex_image_float4")) {
		texture_image_float4 *tex = NULL;
		int id = atoi(name + strlen("__tex_image_float4_"));
		int array_index = id;

		if(array_index >= 0 && array_index < TEX_NUM_FLOAT4_CPU) {
			tex = &kg->texture_float4_images[array_index];
		}

		if(tex) {
			tex->data = (float4*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else if(strstr(name, "__tex_image_float")) {
		texture_image_float *tex = NULL;
		int id = atoi(name + strlen("__tex_image_float_"));
		int array_index = id - TEX_START_FLOAT_CPU;

		if(array_index >= 0 && array_index < TEX_NUM_FLOAT_CPU) {
			tex = &kg->texture_float_images[array_index];
		}

		if(tex) {
			tex->data = (float*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else if(strstr(name, "__tex_image_byte4")) {
		texture_image_uchar4 *tex = NULL;
		int id = atoi(name + strlen("__tex_image_byte4_"));
		int array_index = id - TEX_START_BYTE4_CPU;

		if(array_index >= 0 && array_index < TEX_NUM_BYTE4_CPU) {
			tex = &kg->texture_byte4_images[array_index];
		}

		if(tex) {
			tex->data = (uchar4*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else if(strstr(name, "__tex_image_byte")) {
		texture_image_uchar *tex = NULL;
		int id = atoi(name + strlen("__tex_image_byte_"));
		int array_index = id - TEX_START_BYTE_CPU;

		if(array_index >= 0 && array_index < TEX_NUM_BYTE_CPU) {
			tex = &kg->texture_byte_images[array_index];
		}

		if(tex) {
			tex->data = (uchar*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else if(strstr(name, "__tex_image_half4")) {
		texture_image_half4 *tex = NULL;
		int id = atoi(name + strlen("__tex_image_half4_"));
		int array_index = id - TEX_START_HALF4_CPU;

		if(array_index >= 0 && array_index < TEX_NUM_HALF4_CPU) {
			tex = &kg->texture_half4_images[array_index];
		}

		if(tex) {
			tex->data = (half4*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else if(strstr(name, "__tex_image_half")) {
		texture_image_half *tex = NULL;
		int id = atoi(name + strlen("__tex_image_half_"));
		int array_index = id - TEX_START_HALF_CPU;

		if(array_index >= 0 && array_index < TEX_NUM_HALF_CPU) {
			tex = &kg->texture_half_images[array_index];
		}

		if(tex) {
			tex->data = (half*)mem;
			tex->dimensions_set(width, height, depth);
			tex->interpolation = interpolation;
			tex->extension = extension;
		}
	}
	else
		assert(0);
}

CCL_NAMESPACE_END