libavcodec/x86/rv40dsp_mmx.c

   1 /*
   2  * Copyright (c) 2008 Konstantin Shishkov, Mathieu Velten
   3  *
   4  * MMX-optimized DSP functions for RV40, based on H.264 optimizations by
   5  * Michael Niedermayer and Loren Merritt
   6  *
   7  * This file is part of FFmpeg.
   8  *
   9  * FFmpeg is free software; you can redistribute it and/or
  10  * modify it under the terms of the GNU Lesser General Public
  11  * License as published by the Free Software Foundation; either
  12  * version 2.1 of the License, or (at your option) any later version.
  13  *
  14  * FFmpeg is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17  * Lesser General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU Lesser General Public
  20  * License along with FFmpeg; if not, write to the Free Software
  21  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  22  */
  23
  24 #include "dsputil_mmx.h"
  25
  26 /* bias interleaved with bias div 8, use p+1 to access bias div 8 */
  27 DECLARE_ALIGNED_8(static const uint64_t, rv40_bias_reg[4][8]) = {
  28     { 0x0000000000000000ULL, 0x0000000000000000ULL, 0x0010001000100010ULL, 0x0002000200020002ULL,
  29       0x0020002000200020ULL, 0x0004000400040004ULL, 0x0010001000100010ULL, 0x0002000200020002ULL },
  30     { 0x0020002000200020ULL, 0x0004000400040004ULL, 0x001C001C001C001CULL, 0x0003000300030003ULL,
  31       0x0020002000200020ULL, 0x0004000400040004ULL, 0x001C001C001C001CULL, 0x0003000300030003ULL },
  32     { 0x0000000000000000ULL, 0x0000000000000000ULL, 0x0020002000200020ULL, 0x0004000400040004ULL,
  33       0x0010001000100010ULL, 0x0002000200020002ULL, 0x0020002000200020ULL, 0x0004000400040004ULL },
  34     { 0x0020002000200020ULL, 0x0004000400040004ULL, 0x001C001C001C001CULL, 0x0003000300030003ULL,
  35       0x0020002000200020ULL, 0x0004000400040004ULL, 0x001C001C001C001CULL, 0x0003000300030003ULL }
  36 };
  37
  38 static void put_rv40_chroma_mc8_mmx(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  39 {
  40     put_h264_chroma_generic_mc8_mmx(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  41 }
  42 static void put_rv40_chroma_mc4_mmx(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  43 {
  44     put_h264_chroma_generic_mc4_mmx(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  45 }
  46 static void avg_rv40_chroma_mc8_mmx2(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  47 {
  48     avg_h264_chroma_generic_mc8_mmx2(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  49 }
  50 static void avg_rv40_chroma_mc4_mmx2(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  51 {
  52     avg_h264_chroma_generic_mc4_mmx2(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  53 }
  54 static void avg_rv40_chroma_mc8_3dnow(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  55 {
  56     avg_h264_chroma_generic_mc8_3dnow(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  57 }
  58 static void avg_rv40_chroma_mc4_3dnow(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
  59 {
  60     avg_h264_chroma_generic_mc4_3dnow(dst, src, stride, h, x, y, &rv40_bias_reg[y>>1][x&(~1)]);
  61 }