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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
|
/*
* Copyright © 2004, 2005 Red Hat, Inc.
* Copyright © 2004 Nicholas Miell
* Copyright © 2005 Trolltech AS
*
* Permission to use, copy, modify, distribute, and sell this software and its
* documentation for any purpose is hereby granted without fee, provided that
* the above copyright notice appear in all copies and that both that
* copyright notice and this permission notice appear in supporting
* documentation, and that the name of Red Hat not be used in advertising or
* publicity pertaining to distribution of the software without specific,
* written prior permission. Red Hat makes no representations about the
* suitability of this software for any purpose. It is provided "as is"
* without express or implied warranty.
*
* THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
* SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
* FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
* SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
* AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
* OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
* SOFTWARE.
*
* Author: Søren Sandmann (sandmann@redhat.com)
* Minor Improvements: Nicholas Miell (nmiell@gmail.com)
* MMX code paths for fbcompose.c by Lars Knoll (lars@trolltech.com)
*
* Based on work by Owen Taylor
*/
#ifdef HAVE_DIX_CONFIG_H
#include <dix-config.h>
#endif
#ifdef USE_MMX
#if defined(__amd64__) || defined(__x86_64__)
#define USE_SSE
#endif
#include <mmintrin.h>
#ifdef USE_SSE
#include <xmmintrin.h> /* for _mm_shuffle_pi16 and _MM_SHUFFLE */
#endif
#ifdef RENDER
#include "fb.h"
#include "fbmmx.h"
#include "picturestr.h"
#include "mipict.h"
#include "fbpict.h"
#define noVERBOSE
#ifdef VERBOSE
#define CHECKPOINT() ErrorF ("at %s %d\n", __FUNCTION__, __LINE__)
#else
#define CHECKPOINT()
#endif
typedef unsigned long long ullong;
#ifdef __GNUC__
typedef ullong mmxdatafield;
#endif
#ifdef _MSC_VER
typedef unsigned __int64 ullong;
typedef __m64 mmxdatafield;
#endif
Bool
fbFillmmx (FbBits *bits,
FbStride stride,
int bpp,
int x,
int y,
int width,
int height,
FbBits xor)
{
ullong fill;
__m64 vfill;
CARD32 byte_width;
CARD8 *byte_line;
#ifdef __GNUC__
__m64 v1, v2, v3, v4, v5, v6, v7;
#endif
if (bpp == 16 && (xor >> 16 != (xor & 0xffff)))
return FALSE;
if (bpp != 16 && bpp != 32)
return FALSE;
if (bpp == 16)
{
stride = stride * sizeof (FbBits) / 2;
byte_line = (CARD8 *)(((CARD16 *)bits) + stride * y + x);
byte_width = 2 * width;
stride *= 2;
}
else
{
stride = stride * sizeof (FbBits) / 4;
byte_line = (CARD8 *)(((CARD32 *)bits) + stride * y + x);
byte_width = 4 * width;
stride *= 4;
}
fill = ((ullong)xor << 32) | xor;
vfill = (__m64)fill;
#ifdef __GNUC__
__asm__ (
"movq %7, %0\n"
"movq %7, %1\n"
"movq %7, %2\n"
"movq %7, %3\n"
"movq %7, %4\n"
"movq %7, %5\n"
"movq %7, %6\n"
: "=y" (v1), "=y" (v2), "=y" (v3),
"=y" (v4), "=y" (v5), "=y" (v6), "=y" (v7)
: "y" (vfill));
#endif
while (height--)
{
int w;
CARD8 *d = byte_line;
byte_line += stride;
w = byte_width;
while (w >= 2 && ((unsigned long)d & 3))
{
*(CARD16 *)d = xor;
w -= 2;
d += 2;
}
while (w >= 4 && ((unsigned long)d & 7))
{
*(CARD32 *)d = xor;
w -= 4;
d += 4;
}
while (w >= 64)
{
#ifdef __GNUC__
__asm__ (
"movq %1, (%0)\n"
"movq %2, 8(%0)\n"
"movq %3, 16(%0)\n"
"movq %4, 24(%0)\n"
"movq %5, 32(%0)\n"
"movq %6, 40(%0)\n"
"movq %7, 48(%0)\n"
"movq %8, 56(%0)\n"
:
: "r" (d),
"y" (vfill), "y" (v1), "y" (v2), "y" (v3),
"y" (v4), "y" (v5), "y" (v6), "y" (v7)
: "memory");
#else
*(__m64*) (d + 0) = vfill;
*(__m64*) (d + 8) = vfill;
*(__m64*) (d + 16) = vfill;
*(__m64*) (d + 24) = vfill;
*(__m64*) (d + 32) = vfill;
*(__m64*) (d + 40) = vfill;
*(__m64*) (d + 48) = vfill;
*(__m64*) (d + 56) = vfill;
#endif
w -= 64;
d += 64;
}
while (w >= 4)
{
*(CARD32 *)d = xor;
w -= 4;
d += 4;
}
if (w >= 2)
{
*(CARD16 *)d = xor;
w -= 2;
d += 2;
}
}
_mm_empty();
return TRUE;
}
Bool
fbBltmmx (FbBits *src_bits,
FbBits *dst_bits,
FbStride src_stride,
FbStride dst_stride,
int src_bpp,
int dst_bpp,
int src_x, int src_y,
int dst_x, int dst_y,
int width, int height)
{
CARD8 * src_bytes;
CARD8 * dst_bytes;
int byte_width;
if (src_bpp != dst_bpp)
return FALSE;
if (src_bpp == 16)
{
src_stride = src_stride * sizeof (FbBits) / 2;
dst_stride = dst_stride * sizeof (FbBits) / 2;
src_bytes = (CARD8 *)(((CARD16 *)src_bits) + src_stride * (src_y) + (src_x));
dst_bytes = (CARD8 *)(((CARD16 *)dst_bits) + dst_stride * (dst_y) + (dst_x));
byte_width = 2 * width;
src_stride *= 2;
dst_stride *= 2;
} else if (src_bpp == 32) {
src_stride = src_stride * sizeof (FbBits) / 4;
dst_stride = dst_stride * sizeof (FbBits) / 4;
src_bytes = (CARD8 *)(((CARD32 *)src_bits) + src_stride * (src_y) + (src_x));
dst_bytes = (CARD8 *)(((CARD32 *)dst_bits) + dst_stride * (dst_y) + (dst_x));
byte_width = 4 * width;
src_stride *= 4;
dst_stride *= 4;
} else {
return FALSE;
}
while (height--)
{
int w;
CARD8 *s = src_bytes;
CARD8 *d = dst_bytes;
src_bytes += src_stride;
dst_bytes += dst_stride;
w = byte_width;
while (w >= 2 && ((unsigned long)d & 3))
{
*(CARD16 *)d = *(CARD16 *)s;
w -= 2;
s += 2;
d += 2;
}
while (w >= 4 && ((unsigned long)d & 7))
{
*(CARD32 *)d = *(CARD32 *)s;
w -= 4;
s += 4;
d += 4;
}
while (w >= 64)
{
#ifdef __GNUC__
__asm__ (
"movq (%1), %%mm0\n"
"movq 8(%1), %%mm1\n"
"movq 16(%1), %%mm2\n"
"movq 24(%1), %%mm3\n"
"movq 32(%1), %%mm4\n"
"movq 40(%1), %%mm5\n"
"movq 48(%1), %%mm6\n"
"movq 56(%1), %%mm7\n"
"movq %%mm0, (%0)\n"
"movq %%mm1, 8(%0)\n"
"movq %%mm2, 16(%0)\n"
"movq %%mm3, 24(%0)\n"
"movq %%mm4, 32(%0)\n"
"movq %%mm5, 40(%0)\n"
"movq %%mm6, 48(%0)\n"
"movq %%mm7, 56(%0)\n"
:
: "r" (d), "r" (s)
: "memory",
"%mm0", "%mm1", "%mm2", "%mm3",
"%mm4", "%mm5", "%mm6", "%mm7");
#else
__m64 v0 = *(__m64 *)(s + 0);
__m64 v1 = *(__m64 *)(s + 8);
__m64 v2 = *(__m64 *)(s + 16);
__m64 v3 = *(__m64 *)(s + 24);
__m64 v4 = *(__m64 *)(s + 32);
__m64 v5 = *(__m64 *)(s + 40);
__m64 v6 = *(__m64 *)(s + 48);
__m64 v7 = *(__m64 *)(s + 56);
*(__m64 *)(d + 0) = v0;
*(__m64 *)(d + 8) = v1;
*(__m64 *)(d + 16) = v2;
*(__m64 *)(d + 24) = v3;
*(__m64 *)(d + 32) = v4;
*(__m64 *)(d + 40) = v5;
*(__m64 *)(d + 48) = v6;
*(__m64 *)(d + 56) = v7;
#endif
w -= 64;
s += 64;
d += 64;
}
while (w >= 4)
{
*(CARD32 *)d = *(CARD32 *)s;
w -= 4;
s += 4;
d += 4;
}
if (w >= 2)
{
*(CARD16 *)d = *(CARD16 *)s;
w -= 2;
s += 2;
d += 2;
}
}
_mm_empty();
return TRUE;
}
#endif /* RENDER */
#endif /* USE_MMX */
|
