2 * Copyright © 2013 Intel Corporation
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:
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
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
24 * Keith Packard <keithp@keithp.com>
25 * Eric Anholt <eric@anholt.net>
26 * Zhao Yakui <yakui.zhao@intel.com>
32 define(`YCbCr_base', `src_sample_base')
34 define(`Cr', `src_sample_b')
35 define(`Cr_01', `src_sample_b_01')
36 define(`Cr_23', `src_sample_b_23')
38 define(`Y', `src_sample_r')
39 define(`Y_01', `src_sample_r_01')
40 define(`Y_23', `src_sample_r_23')
42 define(`Cb', `src_sample_g')
43 define(`Cb_01', `src_sample_g_01')
44 define(`Cb_23', `src_sample_g_23')
46 define(`Crn', `mask_sample_g')
47 define(`Crn_01', `mask_sample_g_01')
48 define(`Crn_23', `mask_sample_g_23')
50 define(`Yn', `mask_sample_r')
51 define(`Yn_01', `mask_sample_r_01')
52 define(`Yn_23', `mask_sample_r_23')
54 define(`Cbn', `mask_sample_b')
55 define(`Cbn_01', `mask_sample_b_01')
56 define(`Cbn_23', `mask_sample_b_23')
58 /* color space conversion function:
59 * R = Clamp ( 1.164(Y-16/255) + 1.596(Cr-128/255), 0, 1)
60 * G = Clamp ( 1.164(Y-16/255) - 0.813(Cr-128/255) - 0.392(Cb-128/255), 0, 1)
61 * B = Clamp ( 1.164(Y-16/255) + 2.017(Cb-128/255), 0, 1)
64 /* Normalize Y, Cb and Cr:
66 * Yn = (Y - 16/255) * 1.164
67 * Crn = Cr - 128 / 255
68 * Cbn = Cb - 128 / 255
70 add (16) Yn<1>F Y<8;8,1>F -0.0627451F { compr align1 };
71 mul (16) Yn<1>F Yn<8;8,1>F 1.164F { compr align1 };
73 add (16) Crn<1>F Cr<8;8,1>F -0.501961F { compr align1 };
75 add (16) Cbn<1>F Cb<8;8,1>F -0.501961F { compr align1 };
80 mov (8) acc0<1>F Yn_01.0<8;8,1>F { align1 };
81 mac.sat(8) src_sample_r_01<1>F Crn_01<8;8,1>F 1.596F { align1 };
82 mov (8) acc0<1>F Yn_23.0<8;8,1>F { align1 };
83 mac.sat(8) src_sample_r_23<1>F Crn_23<8;8,1>F 1.596F { align1 };
86 * G = Crn * -0.813 + Cbn * -0.392 + Y
88 mov (8) acc0<1>F Yn_01.0<8;8,1>F { align1 };
89 mac (8) acc0<1>F Crn_01.0<8;8,1>F -0.813F { align1 };
90 mac.sat(8) src_sample_g_01<1>F Cbn_01.0<8;8,1>F -0.392F { align1 };
91 mov (8) acc0<1>F Yn_23.0<8;8,1>F { align1 };
92 mac (8) acc0<1>F Crn_23.0<8;8,1>F -0.813F { align1 };
93 mac.sat(8) src_sample_g_23<1>F Cbn_23.0<8;8,1>F -0.392F { align1 };
98 mov (8) acc0<1>F Yn_01.0<8;8,1>F { align1 };
99 mac.sat(8) src_sample_b_01<1>F Cbn_01.0<8;8,1>F 2.017F { align1 };
101 mov (8) acc0<1>F Yn_23.0<8;8,1>F { align1 };
102 mac.sat(8) src_sample_b_23<1>F Cbn_23.0<8;8,1>F 2.017F { align1 };
106 mov (16) src_sample_a<1>F 1.0F { compr align1 };