1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
/*
* Copyright © 2006 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.
*
* Authors:
* Wang Zhenyu <zhenyu.z.wang@intel.com>
* Keith Packard <keithp@keithp.com>
*/
/********** Compute w *************/
mul (16) temp_x<1>F dst_x<8,8,1>F dw_dx { compr align1 };
mul (16) temp_y<1>F dst_y<8,8,1>F dw_dy { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F temp_y<8,8,1>F { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F wo { compr align1 };
send (8) 0 w_0<1>F temp_x_0<8,8,1>F math inv mlen 1 rlen 1 { align1 };
send (8) 0 w_1<1>F temp_x_1<8,8,1>F math inv mlen 1 rlen 1 { sechalf align1 };
/********** Compute u *************/
mul (16) temp_x<1>F dst_x<8,8,1>F du_dx { compr align1 };
mul (16) temp_y<1>F dst_y<8,8,1>F du_dy { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F temp_y<8,8,1>F { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F uo { compr align1 };
mul (16) u<1>F temp_x<8,8,1>F w<8,8,1>F { compr align1 };
/********** Compute v *************/
mul (16) temp_x<1>F dst_x<8,8,1>F dv_dx { compr align1 };
mul (16) temp_y<1>F dst_y<8,8,1>F dv_dy { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F temp_y<8,8,1>F { compr align1 };
add (16) temp_x<1>F temp_x<8,8,1>F vo { compr align1 };
mul (16) v<1>F temp_x<8,8,1>F w<8,8,1>F { compr align1 };
|
