blob: adc141a7b284cb4a5a43692a69fd53d3752aed42 (
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
|
/*
* 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.
*/
#ifndef __UTIL_OPTIMIZATION_H__
#define __UTIL_OPTIMIZATION_H__
#ifndef __KERNEL_GPU__
/* quiet unused define warnings */
#if defined(__KERNEL_SSE2__) || \
defined(__KERNEL_SSE3__) || \
defined(__KERNEL_SSSE3__) || \
defined(__KERNEL_SSE41__) || \
defined(__KERNEL_AVX__) || \
defined(__KERNEL_AVX2__)
/* do nothing */
#endif
/* x86
*
* Compile a regular, SSE2 and SSE3 kernel. */
#if defined(i386) || defined(_M_IX86)
# ifdef WITH_KERNEL_SSE2
# define WITH_CYCLES_OPTIMIZED_KERNEL_SSE2
# endif
# ifdef WITH_KERNEL_SSE3
# define WITH_CYCLES_OPTIMIZED_KERNEL_SSE3
# endif
#endif /* defined(i386) || defined(_M_IX86) */
/* x86-64
*
* Compile a regular (includes SSE2), SSE3, SSE 4.1, AVX and AVX2 kernel. */
#if defined(__x86_64__) || defined(_M_X64)
/* SSE2 is always available on x86-64 CPUs, so auto enable */
# define __KERNEL_SSE2__
/* no SSE2 kernel on x86-64, part of regular kernel */
# ifdef WITH_KERNEL_SSE3
# define WITH_CYCLES_OPTIMIZED_KERNEL_SSE3
# endif
# ifdef WITH_KERNEL_SSE41
# define WITH_CYCLES_OPTIMIZED_KERNEL_SSE41
# endif
# ifdef WITH_KERNEL_AVX
# define WITH_CYCLES_OPTIMIZED_KERNEL_AVX
# endif
# ifdef WITH_KERNEL_AVX2
# define WITH_CYCLES_OPTIMIZED_KERNEL_AVX2
# endif
#endif /* defined(__x86_64__) || defined(_M_X64) */
/* SSE Experiment
*
* This is disabled code for an experiment to use SSE types globally for types
* such as float3 and float4. Currently this gives an overall slowdown. */
#if 0
# define __KERNEL_SSE__
# ifndef __KERNEL_SSE2__
# define __KERNEL_SSE2__
# endif
# ifndef __KERNEL_SSE3__
# define __KERNEL_SSE3__
# endif
# ifndef __KERNEL_SSSE3__
# define __KERNEL_SSSE3__
# endif
# ifndef __KERNEL_SSE4__
# define __KERNEL_SSE4__
# endif
#endif
/* SSE Intrinsics includes
*
* We assume __KERNEL_SSEX__ flags to have been defined at this point */
/* SSE intrinsics headers */
#ifndef FREE_WINDOWS64
#ifdef _MSC_VER
# include <intrin.h>
#elif (defined(__x86_64__) || defined(__i386__))
# include <x86intrin.h>
#endif
#else
/* MinGW64 has conflicting declarations for these SSE headers in <windows.h>.
* Since we can't avoid including <windows.h>, better only include that */
#include "util_windows.h"
#endif
#endif
#endif /* __UTIL_OPTIMIZATION_H__ */
|
