summaryrefslogtreecommitdiff
path: root/libavcodec/x86/dsputil_mmx_qns_template.c
blob: 77a41b9dcbe024f69318084cb898d4c578bc7d07 (plain)
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
/*
 * DSP utils : QNS functions are compiled 3 times for mmx/3dnow/ssse3
 * Copyright (c) 2004 Michael Niedermayer
 *
 * MMX optimization by Michael Niedermayer <michaelni@gmx.at>
 * 3DNow! and SSSE3 optimization by Zuxy Meng <zuxy.meng@gmail.com>
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * 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
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#define MAX_ABS (512 >> (SCALE_OFFSET>0 ? SCALE_OFFSET : 0))

static int DEF(try_8x8basis)(int16_t rem[64], int16_t weight[64], int16_t basis[64], int scale)
{
    x86_reg i=0;

    assert(FFABS(scale) < MAX_ABS);
    scale<<= 16 + SCALE_OFFSET - BASIS_SHIFT + RECON_SHIFT;

    SET_RND(mm6);
    __asm__ volatile(
        "pxor %%mm7, %%mm7              \n\t"
        "movd  %4, %%mm5                \n\t"
        "punpcklwd %%mm5, %%mm5         \n\t"
        "punpcklwd %%mm5, %%mm5         \n\t"
        ".p2align 4                     \n\t"
        "1:                             \n\t"
        "movq  (%1, %0), %%mm0          \n\t"
        "movq  8(%1, %0), %%mm1         \n\t"
        PMULHRW(%%mm0, %%mm1, %%mm5, %%mm6)
        "paddw (%2, %0), %%mm0          \n\t"
        "paddw 8(%2, %0), %%mm1         \n\t"
        "psraw $6, %%mm0                \n\t"
        "psraw $6, %%mm1                \n\t"
        "pmullw (%3, %0), %%mm0         \n\t"
        "pmullw 8(%3, %0), %%mm1        \n\t"
        "pmaddwd %%mm0, %%mm0           \n\t"
        "pmaddwd %%mm1, %%mm1           \n\t"
        "paddd %%mm1, %%mm0             \n\t"
        "psrld $4, %%mm0                \n\t"
        "paddd %%mm0, %%mm7             \n\t"
        "add $16, %0                    \n\t"
        "cmp $128, %0                   \n\t" //FIXME optimize & bench
        " jb 1b                         \n\t"
        PHADDD(%%mm7, %%mm6)
        "psrld $2, %%mm7                \n\t"
        "movd %%mm7, %0                 \n\t"

        : "+r" (i)
        : "r"(basis), "r"(rem), "r"(weight), "g"(scale)
    );
    return i;
}

static void DEF(add_8x8basis)(int16_t rem[64], int16_t basis[64], int scale)
{
    x86_reg i=0;

    if(FFABS(scale) < MAX_ABS){
        scale<<= 16 + SCALE_OFFSET - BASIS_SHIFT + RECON_SHIFT;
        SET_RND(mm6);
        __asm__ volatile(
                "movd  %3, %%mm5        \n\t"
                "punpcklwd %%mm5, %%mm5 \n\t"
                "punpcklwd %%mm5, %%mm5 \n\t"
                ".p2align 4             \n\t"
                "1:                     \n\t"
                "movq  (%1, %0), %%mm0  \n\t"
                "movq  8(%1, %0), %%mm1 \n\t"
                PMULHRW(%%mm0, %%mm1, %%mm5, %%mm6)
                "paddw (%2, %0), %%mm0  \n\t"
                "paddw 8(%2, %0), %%mm1 \n\t"
                "movq %%mm0, (%2, %0)   \n\t"
                "movq %%mm1, 8(%2, %0)  \n\t"
                "add $16, %0            \n\t"
                "cmp $128, %0           \n\t" // FIXME optimize & bench
                " jb 1b                 \n\t"

                : "+r" (i)
                : "r"(basis), "r"(rem), "g"(scale)
        );
    }else{
        for(i=0; i<8*8; i++){
            rem[i] += (basis[i]*scale + (1<<(BASIS_SHIFT - RECON_SHIFT-1)))>>(BASIS_SHIFT - RECON_SHIFT);
        }
    }
}