This repository has been archived by the owner on Feb 11, 2021. It is now read-only.
SDL_blit_copy.c
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
/*
SDL - Simple DirectMedia Layer
Copyright (C) 1997-2006 Sam Lantinga
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
Sam Lantinga
slouken@libsdl.org
*/
#include "SDL_config.h"
#include "SDL_video.h"
#include "SDL_blit.h"
26
#include "SDL_blit_copy.h"
27
28
29
30
#ifdef __MMX__
static __inline__ void
31
SDL_memcpyMMX(Uint8 * dst, const Uint8 * src, int len)
35
__m64 values[8];
36
for (i = len / 64; i--;) {
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
_mm_prefetch(src, _MM_HINT_NTA);
values[0] = *(__m64 *) (src + 0);
values[1] = *(__m64 *) (src + 8);
values[2] = *(__m64 *) (src + 16);
values[3] = *(__m64 *) (src + 24);
values[4] = *(__m64 *) (src + 32);
values[5] = *(__m64 *) (src + 40);
values[6] = *(__m64 *) (src + 48);
values[7] = *(__m64 *) (src + 56);
_mm_stream_pi((__m64 *) (dst + 0), values[0]);
_mm_stream_pi((__m64 *) (dst + 8), values[1]);
_mm_stream_pi((__m64 *) (dst + 16), values[2]);
_mm_stream_pi((__m64 *) (dst + 24), values[3]);
_mm_stream_pi((__m64 *) (dst + 32), values[4]);
_mm_stream_pi((__m64 *) (dst + 40), values[5]);
_mm_stream_pi((__m64 *) (dst + 48), values[6]);
_mm_stream_pi((__m64 *) (dst + 56), values[7]);
54
55
56
src += 64;
dst += 64;
}
58
59
60
61
62
63
64
if (len & 63)
SDL_memcpy(dst, src, len & 63);
}
#endif /* __MMX__ */
#ifdef __SSE__
static __inline__ void
65
SDL_memcpySSE(Uint8 * dst, const Uint8 * src, int len)
69
__m128 values[4];
70
for (i = len / 64; i--;) {
71
72
73
74
75
76
77
78
79
_mm_prefetch(src, _MM_HINT_NTA);
values[0] = *(__m128 *) (src + 0);
values[1] = *(__m128 *) (src + 16);
values[2] = *(__m128 *) (src + 32);
values[3] = *(__m128 *) (src + 48);
_mm_stream_ps((float *) (dst + 0), values[0]);
_mm_stream_ps((float *) (dst + 16), values[1]);
_mm_stream_ps((float *) (dst + 32), values[2]);
_mm_stream_ps((float *) (dst + 48), values[3]);
80
81
82
src += 64;
dst += 64;
}
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
if (len & 63)
SDL_memcpy(dst, src, len & 63);
}
#endif /* __SSE__ */
void
SDL_BlitCopy(SDL_BlitInfo * info)
{
Uint8 *src, *dst;
int w, h;
int srcskip, dstskip;
w = info->d_width * info->dst->BytesPerPixel;
h = info->d_height;
src = info->s_pixels;
dst = info->d_pixels;
srcskip = w + info->s_skip;
dstskip = w + info->d_skip;
#ifdef __SSE__
104
if (SDL_HasSSE() && !((uintptr_t) src & 15) && !((uintptr_t) dst & 15)) {
105
106
107
108
109
110
111
112
113
114
while (h--) {
SDL_memcpySSE(dst, src, w);
src += srcskip;
dst += dstskip;
}
return;
}
#endif
#ifdef __MMX__
115
if (SDL_HasMMX() && !((uintptr_t) src & 7) && !((uintptr_t) dst & 7)) {
116
117
118
119
120
while (h--) {
SDL_memcpyMMX(dst, src, w);
src += srcskip;
dst += dstskip;
}
121
_mm_empty();
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
return;
}
#endif
while (h--) {
SDL_memcpy(dst, src, w);
src += srcskip;
dst += dstskip;
}
}
void
SDL_BlitCopyOverlap(SDL_BlitInfo * info)
{
Uint8 *src, *dst;
int w, h;
int skip;
w = info->d_width * info->dst->BytesPerPixel;
h = info->d_height;
src = info->s_pixels;
dst = info->d_pixels;
skip = w + info->s_skip;
145
if ((dst < src) || (dst >= (src + h * skip))) {
146
147
148
149
150
151
152
153
154
155
156
157
158
SDL_BlitCopy(info);
} else {
src += ((h - 1) * skip);
dst += ((h - 1) * skip);
while (h--) {
SDL_revcpy(dst, src, w);
src -= skip;
dst -= skip;
}
}
}
/* vi: set ts=4 sw=4 expandtab: */