| 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 |
|
| 30 |
/* shader for backward predict mc |
| 31 |
*/ |
| 32 |
|
| 33 |
/* save payload */ |
| 34 |
mov (8) g76.0<1>UD g1.0<8,8,1>UD {align1}; |
| 35 |
//mov (8) g77.0<1>UD g2.0<8,8,1>UD {align1}; |
| 36 |
|
| 37 |
include(`block_clear.g4i') |
| 38 |
|
| 39 |
mov (8) g115.0<1>UD g1.0<8,8,1>UD {align1}; |
| 40 |
mov (1) g1.8<1>UD 0x0070007UD {align1}; |
| 41 |
define(`input_surface', `4') |
| 42 |
define(`mv1', `g115.14') |
| 43 |
define(`mv2', `g115.16') |
| 44 |
/* Y */ |
| 45 |
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */ |
| 46 |
asr (2) g1.14<1>W g115.14<2,2,1>W 1W {align1}; |
| 47 |
add (2) g2.0<1>UD g115.0<2,2,1>UD g1.14<2,2,1>W {align1}; |
| 48 |
include(`motion_frame_y.g4i') |
| 49 |
/* motion_vector = motion_vector >> 1 */ |
| 50 |
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */ |
| 51 |
/* U */ |
| 52 |
shr (2) g1.0<1>UD g115.0<2,2,1>UD 1UD {align1}; |
| 53 |
asr (2) g115.14<1>W g115.14<2,2,1>W 1W {align1}; |
| 54 |
asr (2) g1.14<1>W g115.14<2,2,1>W 1W {align1}; |
| 55 |
add (2) g2.0<1>UD g1.0<2,2,1>UD g1.14<2,2,1>W {align1}; |
| 56 |
define(`input_surface1', `5') |
| 57 |
define(`input_surface2', `6') |
| 58 |
mov (1) g2.8<1>UD 0x007000fUD {align1}; |
| 59 |
include(`motion_frame_uv.g4i') |
| 60 |
/* V */ |
| 61 |
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */ |
| 62 |
include(`addidct.g4i') |
| 63 |
|
| 64 |
send (16) 0 acc0<1>UW g0<8,8,1>UW |
| 65 |
thread_spawner(0, 0, 0) mlen 1 rlen 0 { align1 EOT}; |