dsputil_arm.S 4.37 KB
Newer Older
1
@
2
@ ARMv4 optimized DSP utils
3 4
@ Copyright (c) 2004 AGAWA Koji <i (AT) atty (DOT) jp>
@
5 6 7
@ This file is part of FFmpeg.
@
@ FFmpeg is free software; you can redistribute it and/or
8 9
@ modify it under the terms of the GNU Lesser General Public
@ License as published by the Free Software Foundation; either
10
@ version 2.1 of the License, or (at your option) any later version.
11
@
12
@ FFmpeg is distributed in the hope that it will be useful,
13 14 15 16 17
@ but WITHOUT ANY WARRANTY; without even the implied warranty of
@ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
@ Lesser General Public License for more details.
@
@ You should have received a copy of the GNU Lesser General Public
18
@ License along with FFmpeg; if not, write to the Free Software
19
@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 21
@

22
#include "config.h"
23
#include "libavutil/arm/asm.S"
24

25
#if !HAVE_ARMV5TE_EXTERNAL
26
#define pld @
27 28
#endif

29
        .align 5
30 31
@ void ff_add_pixels_clamped_arm(int16_t *block, uint8_t *dest, int stride)
function ff_add_pixels_clamped_arm, export=1
32 33 34 35 36 37 38 39 40
        push            {r4-r10}
        mov             r10, #8
1:
        ldr             r4,  [r1]               /* load dest */
        /* block[0] and block[1]*/
        ldrsh           r5,  [r0]
        ldrsh           r7,  [r0, #2]
        and             r6,  r4,  #0xFF
        and             r8,  r4,  #0xFF00
41
        add             r6,  r6,  r5
42 43 44 45
        add             r8,  r7,  r8,  lsr #8
        mvn             r5,  r5
        mvn             r7,  r7
        tst             r6,  #0x100
46
        it              ne
47 48
        movne           r6,  r5,  lsr #24
        tst             r8,  #0x100
49
        it              ne
50 51 52
        movne           r8,  r7,  lsr #24
        mov             r9,  r6
        ldrsh           r5,  [r0, #4]           /* moved form [A] */
53
        orr             r9,  r9,  r8,  lsl #8
54 55 56 57 58
        /* block[2] and block[3] */
        /* [A] */
        ldrsh           r7,  [r0, #6]
        and             r6,  r4,  #0xFF0000
        and             r8,  r4,  #0xFF000000
59 60
        add             r6,  r5,  r6,  lsr #16
        add             r8,  r7,  r8,  lsr #24
61 62 63
        mvn             r5,  r5
        mvn             r7,  r7
        tst             r6,  #0x100
64
        it              ne
65 66
        movne           r6,  r5,  lsr #24
        tst             r8,  #0x100
67
        it              ne
68
        movne           r8,  r7,  lsr #24
69
        orr             r9,  r9,  r6,  lsl #16
70
        ldr             r4,  [r1, #4]           /* moved form [B] */
71
        orr             r9,  r9,  r8,  lsl #24
72 73 74 75 76 77 78 79 80 81 82
        /* store dest */
        ldrsh           r5,  [r0, #8]           /* moved form [C] */
        str             r9,  [r1]

        /* load dest */
        /* [B] */
        /* block[4] and block[5] */
        /* [C] */
        ldrsh           r7,  [r0, #10]
        and             r6,  r4,  #0xFF
        and             r8,  r4,  #0xFF00
83
        add             r6,  r6,  r5
84
        add             r8,  r7,  r8,  lsr #8
85 86 87
        mvn             r5,  r5
        mvn             r7,  r7
        tst             r6,  #0x100
88
        it              ne
89 90
        movne           r6,  r5,  lsr #24
        tst             r8,  #0x100
91
        it              ne
92 93 94
        movne           r8,  r7,  lsr #24
        mov             r9,  r6
        ldrsh           r5,  [r0, #12]          /* moved from [D] */
95
        orr             r9,  r9,  r8,  lsl #8
96 97 98 99 100
        /* block[6] and block[7] */
        /* [D] */
        ldrsh           r7,  [r0, #14]
        and             r6,  r4,  #0xFF0000
        and             r8,  r4,  #0xFF000000
101 102
        add             r6,  r5,  r6,  lsr #16
        add             r8,  r7,  r8,  lsr #24
103 104 105
        mvn             r5,  r5
        mvn             r7,  r7
        tst             r6,  #0x100
106
        it              ne
107 108
        movne           r6,  r5,  lsr #24
        tst             r8,  #0x100
109
        it              ne
110
        movne           r8,  r7,  lsr #24
111
        orr             r9,  r9,  r6,  lsl #16
112
        add             r0,  r0,  #16           /* moved from [E] */
113
        orr             r9,  r9,  r8,  lsl #24
114 115 116 117 118 119 120 121 122 123 124
        subs            r10, r10, #1            /* moved from [F] */
        /* store dest */
        str             r9,  [r1, #4]

        /* [E] */
        /* [F] */
        add             r1,  r1,  r2
        bne             1b

        pop             {r4-r10}
        bx              lr
125
endfunc