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 <nanhai.zou@intel.com>
25 *    Zhang Hua jun <huajun.zhang@intel.com>
26 *    Xing Dong sheng <dongsheng.xing@intel.com>
27 *
28 */
29mov (8) g76.0<1>UD g1.0<8,8,1>UD {align1};
30//mov (8) g77.0<1>UD g2.0<8,8,1>UD {align1};
31
32include(`block_clear.g4i')
33mov (8) g115.0<1>UD g1.0<8,8,1>UD {align1};
34mov (8) g116.0<1>UD g1.0<8,8,1>UD {align1};
35/*Y buffer*/
36mov(1) g1.8<1>UD 0x007000fUD  { align1 };
37asr (2) g115.14<1>W g1.14<2,2,1>W 1UW {align1};
38add (2) g115.0<1>UD g116.0<2,2,1>UD g115.14<2,2,1>W {align1};
39and (1) g115.4<1>UD g115.4<1,1,1>UD 0xFFFFFFFEUD {align1};
40mov (1) g115.8<1>UD 0x1fUD  { align1 }; //read 1 line, 32 columns.
41/*first vector*/
42and.nz (1) null g1.31<1,1,1>UB 0x1UW {align1};
43(f0) add (1) g115.4<1>UD g115.4<1,1,1>UD 1UD {align1};
44define(`surface',`4')
45define(`mv1',`g1.14')
46define(`mv2',`g1.16')
47include(`motion_field_y.g4i')
48mov (8) g28.0<1>UD g96.0<8,8,1>UD {align1};
49mov (8) g30.0<1>UD g97.0<8,8,1>UD {align1};
50mov (8) g32.0<1>UD g98.0<8,8,1>UD {align1};
51mov (8) g34.0<1>UD g99.0<8,8,1>UD {align1};
52mov (8) g36.0<1>UD g100.0<8,8,1>UD {align1};
53mov (8) g38.0<1>UD g101.0<8,8,1>UD {align1};
54mov (8) g40.0<1>UD g102.0<8,8,1>UD {align1};
55mov (8) g42.0<1>UD g103.0<8,8,1>UD {align1};
56/*second vector*/
57asr (2) g115.14<1>W g1.22<2,2,1>W 1UW {align1};
58add (2) g115.0<1>UD g116.0<2,2,1>UD g115.14<2,2,1>W {align1};
59and (1) g115.4<1>UD g115.4<1,1,1>UD 0xFFFFFFFEUD {align1};
60mov (1) g115.8<1>UD 0x1fUD { align1 };              //read 1 line, 32 columns.
61
62and.nz (1) null g1.31<1,1,1>UB 0x4UW {align1};
63(f0) add (1) g115.4<1>UD g115.4<1,1,1>UD 1UD {align1};
64define(`surface',`4')
65define(`mv1',`g1.22')
66define(`mv2',`g1.24')
67include(`motion_field_y.g4i')
68mov (8) g29.0<1>UD g96.0<8,8,1>UD {align1};
69mov (8) g31.0<1>UD g97.0<8,8,1>UD {align1};
70mov (8) g33.0<1>UD g98.0<8,8,1>UD {align1};
71mov (8) g35.0<1>UD g99.0<8,8,1>UD {align1};
72mov (8) g37.0<1>UD g100.0<8,8,1>UD {align1};
73mov (8) g39.0<1>UD g101.0<8,8,1>UD {align1};
74mov (8) g41.0<1>UD g102.0<8,8,1>UD {align1};
75mov (8) g43.0<1>UD g103.0<8,8,1>UD {align1};
76/*U buffer,  V buffer*/
77/*first vector*/
78mov(1) g115.8<1>UD 0x007000fUD  { align1 };
79asr (2) g115.14<1>W g1.14<2,2,1>W 2UW {align1};
80asr (2) g115.0<1>D g116.0<2,2,1>D 1D {align1};
81add (2) g115.0<1>D g115.0<2,2,1>D g115.14<2,2,1>W {align1};
82and (1) g115.4<1>UD g115.4<1,1,1>UD 0xFFFFFFFEUD {align1};
83
84and.nz (1) null g1.31<1,1,1>UB 0x1UW {align1};
85(f0) add (1) g115.4<1>UD g115.4<1,1,1>UD 1UD {align1};
86define(`surface_u',`5')
87define(`surface_v',`6')
88define(`mv1',`g1.14')
89define(`mv2',`g1.16')
90include(`motion_field_uv.g4i')
91mov (8) g44.0<1>UW g78.0<8,8,1>UW {align1};
92mov (8) g45.0<1>UW g79.0<8,8,1>UW {align1};
93mov (8) g46.0<1>UW g80.0<8,8,1>UW {align1};
94mov (8) g47.0<1>UW g81.0<8,8,1>UW {align1};
95mov (8) g48.0<1>UW g82.0<8,8,1>UW {align1};
96mov (8) g49.0<1>UW g83.0<8,8,1>UW {align1};
97mov (8) g50.0<1>UW g84.0<8,8,1>UW {align1};
98mov (8) g51.0<1>UW g85.0<8,8,1>UW {align1};
99/*second vector*/
100asr (2) g115.14<1>W g1.22<2,2,1>W 2UW {align1};
101asr (2) g115.0<1>D g116.0<2,2,1>D 1D {align1};
102add (2) g115.0<1>D g115.0<2,2,1>D g115.14<2,2,1>W {align1};
103and (1) g115.4<1>UD g115.4<1,1,1>UD 0xFFFFFFFEUD {align1};
104
105and.nz (1) null g1.31<1,1,1>UB 0x4UW {align1};
106(f0) add (1) g115.4<1>UD g115.4<1,1,1>UD 1UD {align1};
107define(`mv1',`g1.22')
108define(`mv2',`g1.24')
109include(`motion_field_uv.g4i')
110mov (8) g44.16<1>UW g78.0<8,8,1>UW {align1};
111mov (8) g45.16<1>UW g79.0<8,8,1>UW {align1};
112mov (8) g46.16<1>UW g80.0<8,8,1>UW {align1};
113mov (8) g47.16<1>UW g81.0<8,8,1>UW {align1};
114mov (8) g48.16<1>UW g82.0<8,8,1>UW {align1};
115mov (8) g49.16<1>UW g83.0<8,8,1>UW {align1};
116mov (8) g50.16<1>UW g84.0<8,8,1>UW {align1};
117mov (8) g51.16<1>UW g85.0<8,8,1>UW {align1};
118
119include(`addidct.g4i')
120//send (16) 0 acc0<1>UW g0<8,8,1>UW 
121//	thread_spawner(0, 0, 0) mlen 1 rlen 0 { align1 EOT};
122