Debian Codegraph @

src/shaders/vme/intra_frame_ivb.asm

raw
1 /*
2 * Copyright © <2010>, 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
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sub license, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
11 *
12 * The above copyright notice and this permission notice (including the
13 * next paragraph) shall be included in all copies or substantial portions
14 * of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
17 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
19 * IN NO EVENT SHALL PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR
20 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
21 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
22 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
23 *
24 */
25 // Modual name: IntraFrame.asm
26 //
27 // Make intra predition estimation for Intra frame
28 //
29
30 //
31 // Now, begin source code....
32 //
33
34 /*
35 * __START
36 */
37 __INTRA_START:
38 mov (16) tmp_reg0.0<1>:UD 0x0:UD {align1};
39 mov (16) tmp_reg2.0<1>:UD 0x0:UD {align1};
40 mov (16) tmp_reg4.0<1>:UD 0x0:UD {align1} ;
41 mov (16) tmp_reg6.0<1>:UD 0x0:UD {align1} ;
42
43 shl (2) read0_header.0<1>:D orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */
44 add (1) read0_header.0<1>:D read0_header.0<0,1,0>:D -8:W {align1}; /* X offset */
45 add (1) read0_header.4<1>:D read0_header.4<0,1,0>:D -1:W {align1}; /* Y offset */
46 mov (1) read0_header.8<1>:UD BLOCK_32X1 {align1};
47 mov (1) read0_header.20<1>:UB thread_id_ub {align1}; /* dispatch id */
48
49 shl (2) read1_header.0<1>:D orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */
50 add (1) read1_header.0<1>:D read1_header.0<0,1,0>:D -4:W {align1}; /* X offset */
51 mov (1) read1_header.8<1>:UD BLOCK_4X16 {align1};
52 mov (1) read1_header.20<1>:UB thread_id_ub {align1}; /* dispatch id */
53
54 shl (2) vme_m0.8<1>:UW orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */
55 mov (1) vme_m0.20<1>:UB thread_id_ub {align1}; /* dispatch id */
56
57 mul (1) obw_m0.8<1>:UD w_in_mb_uw<0,1,0>:UW orig_y_ub<0,1,0>:UB {align1};
58 add (1) obw_m0.8<1>:UD obw_m0.8<0,1,0>:UD orig_x_ub<0,1,0>:UB {align1};
59 mov (1) obw_m0.20<1>:UB thread_id_ub {align1}; /* dispatch id */
60
61 /*
62 * Media Read Message -- fetch Luma neighbor edge pixels
63 */
64 /* ROW */
65 mov (8) msg_reg0.0<1>:UD read0_header.0<8,8,1>:UD {align1};
66 send (8) msg_ind INEP_ROW<1>:UB null read(BIND_IDX_INEP, 0, 0, 4) mlen 1 rlen 1 {align1};
67
68 /* COL */
69 mov (8) msg_reg0.0<1>:UD read1_header.0<8,8,1>:UD {align1};
70 send (8) msg_ind INEP_COL0<1>:UB null read(BIND_IDX_INEP, 0, 0, 4) mlen 1 rlen 2 {align1};
71
72 /* m0 */
73 mov (8) vme_msg_0.0<1>:UD vme_m0.0<8,8,1>:UD {align1};
74
75 /* m2 */
76 mov (8) vme_msg_2<1>:UD 0x0:UD {align1};
77
78 /*
79 * VME message
80 */
81 /* m0 */
82 mov (8) vme_msg_0.0<1>:UD vme_m0.0<8,8,1>:UD {align1};
83
84 /* m1 */
85 mov (8) vme_m1.0<1>:ud 0x0:ud {align1};
86 and.z.f0.0 (1) null<1>:UW transform_8x8_ub<0,1,0>:UB 1:UW {align1};
87 (f0.0) mov (1) intra_part_mask_ub<1>:UB LUMA_INTRA_8x8_DISABLE:uw {align1};
88
89 /* assign MB intra struct from the thread payload*/
90 mov (1) mb_intra_struct_ub<1>:UB input_mb_intra_ub<0,1,0>:UB {align1};
91
92 mov (8) vme_msg_1<1>:UD vme_m1.0<8,8,1>:UD {align1};
93
94 /* m2 */
95 mov (8) vme_msg_2<1>:UD 0x0:UD {align1};
96
97 /* m3 */
98 mov (1) INEP_ROW.0<1>:UD 0x0:UD {align1};
99 and (1) INEP_ROW.4<1>:UD INEP_ROW.4<0,1,0>:UD 0xFF000000:UD {align1};
100 mov (8) vme_msg_3<1>:UD INEP_ROW.0<8,8,1>:UD {align1};
101
102 /* m4 */
103 mov (8) vme_msg_4<1>:UD 0x0 {align1};
104 mov (16) vme_msg_4.0<1>:UB INEP_COL0.3<32,8,4>:UB {align1};
105 mov (1) vme_msg_4.16<1>:UD INTRA_PREDICTORE_MODE {align1};
106
107 mov (1) tmp_reg0.0<1>:ud qp_ub<0,1,0>:ub {align1};
108 /* lut_subindex */
109 and (1) tmp_reg1.0<1>:ud tmp_reg0.0<0,1,0>:ud 0x06:ud {align1};
110 shl (1) tmp_reg0.4<1>:ud tmp_reg1.0<0,1,0>:ud 10:ud {align1};
111
112 /* lut_index */
113 and (1) tmp_reg1.0<1>:ud tmp_reg0.0<0,1,0>:ud 0x038:ud {align1};
114 shl (1) tmp_reg1.4<1>:ud tmp_reg1.0<0,1,0>:ud 5:ud {align1};
115
116 add (1) tmp_reg0.0<1>:ud tmp_reg0.4<0,1,0>:ud tmp_reg1.4<0,1,0>:ud {align1};
117 /* Use one register as the descriptor of send instruction */
118
119 add (1) a0.0<1>:ud tmp_reg0.0<0,1,0>:ud 0x0a184000:ud {align1};
120 send (1) vme_wb.0<1>:ud vme_msg_0 0x08 a0.0<0,1,0>:ud {align1};
121
122 /*
123 * Oword Block Write message
124 */
125 mov (8) msg_reg0.0<1>:UD obw_m0<8,8,1>:UD {align1};
126
127 mov (1) msg_reg1.0<1>:UD vme_wb.0<0,1,0>:UD {align1};
128 mov (1) msg_reg1.4<1>:UD vme_wb.16<0,1,0>:UD {align1};
129 mov (1) msg_reg1.8<1>:UD vme_wb.20<0,1,0>:UD {align1};
130 mov (1) msg_reg1.12<1>:UD vme_wb.24<0,1,0>:UD {align1};
131
132 /* bind index 3, write 2 oword (32bytes), msg type: 8(OWord Block Write) */
133 send (16)
134 msg_ind
135 obw_wb
136 null
137 data_port(
138 OBW_CACHE_TYPE,
139 OBW_MESSAGE_TYPE,
140 OBW_CONTROL_0,
141 OBW_BIND_IDX,
142 OBW_WRITE_COMMIT_CATEGORY,
143 OBW_HEADER_PRESENT
144 )
145 mlen 2
146 rlen obw_wb_length
147 {align1};
148
149 __EXIT:
150 /*
151 * kill thread
152 */
153 mov (8) ts_msg_reg0<1>:UD r0<8,8,1>:UD {align1};
154 send (16) ts_msg_ind acc0<1>UW null thread_spawner(0, 0, 1) mlen 1 rlen 0 {align1 EOT};