libavfilter/x86/vf_limiter.asm

   1 ;*****************************************************************************
   2 ;* x86-optimized functions for limiter filter
   3 ;*
   4 ;* This file is part of FFmpeg.
   5 ;*
   6 ;* FFmpeg is free software; you can redistribute it and/or
   7 ;* modify it under the terms of the GNU Lesser General Public
   8 ;* License as published by the Free Software Foundation; either
   9 ;* version 2.1 of the License, or (at your option) any later version.
  10 ;*
  11 ;* FFmpeg is distributed in the hope that it will be useful,
  12 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14 ;* Lesser General Public License for more details.
  15 ;*
  16 ;* You should have received a copy of the GNU Lesser General Public
  17 ;* License along with FFmpeg; if not, write to the Free Software
  18 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  19 ;******************************************************************************
  20
  21 %include "libavutil/x86/x86util.asm"
  22
  23 SECTION .text
  24
  25 INIT_XMM sse2
  26
  27 cglobal limiter_8bit, 6, 7, 3, src, dst, slinesize, dlinesize, w, h, x
  28     movsxdifnidn wq, wd
  29     add        srcq, wq
  30     add        dstq, wq
  31     neg          wq
  32     movd         m1, r6m
  33     punpcklbw    m1, m1
  34     SPLATW       m1, m1
  35     movd         m2, r7m
  36     punpcklbw    m2, m2
  37     SPLATW       m2, m2
  38 .nextrow:
  39     mov          xq, wq
  40
  41     .loop:
  42         movu           m0, [srcq + xq]
  43         CLIPUB         m0, m1, m2
  44         movu    [dstq+xq], m0
  45         add            xq, mmsize
  46     jl .loop
  47
  48     add        srcq, slinesizeq
  49     add        dstq, dlinesizeq
  50     sub        hd, 1
  51     jg .nextrow
  52     RET
  53
  54 INIT_XMM sse4
  55
  56 cglobal limiter_16bit, 6, 7, 3, src, dst, slinesize, dlinesize, w, h, x
  57     shl          wd, 1
  58     add        srcq, wq
  59     add        dstq, wq
  60     neg          wq
  61     movd         m1, r6m
  62     SPLATW       m1, m1
  63     movd         m2, r7m
  64     SPLATW       m2, m2
  65 .nextrow:
  66     mov          xq, wq
  67
  68     .loop:
  69         movu           m0, [srcq + xq]
  70         pmaxuw         m0, m1
  71         pminuw         m0, m2
  72         movu    [dstq+xq], m0
  73         add            xq, mmsize
  74     jl .loop
  75
  76     add        srcq, slinesizeq
  77     add        dstq, dlinesizeq
  78     sub        hd, 1
  79     jg .nextrow
  80     RET