ffmpeg/libavcodec/x86/v210.asm

   1 ;******************************************************************************
   2 ;* V210 SIMD unpack
   3 ;* Copyright (c) 2011 Loren Merritt <lorenm@u.washington.edu>
   4 ;* Copyright (c) 2011 Kieran Kunhya <kieran@kunhya.com>
   5 ;*
   6 ;* This file is part of FFmpeg.
   7 ;*
   8 ;* FFmpeg is free software; you can redistribute it and/or
   9 ;* modify it under the terms of the GNU Lesser General Public
  10 ;* License as published by the Free Software Foundation; either
  11 ;* version 2.1 of the License, or (at your option) any later version.
  12 ;*
  13 ;* FFmpeg is distributed in the hope that it will be useful,
  14 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 ;* Lesser General Public License for more details.
  17 ;*
  18 ;* You should have received a copy of the GNU Lesser General Public
  19 ;* License along with FFmpeg; if not, write to the Free Software
  20 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  21 ;******************************************************************************
  22
  23 %include "libavutil/x86/x86util.asm"
  24
  25 SECTION_RODATA
  26
  27 v210_mask: times 4 dd 0x3ff
  28 v210_mult: dw 64,4,64,4,64,4,64,4
  29 v210_luma_shuf: db 8,9,0,1,2,3,12,13,4,5,6,7,-1,-1,-1,-1
  30 v210_chroma_shuf: db 0,1,8,9,6,7,-1,-1,2,3,4,5,12,13,-1,-1
  31
  32 SECTION .text
  33
  34 %macro v210_planar_unpack 1
  35
  36 ; v210_planar_unpack(const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width)
  37 cglobal v210_planar_unpack_%1, 5, 5, 7
  38     movsxdifnidn r4, r4d
  39     lea    r1, [r1+2*r4]
  40     add    r2, r4
  41     add    r3, r4
  42     neg    r4
  43
  44     mova   m3, [v210_mult]
  45     mova   m4, [v210_mask]
  46     mova   m5, [v210_luma_shuf]
  47     mova   m6, [v210_chroma_shuf]
  48 .loop
  49 %ifidn %1, unaligned
  50     movu   m0, [r0]
  51 %else
  52     mova   m0, [r0]
  53 %endif
  54
  55     pmullw m1, m0, m3
  56     psrld  m0, 10
  57     psrlw  m1, 6  ; u0 v0 y1 y2 v1 u2 y4 y5
  58     pand   m0, m4 ; y0 __ u1 __ y3 __ v2 __
  59
  60     shufps m2, m1, m0, 0x8d ; y1 y2 y4 y5 y0 __ y3 __
  61     pshufb m2, m5 ; y0 y1 y2 y3 y4 y5 __ __
  62     movu   [r1+2*r4], m2
  63
  64     shufps m1, m0, 0xd8 ; u0 v0 v1 u2 u1 __ v2 __
  65     pshufb m1, m6 ; u0 u1 u2 __ v0 v1 v2 __
  66     movq   [r2+r4], m1
  67     movhps [r3+r4], m1
  68
  69     add r0, mmsize
  70     add r4, 6
  71     jl  .loop
  72
  73     REP_RET
  74 %endmacro
  75
  76 INIT_XMM ssse3
  77 v210_planar_unpack unaligned
  78
  79 %if HAVE_AVX_EXTERNAL
  80 INIT_XMM avx
  81 v210_planar_unpack unaligned
  82 %endif
  83
  84 INIT_XMM ssse3
  85 v210_planar_unpack aligned
  86
  87 %if HAVE_AVX_EXTERNAL
  88 INIT_XMM avx
  89 v210_planar_unpack aligned
  90 %endif