aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/lpc_init.c
blob: f2fca53799afa2a6146ce59a15a5a15c94626b9f (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
/*
 * SIMD-optimized LPC functions
 * 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/attributes.h"
#include "libavutil/x86/asm.h"
#include "libavutil/x86/cpu.h"
#include "libavcodec/lpc.h"

void ff_lpc_apply_welch_window_sse2(const int32_t *data, ptrdiff_t len,
                                    double *w_data);
void ff_lpc_apply_welch_window_avx2(const int32_t *data, ptrdiff_t len,
                                    double *w_data);

DECLARE_ASM_CONST(16, double, pd_1)[2] = { 1.0, 1.0 };

#if HAVE_SSE2_INLINE

static void lpc_compute_autocorr_sse2(const double *data, ptrdiff_t 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(pd_1)", %%xmm0    \n\t"
                "movsd    "MANGLE(pd_1)", %%xmm1    \n\t"
                "movsd    "MANGLE(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)
                 NAMED_CONSTRAINTS_ARRAY_ADD(pd_1)
                :"memory"
            );
        } else {
            __asm__ volatile(
                "movsd    "MANGLE(pd_1)", %%xmm0    \n\t"
                "movsd    "MANGLE(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)
                 NAMED_CONSTRAINTS_ARRAY_ADD(pd_1)
            );
        }
    }
}

#endif /* HAVE_SSE2_INLINE */

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

#if HAVE_SSE2_INLINE
    if (INLINE_SSE2_SLOW(cpu_flags))
        c->lpc_compute_autocorr = lpc_compute_autocorr_sse2;
#endif

    if (EXTERNAL_SSE2(cpu_flags))
        c->lpc_apply_welch_window = ff_lpc_apply_welch_window_sse2;

    if (EXTERNAL_AVX2(cpu_flags))
        c->lpc_apply_welch_window = ff_lpc_apply_welch_window_avx2;
}