1/*
2 * Copyright © 2009 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 *    Yan Li <li.l.yan@intel.com>
26 *    Liu Xi bin<xibin.liu@intel.com>
27 */
28/* GRF allocation:
29   g1~g30: constant buffer
30           g1~g2:intra IQ matrix
31           g3~g4:non intra IQ matrix
32           g5~g20:IDCT table
33   g31:    thread payload 
34   g32:    message descriptor for reading reference data
35   g58~g81:reference data
36   g82:    thread payload backup
37   g83~g106:IDCT data                           */
38mov (8) g82.0<1>UD g31.0<8,8,1>UD {align1};
39mov(2) g31.0<1>UD g82.12<2,2,1>UW {align1};
40mov (1) g126.8<1>UD ip {align1};
41mov (1) ip g21.0<1,1,1>UD {align1};
42 
43//Y, (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) 
44asr (2) g31.14<1>W g82.20<2,2,1>W 1W {align1};
45add (2) g32.0<1>UD g31.0<2,2,1>UD g31.14<2,2,1>W {align1};
46define(`input_surface',	`7')
47define(`mv1',	`g82.20')
48define(`mv2',	`g82.22') 
49include(`motion_frame_y.g4i')
50
51//UV, (x', y') = (x >> 1, y >> 1) + (motion_vector.x >> 2, motion_vector.y >> 2)
52shr (2) g31.0<1>UD g31.0<2,2,1>UD 1UD {align1};
53asr (2) g31.14<1>W g82.20<2,2,1>W 2W {align1};
54add (2) g32.0<1>UD g31.0<2,2,1>UD g31.14<2,2,1>W {align1};
55define(`input_surface1', `8')
56define(`input_surface2', `9')
57include(`motion_frame_uv.g4i')
58
59include(`addidct.g4i')
60send (16) 0 acc0<1>UW g0<8,8,1>UW 
61	thread_spawner(0, 0, 0) mlen 1 rlen 0 { align1 EOT};
62