summaryrefslogtreecommitdiff
path: root/src/exa_sf_rotation.g4a
blob: 59d40d47b244bd893b7ab54f261451d4e865fef3 (plain)
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
52
53
54
55
/*
 * Copyright © 2007 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>
 */

/* 1/dx */
send (1) 0 g6<1>F g1.12<0,1,0>F math inv scalar mlen 1 rlen 1 { align1 };
/* 1/dy */
send (1) 0 g6.4<1>F g1.20<0,1,0>F math inv scalar mlen 1 rlen 1 { align1 };
/* du, dv */
mul (1) g7<1>F g3<0,1,0>F -1.0F { align1 };
mul (1) g7.4<1>F g3.4<0,1,0>F -1.0F { align1 };
add (1) g7<1>F g4<0,1,0>F g7<0,1,0>F { align1 };
add (1) g7.4<1>F g4.4<0,1,0>F g7.4<0,1,0>F { align1 };

/* du/dy */
mul (1) g7<1>F g7<0,1,0>F g6.4<0,1,0>F { align1 };
/* dv/dx */
mul (1) g7.4<1>F g7.4<0,1,0>F g6<0,1,0>F { align1 };
/* Cx */
mov (8) m1<1>F g7<0,1,0>F { align1 };
/* Cy */
mov (8) m2<1>F g7.4<0,1,0>F { align1 };
/* Co */
mov (8) m3<1>F g3<8,8,1>F { align1 };
send (8) 0 null g0<8,8,1>F urb 0 transpose used complete mlen 4 rlen 0 { align1 EOT };
nop;
nop;
nop;
nop;
nop;
nop;
nop;
nop;