dca.h 4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 * Copyright (c) 2011 Mans Rullgard <mans@mansr.com>
 *
 * This file is part of Libav.
 *
 * Libav 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.
 *
 * Libav 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 Libav; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#ifndef AVCODEC_ARM_DCA_H
#define AVCODEC_ARM_DCA_H

#include <stdint.h>
25

26
#include "config.h"
27
#include "libavcodec/mathops.h"
28

29
#if HAVE_ARMV6_INLINE && AV_GCC_VERSION_AT_LEAST(4,4) && !CONFIG_THUMB
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

#define decode_blockcodes decode_blockcodes
static inline int decode_blockcodes(int code1, int code2, int levels,
                                    int *values)
{
    int v0, v1, v2, v3, v4, v5;

    __asm__ ("smmul   %8,  %14, %18           \n"
             "smmul   %11, %15, %18           \n"
             "smlabb  %14, %8,  %17, %14      \n"
             "smlabb  %15, %11, %17, %15      \n"
             "smmul   %9,  %8,  %18           \n"
             "smmul   %12, %11, %18           \n"
             "sub     %14, %14, %16, lsr #1   \n"
             "sub     %15, %15, %16, lsr #1   \n"
             "smlabb  %8,  %9,  %17, %8       \n"
             "smlabb  %11, %12, %17, %11      \n"
             "smmul   %10, %9,  %18           \n"
             "smmul   %13, %12, %18           \n"
             "str     %14, %0                 \n"
             "str     %15, %4                 \n"
             "sub     %8,  %8,  %16, lsr #1   \n"
             "sub     %11, %11, %16, lsr #1   \n"
             "smlabb  %9,  %10, %17, %9       \n"
             "smlabb  %12, %13, %17, %12      \n"
             "smmul   %14, %10, %18           \n"
             "smmul   %15, %13, %18           \n"
             "str     %8,  %1                 \n"
             "str     %11, %5                 \n"
             "sub     %9,  %9,  %16, lsr #1   \n"
             "sub     %12, %12, %16, lsr #1   \n"
             "smlabb  %10, %14, %17, %10      \n"
             "smlabb  %13, %15, %17, %13      \n"
             "str     %9,  %2                 \n"
             "str     %12, %6                 \n"
             "sub     %10, %10, %16, lsr #1   \n"
             "sub     %13, %13, %16, lsr #1   \n"
             "str     %10, %3                 \n"
             "str     %13, %7                 \n"
             : "=m"(values[0]), "=m"(values[1]),
               "=m"(values[2]), "=m"(values[3]),
               "=m"(values[4]), "=m"(values[5]),
               "=m"(values[6]), "=m"(values[7]),
               "=&r"(v0), "=&r"(v1), "=&r"(v2),
               "=&r"(v3), "=&r"(v4), "=&r"(v5),
               "+&r"(code1), "+&r"(code2)
             : "r"(levels - 1), "r"(-levels), "r"(ff_inverse[levels]));

    return code1 | code2;
}

#endif
82

83
#if HAVE_NEON_INLINE && HAVE_ASM_MOD_Y
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105

#define int8x8_fmul_int32 int8x8_fmul_int32
static inline void int8x8_fmul_int32(float *dst, const int8_t *src, int scale)
{
    __asm__ ("vcvt.f32.s32 %2,  %2,  #4         \n"
             "vld1.8       {d0},     [%1,:64]   \n"
             "vmovl.s8     q0,  d0              \n"
             "vmovl.s16    q1,  d1              \n"
             "vmovl.s16    q0,  d0              \n"
             "vcvt.f32.s32 q0,  q0              \n"
             "vcvt.f32.s32 q1,  q1              \n"
             "vmul.f32     q0,  q0,  %y2        \n"
             "vmul.f32     q1,  q1,  %y2        \n"
             "vst1.32      {q0-q1},  [%m0,:128] \n"
             : "=Um"(*(float (*)[8])dst)
             : "r"(src), "x"(scale)
             : "d0", "d1", "d2", "d3");
}

#endif

#endif /* AVCODEC_ARM_DCA_H */