aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/lpc_mmx.c
blob: 3a0a1f0f6fd6f49cadf47c644207fd8c88d27f4e (plain) (blame)
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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
/*
 * MMX optimized LPC DSP utils
 * Copyright (c) 2007 Loren Merritt
 *
 * 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
 */

#include "libavutil/x86_cpu.h"
#include "libavutil/cpu.h"
#include "libavcodec/lpc.h"

static void apply_welch_window_sse2(const int32_t *data, int len, double *w_data)
{
    double c = 2.0 / (len-1.0);
    int n2 = len>>1;
    x86_reg i = -n2*sizeof(int32_t);
    x86_reg j =  n2*sizeof(int32_t);
    __asm__ volatile(
        "movsd   %4,     %%xmm7                \n\t"
        "movapd  "MANGLE(ff_pd_1)", %%xmm6     \n\t"
        "movapd  "MANGLE(ff_pd_2)", %%xmm5     \n\t"
        "movlhps %%xmm7, %%xmm7                \n\t"
        "subpd   %%xmm5, %%xmm7                \n\t"
        "addsd   %%xmm6, %%xmm7                \n\t"
        "test    $1,     %5                    \n\t"
        "jz      2f                            \n\t"
#define WELCH(MOVPD, offset)\
        "1:                                    \n\t"\
        "movapd   %%xmm7,  %%xmm1              \n\t"\
        "mulpd    %%xmm1,  %%xmm1              \n\t"\
        "movapd   %%xmm6,  %%xmm0              \n\t"\
        "subpd    %%xmm1,  %%xmm0              \n\t"\
        "pshufd   $0x4e,   %%xmm0, %%xmm1      \n\t"\
        "cvtpi2pd (%3,%0), %%xmm2              \n\t"\
        "cvtpi2pd "#offset"*4(%3,%1), %%xmm3   \n\t"\
        "mulpd    %%xmm0,  %%xmm2              \n\t"\
        "mulpd    %%xmm1,  %%xmm3              \n\t"\
        "movapd   %%xmm2, (%2,%0,2)            \n\t"\
        MOVPD"    %%xmm3, "#offset"*8(%2,%1,2) \n\t"\
        "subpd    %%xmm5,  %%xmm7              \n\t"\
        "sub      $8,      %1                  \n\t"\
        "add      $8,      %0                  \n\t"\
        "jl 1b                                 \n\t"\

        WELCH("movupd", -1)
        "jmp 3f                                \n\t"
        "2:                                    \n\t"
        WELCH("movapd", -2)
        "3:                                    \n\t"
        :"+&r"(i), "+&r"(j)
        :"r"(w_data+n2), "r"(data+n2), "m"(c), "r"(len)
         XMM_CLOBBERS_ONLY("%xmm0", "%xmm1", "%xmm2", "%xmm3",
                                    "%xmm5", "%xmm6", "%xmm7")
    );
#undef WELCH
}

static void lpc_compute_autocorr_sse2(const double *data, int len, int lag,
                                   double *autoc)
{
    int j;

    if((x86_reg)data & 15)
        data++;

    for(j=0; j<lag; j+=2){
        x86_reg i = -len*sizeof(double);
        if(j == lag-2) {
            __asm__ volatile(
                "movsd    "MANGLE(ff_pd_1)", %%xmm0 \n\t"
                "movsd    "MANGLE(ff_pd_1)", %%xmm1 \n\t"
                "movsd    "MANGLE(ff_pd_1)", %%xmm2 \n\t"
                "1:                                 \n\t"
                "movapd   (%2,%0), %%xmm3           \n\t"
                "movupd -8(%3,%0), %%xmm4           \n\t"
                "movapd   (%3,%0), %%xmm5           \n\t"
                "mulpd     %%xmm3, %%xmm4           \n\t"
                "mulpd     %%xmm3, %%xmm5           \n\t"
                "mulpd -16(%3,%0), %%xmm3           \n\t"
                "addpd     %%xmm4, %%xmm1           \n\t"
                "addpd     %%xmm5, %%xmm0           \n\t"
                "addpd     %%xmm3, %%xmm2           \n\t"
                "add       $16,    %0               \n\t"
                "jl 1b                              \n\t"
                "movhlps   %%xmm0, %%xmm3           \n\t"
                "movhlps   %%xmm1, %%xmm4           \n\t"
                "movhlps   %%xmm2, %%xmm5           \n\t"
                "addsd     %%xmm3, %%xmm0           \n\t"
                "addsd     %%xmm4, %%xmm1           \n\t"
                "addsd     %%xmm5, %%xmm2           \n\t"
                "movsd     %%xmm0,   (%1)           \n\t"
                "movsd     %%xmm1,  8(%1)           \n\t"
                "movsd     %%xmm2, 16(%1)           \n\t"
                :"+&r"(i)
                :"r"(autoc+j), "r"(data+len), "r"(data+len-j)
                :"memory"
            );
        } else {
            __asm__ volatile(
                "movsd    "MANGLE(ff_pd_1)", %%xmm0 \n\t"
                "movsd    "MANGLE(ff_pd_1)", %%xmm1 \n\t"
                "1:                                 \n\t"
                "movapd   (%3,%0), %%xmm3           \n\t"
                "movupd -8(%4,%0), %%xmm4           \n\t"
                "mulpd     %%xmm3, %%xmm4           \n\t"
                "mulpd    (%4,%0), %%xmm3           \n\t"
                "addpd     %%xmm4, %%xmm1           \n\t"
                "addpd     %%xmm3, %%xmm0           \n\t"
                "add       $16,    %0               \n\t"
                "jl 1b                              \n\t"
                "movhlps   %%xmm0, %%xmm3           \n\t"
                "movhlps   %%xmm1, %%xmm4           \n\t"
                "addsd     %%xmm3, %%xmm0           \n\t"
                "addsd     %%xmm4, %%xmm1           \n\t"
                "movsd     %%xmm0, %1               \n\t"
                "movsd     %%xmm1, %2               \n\t"
                :"+&r"(i), "=m"(autoc[j]), "=m"(autoc[j+1])
                :"r"(data+len), "r"(data+len-j)
            );
        }
    }
}

av_cold void ff_lpc_init_x86(LPCContext *c)
{
    int mm_flags = av_get_cpu_flags();

    if (mm_flags & (AV_CPU_FLAG_SSE2|AV_CPU_FLAG_SSE2SLOW)) {
        c->lpc_apply_welch_window = apply_welch_window_sse2;
        c->lpc_compute_autocorr = lpc_compute_autocorr_sse2;
    }
}