f6224eae74
Tested by jsg@, kettenis@ and myself on a wide range of intel cards.
70 lines
2.6 KiB
Plaintext
70 lines
2.6 KiB
Plaintext
/*
|
|
* Copyright © 2008 Intel Corporation
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
* to deal in the Software without restriction, including without limitation
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice (including the next
|
|
* paragraph) shall be included in all copies or substantial portions of the
|
|
* Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*
|
|
* Author:
|
|
* Zou Nan hai <nanhai.zou@intel.com>
|
|
* Zhang Hua jun <huajun.zhang@intel.com>
|
|
* Xing Dong sheng <dongsheng.xing@intel.com>
|
|
*
|
|
*/
|
|
|
|
/* shader for backward predict mc
|
|
*/
|
|
mov (8) g76.0<1>UD g1.0<8,8,1>UD {align1};
|
|
//mov (8) g77.0<1>UD g2.0<8,8,1>UD {align1};
|
|
|
|
include(`block_clear.g4i')
|
|
|
|
mov (2) g1.14<1>UW g1.18<2,2,1>UW {align1};
|
|
/* save payload */
|
|
mov (8) g115.0<1>UD g1.0<8,8,1>UD {align1};
|
|
/* 8x8 media read/write payload */
|
|
mov (1) g1.8<1>UD 0x0070007UD {align1};
|
|
/* save payload, again */
|
|
define(`dest', `g118')
|
|
define(`input_surface', `7')
|
|
define(`mv1', `g115.14')
|
|
define(`mv2', `g115.16')
|
|
/* Y */
|
|
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */
|
|
asr (2) g1.14<1>W g115.14<2,2,1>W 1W {align1};
|
|
add (2) g2.0<1>UD g115.0<2,2,1>UD g1.14<2,2,1>W {align1};
|
|
include(`motion_frame_y.g4i')
|
|
/* motion_vector = motion_vector >> 1 */
|
|
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */
|
|
shr (2) g1.0<1>UD g115.0<2,2,1>UD 1UD {align1};
|
|
asr (2) g115.14<1>W g115.14<2,2,1>W 1W {align1};
|
|
asr (2) g1.14<1>W g115.14<2,2,1>W 1W {align1};
|
|
add (2) g2.0<1>UD g1.0<2,2,1>UD g1.14<2,2,1>W {align1};
|
|
/* U */
|
|
define(`input_surface1', `8')
|
|
define(`input_surface2', `9')
|
|
mov (1) g2.8<1>UD 0x007000fUD {align1};
|
|
include(`motion_frame_uv.g4i')
|
|
|
|
/* V */
|
|
/* (x', y') = (x, y) + (motion_vector.x >> 1, motion_vector.y >> 1) */
|
|
include(`addidct.g4i')
|
|
|
|
send (16) 0 acc0<1>UW g0<8,8,1>UW
|
|
thread_spawner(0, 0, 0) mlen 1 rlen 0 { align1 EOT};
|