libavresample/x86/audio_convert.asm

   1 ;******************************************************************************
   2 ;* x86 optimized Format Conversion Utils
   3 ;* Copyright (c) 2008 Loren Merritt
   4 ;*
   5 ;* This file is part of Libav.
   6 ;*
   7 ;* Libav is free software; you can redistribute it and/or
   8 ;* modify it under the terms of the GNU Lesser General Public
   9 ;* License as published by the Free Software Foundation; either
  10 ;* version 2.1 of the License, or (at your option) any later version.
  11 ;*
  12 ;* Libav is distributed in the hope that it will be useful,
  13 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15 ;* Lesser General Public License for more details.
  16 ;*
  17 ;* You should have received a copy of the GNU Lesser General Public
  18 ;* License along with Libav; if not, write to the Free Software
  19 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  20 ;******************************************************************************
  21
  22 %include "x86inc.asm"
  23 %include "x86util.asm"
  24
  25 SECTION_TEXT
  26
  27 ;-----------------------------------------------------------------------------
  28 ; void ff_conv_fltp_to_flt_6ch(float *dst, float *const *src, int len,
  29 ;                              int channels);
  30 ;-----------------------------------------------------------------------------
  31
  32 %macro CONV_FLTP_TO_FLT_6CH 0
  33 cglobal conv_fltp_to_flt_6ch, 2,8,7, dst, src, src1, src2, src3, src4, src5, len
  34 %if ARCH_X86_64
  35     mov     lend, r2d
  36 %else
  37     %define lend dword r2m
  38 %endif
  39     mov    src1q, [srcq+1*gprsize]
  40     mov    src2q, [srcq+2*gprsize]
  41     mov    src3q, [srcq+3*gprsize]
  42     mov    src4q, [srcq+4*gprsize]
  43     mov    src5q, [srcq+5*gprsize]
  44     mov     srcq, [srcq]
  45     sub    src1q, srcq
  46     sub    src2q, srcq
  47     sub    src3q, srcq
  48     sub    src4q, srcq
  49     sub    src5q, srcq
  50 .loop:
  51     mova      m0, [srcq      ]
  52     mova      m1, [srcq+src1q]
  53     mova      m2, [srcq+src2q]
  54     mova      m3, [srcq+src3q]
  55     mova      m4, [srcq+src4q]
  56     mova      m5, [srcq+src5q]
  57 %if cpuflag(sse)
  58     SBUTTERFLYPS 0, 1, 6
  59     SBUTTERFLYPS 2, 3, 6
  60     SBUTTERFLYPS 4, 5, 6
  61
  62     movaps    m6, m4
  63     shufps    m4, m0, q3210
  64     movlhps   m0, m2
  65     movhlps   m6, m2
  66     movaps [dstq   ], m0
  67     movaps [dstq+16], m4
  68     movaps [dstq+32], m6
  69
  70     movaps    m6, m5
  71     shufps    m5, m1, q3210
  72     movlhps   m1, m3
  73     movhlps   m6, m3
  74     movaps [dstq+48], m1
  75     movaps [dstq+64], m5
  76     movaps [dstq+80], m6
  77 %else ; mmx
  78     SBUTTERFLY dq, 0, 1, 6
  79     SBUTTERFLY dq, 2, 3, 6
  80     SBUTTERFLY dq, 4, 5, 6
  81
  82     movq   [dstq   ], m0
  83     movq   [dstq+ 8], m2
  84     movq   [dstq+16], m4
  85     movq   [dstq+24], m1
  86     movq   [dstq+32], m3
  87     movq   [dstq+40], m5
  88 %endif
  89     add      srcq, mmsize
  90     add      dstq, mmsize*6
  91     sub      lend, mmsize/4
  92     jg .loop
  93 %if mmsize == 8
  94     emms
  95     RET
  96 %else
  97     REP_RET
  98 %endif
  99 %endmacro
 100
 101 INIT_MMX mmx
 102 CONV_FLTP_TO_FLT_6CH
 103 INIT_XMM sse
 104 CONV_FLTP_TO_FLT_6CH