« back to all changes in this revision
Viewing changes to include/sse.h
- browse files at revision 1.1.4
- compare with another revision
- download diff
- download tarball
- view history from revision 1.1.4
- Committer: Bazaar Package Importer
- Author(s): Steve Langasek
- Date: 2009-05-01 05:30:24 UTC
- mfrom: (1.2.3 upstream)
- mto: This revision was merged to the branch mainline in revision 26.
- Revision ID: james.westby@ubuntu.com-20090501053024-eo6umwjsksox3uaf
Tags: upstream-0.8.3
Import upstream version 0.8.3
- files added:
- other_src/driver++.cpp
- files removed:
- include/sse.h
- files modified:
- ChangeLog
- config.guess
- config.sub
- ltmain.sh
added
removed
include/sse.h
1
/*
2
* sse.h
3
* Copyright (C) 1999 R. Fisher
4
*
5
* This file is part of mpeg2dec, a free MPEG-2 video stream decoder.
6
*
7
* mpeg2dec is free software; you can redistribute it and/or modify
8
* it under the terms of the GNU General Public License as published by
9
* the Free Software Foundation; either version 2 of the License, or
10
* (at your option) any later version.
11
*
12
* mpeg2dec is distributed in the hope that it will be useful,
13
* but WITHOUT ANY WARRANTY; without even the implied warranty of
14
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
* GNU General Public License for more details.
16
*
17
* You should have received a copy of the GNU General Public License
18
* along with this program; if not, write to the Free Software
19
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
20
*/
21
22
#define ATTR_ALIGN(x) __attribute__ ((aligned(16)))
23
24
typedef union {
25
float sf[4]; /* Single-precision (32-bit) value */
26
} ATTR_ALIGN(16) sse_t; /* On a 16 byte (128-bit) boundary */
27
28
29
#define sse_i2r(op, imm, reg) \
30
__asm__ __volatile__ (#op " %0, %%" #reg \
31
: /* nothing */ \
32
: "X" (imm) )
33
34
#define sse_m2r(op, mem, reg) \
35
__asm__ __volatile__ (#op " %0, %%" #reg \
36
: /* nothing */ \
37
: "X" (mem))
38
39
#define sse_r2m(op, reg, mem) \
40
__asm__ __volatile__ (#op " %%" #reg ", %0" \
41
: "=m" (mem) \
42
: /* nothing */ )
43
44
#define sse_r2r(op, regs, regd) \
45
__asm__ __volatile__ (#op " %" #regs ", %" #regd)
46
47
#define sse_r2ri(op, regs, regd, imm) \
48
__asm__ __volatile__ (#op " %0, %%" #regs ", %%" #regd \
49
: /* nothing */ \
50
: "X" (imm) )
51
52
#define sse_m2ri(op, mem, reg, subop) \
53
__asm__ __volatile__ (#op " %0, %%" #reg ", " #subop \
54
: /* nothing */ \
55
: "X" (mem))
56
57
58
#define movaps_m2r(var, reg) sse_m2r(movaps, var, reg)
59
#define movaps_r2m(reg, var) sse_r2m(movaps, reg, var)
60
#define movaps_r2r(regs, regd) sse_r2r(movaps, regs, regd)
61
62
#define movntps_r2m(xmmreg, var) sse_r2m(movntps, xmmreg, var)
63
64
#define movups_m2r(var, reg) sse_m2r(movups, var, reg)
65
#define movups_r2m(reg, var) sse_r2m(movups, reg, var)
66
#define movups_r2r(regs, regd) sse_r2r(movups, regs, regd)
67
68
#define movhlps_r2r(regs, regd) sse_r2r(movhlps, regs, regd)
69
70
#define movlhps_r2r(regs, regd) sse_r2r(movlhps, regs, regd)
71
72
#define movhps_m2r(var, reg) sse_m2r(movhps, var, reg)
73
#define movhps_r2m(reg, var) sse_r2m(movhps, reg, var)
74
75
#define movlps_m2r(var, reg) sse_m2r(movlps, var, reg)
76
#define movlps_r2m(reg, var) sse_r2m(movlps, reg, var)
77
78
#define movss_m2r(var, reg) sse_m2r(movss, var, reg)
79
#define movss_r2m(reg, var) sse_r2m(movss, reg, var)
80
#define movss_r2r(regs, regd) sse_r2r(movss, regs, regd)
81
82
#define shufps_m2r(var, reg, index) sse_m2ri(shufps, var, reg, index)
83
#define shufps_r2r(regs, regd, index) sse_r2ri(shufps, regs, regd, index)
84
85
#define cvtpi2ps_m2r(var, xmmreg) sse_m2r(cvtpi2ps, var, xmmreg)
86
#define cvtpi2ps_r2r(mmreg, xmmreg) sse_r2r(cvtpi2ps, mmreg, xmmreg)
87
88
#define cvtps2pi_m2r(var, mmreg) sse_m2r(cvtps2pi, var, mmreg)
89
#define cvtps2pi_r2r(xmmreg, mmreg) sse_r2r(cvtps2pi, mmreg, xmmreg)
90
91
#define cvttps2pi_m2r(var, mmreg) sse_m2r(cvttps2pi, var, mmreg)
92
#define cvttps2pi_r2r(xmmreg, mmreg) sse_r2r(cvttps2pi, mmreg, xmmreg)
93
94
#define cvtsi2ss_m2r(var, xmmreg) sse_m2r(cvtsi2ss, var, xmmreg)
95
#define cvtsi2ss_r2r(reg, xmmreg) sse_r2r(cvtsi2ss, reg, xmmreg)
96
97
#define cvtss2si_m2r(var, reg) sse_m2r(cvtss2si, var, reg)
98
#define cvtss2si_r2r(xmmreg, reg) sse_r2r(cvtss2si, xmmreg, reg)
99
100
#define cvttss2si_m2r(var, reg) sse_m2r(cvtss2si, var, reg)
101
#define cvttss2si_r2r(xmmreg, reg) sse_r2r(cvtss2si, xmmreg, reg)
102
103
#define movmskps(xmmreg, reg) \
104
__asm__ __volatile__ ("movmskps %" #xmmreg ", %" #reg)
105
106
#define addps_m2r(var, reg) sse_m2r(addps, var, reg)
107
#define addps_r2r(regs, regd) sse_r2r(addps, regs, regd)
108
109
#define addss_m2r(var, reg) sse_m2r(addss, var, reg)
110
#define addss_r2r(regs, regd) sse_r2r(addss, regs, regd)
111
112
#define subps_m2r(var, reg) sse_m2r(subps, var, reg)
113
#define subps_r2r(regs, regd) sse_r2r(subps, regs, regd)
114
115
#define subss_m2r(var, reg) sse_m2r(subss, var, reg)
116
#define subss_r2r(regs, regd) sse_r2r(subss, regs, regd)
117
118
#define mulps_m2r(var, reg) sse_m2r(mulps, var, reg)
119
#define mulps_r2r(regs, regd) sse_r2r(mulps, regs, regd)
120
121
#define mulss_m2r(var, reg) sse_m2r(mulss, var, reg)
122
#define mulss_r2r(regs, regd) sse_r2r(mulss, regs, regd)
123
124
#define divps_m2r(var, reg) sse_m2r(divps, var, reg)
125
#define divps_r2r(regs, regd) sse_r2r(divps, regs, regd)
126
127
#define divss_m2r(var, reg) sse_m2r(divss, var, reg)
128
#define divss_r2r(regs, regd) sse_r2r(divss, regs, regd)
129
130
#define rcpps_m2r(var, reg) sse_m2r(rcpps, var, reg)
131
#define rcpps_r2r(regs, regd) sse_r2r(rcpps, regs, regd)
132
133
#define rcpss_m2r(var, reg) sse_m2r(rcpss, var, reg)
134
#define rcpss_r2r(regs, regd) sse_r2r(rcpss, regs, regd)
135
136
#define rsqrtps_m2r(var, reg) sse_m2r(rsqrtps, var, reg)
137
#define rsqrtps_r2r(regs, regd) sse_r2r(rsqrtps, regs, regd)
138
139
#define rsqrtss_m2r(var, reg) sse_m2r(rsqrtss, var, reg)
140
#define rsqrtss_r2r(regs, regd) sse_r2r(rsqrtss, regs, regd)
141
142
#define sqrtps_m2r(var, reg) sse_m2r(sqrtps, var, reg)
143
#define sqrtps_r2r(regs, regd) sse_r2r(sqrtps, regs, regd)
144
145
#define sqrtss_m2r(var, reg) sse_m2r(sqrtss, var, reg)
146
#define sqrtss_r2r(regs, regd) sse_r2r(sqrtss, regs, regd)
147
148
#define andps_m2r(var, reg) sse_m2r(andps, var, reg)
149
#define andps_r2r(regs, regd) sse_r2r(andps, regs, regd)
150
151
#define andnps_m2r(var, reg) sse_m2r(andnps, var, reg)
152
#define andnps_r2r(regs, regd) sse_r2r(andnps, regs, regd)
153
154
#define orps_m2r(var, reg) sse_m2r(orps, var, reg)
155
#define orps_r2r(regs, regd) sse_r2r(orps, regs, regd)
156
157
#define xorps_m2r(var, reg) sse_m2r(xorps, var, reg)
158
#define xorps_r2r(regs, regd) sse_r2r(xorps, regs, regd)
159
160
#define maxps_m2r(var, reg) sse_m2r(maxps, var, reg)
161
#define maxps_r2r(regs, regd) sse_r2r(maxps, regs, regd)
162
163
#define maxss_m2r(var, reg) sse_m2r(maxss, var, reg)
164
#define maxss_r2r(regs, regd) sse_r2r(maxss, regs, regd)
165
166
#define minps_m2r(var, reg) sse_m2r(minps, var, reg)
167
#define minps_r2r(regs, regd) sse_r2r(minps, regs, regd)
168
169
#define minss_m2r(var, reg) sse_m2r(minss, var, reg)
170
#define minss_r2r(regs, regd) sse_r2r(minss, regs, regd)
171
172
#define cmpps_m2r(var, reg, op) sse_m2ri(cmpps, var, reg, op)
173
#define cmpps_r2r(regs, regd, op) sse_r2ri(cmpps, regs, regd, op)
174
175
#define cmpeqps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 0)
176
#define cmpeqps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 0)
177
178
#define cmpltps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 1)
179
#define cmpltps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 1)
180
181
#define cmpleps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 2)
182
#define cmpleps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 2)
183
184
#define cmpunordps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 3)
185
#define cmpunordps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 3)
186
187
#define cmpneqps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 4)
188
#define cmpneqps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 4)
189
190
#define cmpnltps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 5)
191
#define cmpnltps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 5)
192
193
#define cmpnleps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 6)
194
#define cmpnleps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 6)
195
196
#define cmpordps_m2r(var, reg) sse_m2ri(cmpps, var, reg, 7)
197
#define cmpordps_r2r(regs, regd) sse_r2ri(cmpps, regs, regd, 7)
198
199
#define cmpss_m2r(var, reg, op) sse_m2ri(cmpss, var, reg, op)
200
#define cmpss_r2r(regs, regd, op) sse_r2ri(cmpss, regs, regd, op)
201
202
#define cmpeqss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 0)
203
#define cmpeqss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 0)
204
205
#define cmpltss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 1)
206
#define cmpltss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 1)
207
208
#define cmpless_m2r(var, reg) sse_m2ri(cmpss, var, reg, 2)
209
#define cmpless_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 2)
210
211
#define cmpunordss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 3)
212
#define cmpunordss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 3)
213
214
#define cmpneqss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 4)
215
#define cmpneqss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 4)
216
217
#define cmpnltss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 5)
218
#define cmpnltss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 5)
219
220
#define cmpnless_m2r(var, reg) sse_m2ri(cmpss, var, reg, 6)
221
#define cmpnless_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 6)
222
223
#define cmpordss_m2r(var, reg) sse_m2ri(cmpss, var, reg, 7)
224
#define cmpordss_r2r(regs, regd) sse_r2ri(cmpss, regs, regd, 7)
225
226
#define comiss_m2r(var, reg) sse_m2r(comiss, var, reg)
227
#define comiss_r2r(regs, regd) sse_r2r(comiss, regs, regd)
228
229
#define ucomiss_m2r(var, reg) sse_m2r(ucomiss, var, reg)
230
#define ucomiss_r2r(regs, regd) sse_r2r(ucomiss, regs, regd)
231
232
#define unpcklps_m2r(var, reg) sse_m2r(unpcklps, var, reg)
233
#define unpcklps_r2r(regs, regd) sse_r2r(unpcklps, regs, regd)
234
235
#define unpckhps_m2r(var, reg) sse_m2r(unpckhps, var, reg)
236
#define unpckhps_r2r(regs, regd) sse_r2r(unpckhps, regs, regd)
237
238
#define fxrstor(mem) \
239
__asm__ __volatile__ ("fxrstor %0" \
240
: /* nothing */ \
241
: "X" (mem))
242
243
#define fxsave(mem) \
244
__asm__ __volatile__ ("fxsave %0" \
245
: /* nothing */ \
246
: "X" (mem))
247
248
#define stmxcsr(mem) \
249
__asm__ __volatile__ ("stmxcsr %0" \
250
: /* nothing */ \
251
: "X" (mem))
252
253
#define ldmxcsr(mem) \
254
__asm__ __volatile__ ("ldmxcsr %0" \
255
: /* nothing */ \
256
: "X" (mem))
257
Loggerhead is a web-based interface for Breezy
Version: 2.0.1