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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
|
/*
* 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>
*/
/*
* Once the data are ready, write them to the destination
*/
include(`exa_wm.g4i')
/* m0, m1 are all direct passed by PS thread payload */
mov (8) m1<1>F g1<8,8,1>F { align1 };
/* prepare data in m2-m5 for subspan(1,0), m6-m9 for subspan(3,2), then it's ready to write */
/* src_sample0 -> m2
src_sample1 -> m6
src_sample2 -> m3
src_sample3 -> m7
src_sample4 -> m4
src_sample5 -> m8
src_sample6 -> m5
src_sample7 -> m9
*/
mov (8) m2<1>F src_sample0<8,8,1>F { align1 };
mov (8) m3<1>F src_sample2<8,8,1>F { align1 };
mov (8) m4<1>F src_sample4<8,8,1>F { align1 };
mov (8) m5<1>F src_sample6<8,8,1>F { align1 };
mov (8) m6<1>F src_sample1<8,8,1>F { align1 };
mov (8) m7<1>F src_sample3<8,8,1>F { align1 };
mov (8) m8<1>F src_sample5<8,8,1>F { align1 };
mov (8) m9<1>F src_sample7<8,8,1>F { align1 };
/* m0, m1 are all direct passed by PS thread payload */
mov (8) m1<1>UD g1<8,8,1>UD { align1 mask_disable };
/* write */
send (16) 0 acc0<1>UW g0<8,8,1>UW write (
0, /* binding_table */
8, /* pixel scordboard clear, msg type simd16 single source */
4, /* render target write */
0 /* no write commit message */
)
mlen 10
rlen 0
{ align1 EOT };
nop;
nop;
nop;
nop;
nop;
nop;
nop;
nop;
nop;
|
