idctdsp_msa.c 5.44 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 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
/*
 * Copyright (c) 2015 Manojkumar Bhosale (Manojkumar.Bhosale@imgtec.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
 */

#include "libavutil/mips/generic_macros_msa.h"
#include "idctdsp_mips.h"

static void put_pixels_clamped_msa(const int16_t *block, uint8_t *pixels,
                                   int32_t stride)
{
    uint64_t in0_d, in1_d, in2_d, in3_d, in4_d, in5_d, in6_d, in7_d;
    v8i16 in0, in1, in2, in3, in4, in5, in6, in7;

    LD_SH8(block, 8, in0, in1, in2, in3, in4, in5, in6, in7);
    CLIP_SH4_0_255(in0, in1, in2, in3);
    CLIP_SH4_0_255(in4, in5, in6, in7);
    PCKEV_B4_SH(in0, in0, in1, in1, in2, in2, in3, in3, in0, in1, in2, in3);
    PCKEV_B4_SH(in4, in4, in5, in5, in6, in6, in7, in7, in4, in5, in6, in7);

    in0_d = __msa_copy_u_d((v2i64) in0, 0);
    in1_d = __msa_copy_u_d((v2i64) in1, 0);
    in2_d = __msa_copy_u_d((v2i64) in2, 0);
    in3_d = __msa_copy_u_d((v2i64) in3, 0);
    in4_d = __msa_copy_u_d((v2i64) in4, 0);
    in5_d = __msa_copy_u_d((v2i64) in5, 0);
    in6_d = __msa_copy_u_d((v2i64) in6, 0);
    in7_d = __msa_copy_u_d((v2i64) in7, 0);
    SD4(in0_d, in1_d, in2_d, in3_d, pixels, stride);
    pixels += 4 * stride;
    SD4(in4_d, in5_d, in6_d, in7_d, pixels, stride);
}

static void put_signed_pixels_clamped_msa(const int16_t *block, uint8_t *pixels,
                                          int32_t stride)
{
    uint64_t in0_d, in1_d, in2_d, in3_d, in4_d, in5_d, in6_d, in7_d;
    v8i16 in0, in1, in2, in3, in4, in5, in6, in7;

    LD_SH8(block, 8, in0, in1, in2, in3, in4, in5, in6, in7);

    in0 += 128;
    in1 += 128;
    in2 += 128;
    in3 += 128;
    in4 += 128;
    in5 += 128;
    in6 += 128;
    in7 += 128;

    CLIP_SH4_0_255(in0, in1, in2, in3);
    CLIP_SH4_0_255(in4, in5, in6, in7);
    PCKEV_B4_SH(in0, in0, in1, in1, in2, in2, in3, in3, in0, in1, in2, in3);
    PCKEV_B4_SH(in4, in4, in5, in5, in6, in6, in7, in7, in4, in5, in6, in7);

    in0_d = __msa_copy_u_d((v2i64) in0, 0);
    in1_d = __msa_copy_u_d((v2i64) in1, 0);
    in2_d = __msa_copy_u_d((v2i64) in2, 0);
    in3_d = __msa_copy_u_d((v2i64) in3, 0);
    in4_d = __msa_copy_u_d((v2i64) in4, 0);
    in5_d = __msa_copy_u_d((v2i64) in5, 0);
    in6_d = __msa_copy_u_d((v2i64) in6, 0);
    in7_d = __msa_copy_u_d((v2i64) in7, 0);
    SD4(in0_d, in1_d, in2_d, in3_d, pixels, stride);
    pixels += 4 * stride;
    SD4(in4_d, in5_d, in6_d, in7_d, pixels, stride);
}

static void add_pixels_clamped_msa(const int16_t *block, uint8_t *pixels,
                                   int32_t stride)
{
    uint64_t in0_d, in1_d, in2_d, in3_d, in4_d, in5_d, in6_d, in7_d;
    v8i16 in0, in1, in2, in3, in4, in5, in6, in7;
    v16u8 pix_in0, pix_in1, pix_in2, pix_in3;
    v16u8 pix_in4, pix_in5, pix_in6, pix_in7;
    v8u16 pix0, pix1, pix2, pix3, pix4, pix5, pix6, pix7;
    v8i16 zero = { 0 };

    LD_SH8(block, 8, in0, in1, in2, in3, in4, in5, in6, in7);
    LD_UB8(pixels, stride, pix_in0, pix_in1, pix_in2,
           pix_in3, pix_in4, pix_in5, pix_in6, pix_in7);

    ILVR_B4_UH(zero, pix_in0, zero, pix_in1, zero, pix_in2, zero, pix_in3,
               pix0, pix1, pix2, pix3);
    ILVR_B4_UH(zero, pix_in4, zero, pix_in5, zero, pix_in6, zero, pix_in7,
               pix4, pix5, pix6, pix7);

    in0 += (v8i16) pix0;
    in1 += (v8i16) pix1;
    in2 += (v8i16) pix2;
    in3 += (v8i16) pix3;
    in4 += (v8i16) pix4;
    in5 += (v8i16) pix5;
    in6 += (v8i16) pix6;
    in7 += (v8i16) pix7;

    CLIP_SH4_0_255(in0, in1, in2, in3);
    CLIP_SH4_0_255(in4, in5, in6, in7);
    PCKEV_B4_SH(in0, in0, in1, in1, in2, in2, in3, in3, in0, in1, in2, in3);
    PCKEV_B4_SH(in4, in4, in5, in5, in6, in6, in7, in7, in4, in5, in6, in7);

    in0_d = __msa_copy_u_d((v2i64) in0, 0);
    in1_d = __msa_copy_u_d((v2i64) in1, 0);
    in2_d = __msa_copy_u_d((v2i64) in2, 0);
    in3_d = __msa_copy_u_d((v2i64) in3, 0);
    in4_d = __msa_copy_u_d((v2i64) in4, 0);
    in5_d = __msa_copy_u_d((v2i64) in5, 0);
    in6_d = __msa_copy_u_d((v2i64) in6, 0);
    in7_d = __msa_copy_u_d((v2i64) in7, 0);
    SD4(in0_d, in1_d, in2_d, in3_d, pixels, stride);
    pixels += 4 * stride;
    SD4(in4_d, in5_d, in6_d, in7_d, pixels, stride);
}

void ff_put_pixels_clamped_msa(const int16_t *block,
                               uint8_t *av_restrict pixels,
                               ptrdiff_t line_size)
{
    put_pixels_clamped_msa(block, pixels, line_size);
}

void ff_put_signed_pixels_clamped_msa(const int16_t *block,
                                      uint8_t *av_restrict pixels,
                                      ptrdiff_t line_size)
{
    put_signed_pixels_clamped_msa(block, pixels, line_size);
}

void ff_add_pixels_clamped_msa(const int16_t *block,
                               uint8_t *av_restrict pixels,
                               ptrdiff_t line_size)
{
    add_pixels_clamped_msa(block, pixels, line_size);
}