1/*
2 * Copyright (C) 2013 The Android Open Source Project
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 *  * Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 *  * Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in
12 *    the documentation and/or other materials provided with the
13 *    distribution.
14 *
15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
16 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
17 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
18 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
19 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
20 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
21 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
22 * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
23 * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
25 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28    .text
29    .align
30
31    .global scanline_col32cb16blend_arm64
32
33//
34// This function alpha blends a fixed color into a destination scanline, using
35// the formula:
36//
37//     d = s + (((a + (a >> 7)) * d) >> 8)
38//
39// where d is the destination pixel,
40//       s is the source color,
41//       a is the alpha channel of the source color.
42//
43
44// x0 = destination buffer pointer
45// w1 = color value
46// w2 = count
47
48
49scanline_col32cb16blend_arm64:
50
51    lsr         w5, w1, #24                     // shift down alpha
52    mov         w9, #0xff                       // create mask
53    add         w5, w5, w5, lsr #7              // add in top bit
54    mov         w4, #256                        // create #0x100
55    sub         w5, w4, w5                      // invert alpha
56    and         w10, w1, #0xff                  // extract red
57    and         w12, w9, w1, lsr #8             // extract green
58    and         w4,  w9, w1, lsr #16            // extract blue
59    lsl         w10, w10, #5                    // prescale red
60    lsl         w12, w12, #6                    // prescale green
61    lsl         w4,  w4,  #5                    // prescale blue
62    lsr         w9,  w9,  #2                    // create dest green mask
63
641:
65    ldrh        w8, [x0]                        // load dest pixel
66    subs        w2, w2, #1                      // decrement loop counter
67    lsr         w6, w8, #11                     // extract dest red
68    and         w7, w9, w8, lsr #5              // extract dest green
69    and         w8, w8, #0x1f                   // extract dest blue
70
71    madd        w6, w6, w5, w10                 // dest red * alpha + src red
72    madd        w7, w7, w5, w12                 // dest green * alpha + src green
73    madd        w8, w8, w5, w4                  // dest blue * alpha + src blue
74
75    lsr         w6, w6, #8                      // shift down red
76    lsr         w7, w7, #8                      // shift down green
77    lsl         w6, w6, #11                     // shift red into 565
78    orr         w6, w6, w7, lsl #5              // shift green into 565
79    orr         w6, w6, w8, lsr #8              // shift blue into 565
80
81    strh        w6, [x0], #2                    // store pixel to dest, update ptr
82    b.ne        1b                              // if count != 0, loop
83
84    ret
85
86
87
88