1/*
2 * Copyright © 2006 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
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 *
23 * Authors:
24 *    Keith Packard <keithp@keithp.com>
25 *    Eric Anholt <eric@anholt.net>
26 *
27 */
28
29include(`exa_wm.g4i')
30
31define(`YCbCr_base',	`src_sample_base')
32
33define(`Cr',		`src_sample_r')
34define(`Cr_01',		`src_sample_r_01')
35define(`Cr_23',		`src_sample_r_23')
36
37define(`Y',		`src_sample_g')
38define(`Y_01',		`src_sample_g_01')
39define(`Y_23',		`src_sample_g_23')
40
41define(`Cb',		`src_sample_b')
42define(`Cb_01',		`src_sample_b_01')
43define(`Cb_23',		`src_sample_b_23')
44
45define(`Crn',		`mask_sample_r')
46define(`Crn_01',	`mask_sample_r_01')
47define(`Crn_23',	`mask_sample_r_23')
48
49define(`Yn',		`mask_sample_g')
50define(`Yn_01',		`mask_sample_g_01')
51define(`Yn_23',		`mask_sample_g_23')
52
53define(`Cbn',		`mask_sample_b')
54define(`Cbn_01',	`mask_sample_b_01')
55define(`Cbn_23',	`mask_sample_b_23')
56
57    /* color space conversion function:
58     * R = Clamp ( 1.164(Y-16/255) + 1.596(Cr-128/255), 0, 1)
59     * G = Clamp ( 1.164(Y-16/255) - 0.813(Cr-128/255) - 0.392(Cb-128/255), 0, 1)
60     * B = Clamp ( 1.164(Y-16/255) + 2.017(Cb-128/255), 0, 1)
61     */
62
63    /* Normalize Y, Cb and Cr:
64     *
65     * Yn = (Y - 16/255) * 1.164
66     * Crn = Cr - 128 / 255
67     * Cbn = Cb - 128 / 255
68     */
69add (16)    Yn<1>F		Y<8,8,1>F	-0.0627451F { compr align1 };
70mul (16)    Yn<1>F		Yn<8,8,1>F	1.164F	    { compr align1 };
71
72add (16)    Crn<1>F		Cr<8,8,1>F	-0.501961F  { compr align1 };
73
74add (16)    Cbn<1>F		Cb<8,8,1>F	-0.501961F  { compr align1 };
75
76    /* 
77     * R = Y + Cr * 1.596
78     */
79mov (8)    acc0<1>F		Yn<8,8,1>F		    { compr align1 };
80mac.sat(8) src_sample_r_01<1>F	Crn_01<8,8,1>F	1.596F	    { compr align1 };
81     
82mov (8)    acc0<1>F		Yn_23<8,8,1>F		    { compr align1 };
83mac.sat(8) src_sample_r_23<1>F	Crn_23<8,8,1>F	1.596F	    { compr align1 };
84    /*
85     * G = Crn * -0.813 + Cbn * -0.392 + Y
86     */
87mov (8)    acc0<1>F		Yn_23<8,8,1>F		    { compr align1 };
88mac (8)    acc0<1>F		Crn_01<8,8,1>F    	-0.813F	    { compr align1 };
89mac.sat(8) src_sample_g_01<1>F	Cbn_01<8,8,1>F    	-0.392F	    { compr align1 };
90
91mov (8)    acc0<1>F		Yn_23<8,8,1>F	    { compr align1 };
92mac (8)    acc0<1>F		Crn_23<8,8,1>F    	-0.813F	    { compr align1 };
93mac.sat(16) src_sample_g_23<1>F	Cbn_23<8,8,1>F    	-0.392F	    { compr align1 };
94    /*
95     * B = Cbn * 2.017 + Y
96     */
97mov (8)    acc0<1>F	        Yn_01<8,8,1>F		    { compr align1 };
98mac.sat(8) src_sample_b_01<1>F	Cbn_01<8,8,1>F     2.017F	    { compr align1 };
99
100mov (8)    acc0<1>F	        Yn_23<8,8,1>F		    { compr align1 };
101mac.sat(8) src_sample_b_23<1>F	Cbn_23<8,8,1>F     2.017F	    { compr align1 };
102    /*
103     * A = 1.0
104     */
105mov (16)    src_sample_a<1>F	1.0F			    { compr align1 };
106