Debian Codegraph @

xvmc/shader/mc/ipicture.g4a

raw
1 /*
2 * Copyright © 2008 Intel Corporation
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 * SOFTWARE.
22 *
23 * Author:
24 * Zou Nan hai <[email protected]>
25 * Zhang Hua jun <[email protected]>
26 * Xing Dong sheng <[email protected]>
27 *
28 */
29 mov (8) g115.0<1>UD g1.0<8,8,1>UD {align1};
30
31 and.nz (1) null g2.0<1,1,1>UD 0x1UD{align1};
32 (f0) jmpi direct_idct;
33 add (1) g2.8<1>UD g115.8<1,1,1>UD 0UD{align1};
34 send (16) 0 g3.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
35 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
36 send (16) 0 g4.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
37 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
38 send (16) 0 g5.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
39 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
40 send (16) 0 g6.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
41 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
42 send (16) 0 g7.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
43 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
44 send (16) 0 g8.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
45 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
46 send (16) 0 g9.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
47 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
48 send (16) 0 g10.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
49 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
50 send (16) 0 g11.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
51 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
52 send (16) 0 g12.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
53 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
54 send (16) 0 g13.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
55 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
56 send (16) 0 g14.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
57 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
58 send (16) 0 g15.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
59 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
60 send (16) 0 g16.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
61 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
62 send (16) 0 g17.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
63 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
64 send (16) 0 g18.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
65 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
66 send (16) 0 g19.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
67 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
68 send (16) 0 g20.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
69 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
70 send (16) 0 g21.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
71 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
72 send (16) 0 g22.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
73 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
74 send (16) 0 g23<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
75 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
76 send (16) 0 g24.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
77 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
78 send (16) 0 g25.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
79 add (1) g2.8<1>UD g2.8<1,1,1>UD 32UD {align1};
80 send (16) 0 g26.0<1>UD g2<16,16,1>UD read(3, 0, 2, 0) mlen 1 rlen 1 { align1 };
81 direct_idct:
82 mov (1) g1.8<1>UD 0x00F000FUD {align1};
83 mov.sat (16) g3.0<2>UB g3.0<16,16,1>W {align1};
84 mov.sat (16) g4.0<2>UB g4.0<16,16,1>W {align1};
85 mov.sat (16) g5.0<2>UB g5.0<16,16,1>W {align1};
86 mov.sat (16) g6.0<2>UB g6.0<16,16,1>W {align1};
87 mov.sat (16) g7.0<2>UB g7.0<16,16,1>W {align1};
88 mov.sat (16) g8.0<2>UB g8.0<16,16,1>W {align1};
89 mov.sat (16) g9.0<2>UB g9.0<16,16,1>W {align1};
90 mov.sat (16) g10.0<2>UB g10.0<16,16,1>W {align1};
91 mov.sat (16) g11.0<2>UB g11.0<16,16,1>W {align1};
92 mov.sat (16) g12.0<2>UB g12.0<16,16,1>W {align1};
93 mov.sat (16) g13.0<2>UB g13.0<16,16,1>W {align1};
94 mov.sat (16) g14.0<2>UB g14.0<16,16,1>W {align1};
95 mov.sat (16) g15.0<2>UB g15.0<16,16,1>W {align1};
96 mov.sat (16) g16.0<2>UB g16.0<16,16,1>W {align1};
97 mov.sat (16) g17.0<2>UB g17.0<16,16,1>W {align1};
98 mov.sat (16) g18.0<2>UB g18.0<16,16,1>W {align1};
99
100 and.nz (1) null g1.30<1,1,1>UB 0x1UW{align1};
101 (f0) jmpi field_dct;
102 //Frame IDCT
103 mov (16) m1.0<1>UB g3.0<16,16,2>UB {align1};
104 mov (16) m1.16<1>UB g4.0<16,16,2>UB {align1};
105 mov (16) m2.0<1>UB g5.0<16,16,2>UB {align1};
106 mov (16) m2.16<1>UB g6.0<16,16,2>UB {align1};
107 mov (16) m3.0<1>UB g7.0<16,16,2>UB {align1};
108 mov (16) m3.16<1>UB g8.0<16,16,2>UB {align1};
109 mov (16) m4.0<1>UB g9.0<16,16,2>UB {align1};
110 mov (16) m4.16<1>UB g10.0<16,16,2>UB {align1};
111 mov (16) m5.0<1>UB g11.0<16,16,2>UB {align1};
112 mov (16) m5.16<1>UB g12.0<16,16,2>UB {align1};
113 mov (16) m6.0<1>UB g13.0<16,16,2>UB {align1};
114 mov (16) m6.16<1>UB g14.0<16,16,2>UB {align1};
115 mov (16) m7.0<1>UB g15.0<16,16,2>UB {align1};
116 mov (16) m7.16<1>UB g16.0<16,16,2>UB {align1};
117 mov (16) m8.0<1>UB g17.0<16,16,2>UB {align1};
118 mov (16) m8.16<1>UB g18.0<16,16,2>UB {align1};
119 jmpi write_back;
120
121 field_dct:
122 //Field IDCT
123 mov (16) m1.0<1>UB g3.0<16,16,2>UB {align1};
124 mov (16) m1.16<1>UB g11.0<16,16,2>UB {align1};
125 mov (16) m2.0<1>UB g4.0<16,16,2>UB {align1};
126 mov (16) m2.16<1>UB g12.0<16,16,2>UB {align1};
127 mov (16) m3.0<1>UB g5.0<16,16,2>UB {align1};
128 mov (16) m3.16<1>UB g13.0<16,16,2>UB {align1};
129 mov (16) m4.0<1>UB g6.0<16,16,2>UB {align1};
130 mov (16) m4.16<1>UB g14.0<16,16,2>UB {align1};
131 mov (16) m5.0<1>UB g7.0<16,16,2>UB {align1};
132 mov (16) m5.16<1>UB g15.0<16,16,2>UB {align1};
133 mov (16) m6.0<1>UB g8.0<16,16,2>UB {align1};
134 mov (16) m6.16<1>UB g16.0<16,16,2>UB {align1};
135 mov (16) m7.0<1>UB g9.0<16,16,2>UB {align1};
136 mov (16) m7.16<1>UB g17.0<16,16,2>UB {align1};
137 mov (16) m8.0<1>UB g10.0<16,16,2>UB {align1};
138 mov (16) m8.16<1>UB g18.0<16,16,2>UB {align1};
139
140 write_back:
141 send (16) 0 acc0<1>UW g1<8,8,1>UW write(0,0,2,0) mlen 9 rlen 0 {align1};
142 //U
143 mov (1) g1.8<1>UD 0x0070007UD { align1 };
144 shr (2) g1.0<1>UD g115.0<2,2,1>UD 1D {align1};
145 mov.sat (16) g19.0<2>UB g19.0<16,16,1>W {align1};
146 mov.sat (16) g20.0<2>UB g20.0<16,16,1>W {align1};
147 mov.sat (16) g21.0<2>UB g21.0<16,16,1>W {align1};
148 mov.sat (16) g22.0<2>UB g22.0<16,16,1>W {align1};
149 mov (16) m1.0<1>UB g19.0<16,16,2>UB {align1};
150 mov (16) m1.16<1>UB g20.0<16,16,2>UB {align1};
151 mov (16) m2.0<1>UB g21.0<16,16,2>UB {align1};
152 mov (16) m2.16<1>UB g22.0<16,16,2>UB {align1};
153 send (16) 0 acc0<1>UW g1<8,8,1>UW write(1, 0, 2, 0) mlen 3 rlen 0 { align1 };
154 //V
155 mov.sat (16) g23.0<2>UB g23.0<16,16,1>W {align1};
156 mov.sat (16) g24.0<2>UB g24.0<16,16,1>W {align1};
157 mov.sat (16) g25.0<2>UB g25.0<16,16,1>W {align1};
158 mov.sat (16) g26.0<2>UB g26.0<16,16,1>W {align1};
159 mov (16) m1.0<1>UB g23.0<16,16,2>UB {align1};
160 mov (16) m1.16<1>UB g24.0<16,16,2>UB {align1};
161 mov (16) m2.0<1>UB g25.0<16,16,2>UB {align1};
162 mov (16) m2.16<1>UB g26.0<16,16,2>UB {align1};
163 send (16) 0 acc0<1>UW g1<8,8,1>UW write(2, 0, 2, 0) mlen 3 rlen 0 { align1 };
164
165 send (16) 0 acc0<1>UW g0<8,8,1>UW
166 thread_spawner(0, 0, 0) mlen 1 rlen 0 { align1 EOT};