Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from

h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now
coded in asm instead of C, this is (depending on the function) up to 50%
faster for cases where gcc didn't do a great job at looping.

Since h264_idct_add8() is now faster than the manual loop setup in h264.c,
in-asm idct calling can now be enabled for chroma as well (see r16207). For
MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does
the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.

Originally committed as revision 25119 to svn://svn.ffmpeg.org/ffmpeg/trunk

libavcodec/h264.c

@@ -1318,14 +1318,9 @@ static av_always_inline void hl_decode_mb_internal(H264Context *h, int simple){
                 chroma_dc_dequant_idct_c(h->mb + 16*16, h->chroma_qp[0], h->dequant4_coeff[IS_INTRA(mb_type) ? 1:4][h->chroma_qp[0]][0]);
                 chroma_dc_dequant_idct_c(h->mb + 16*16+4*16, h->chroma_qp[1], h->dequant4_coeff[IS_INTRA(mb_type) ? 2:5][h->chroma_qp[1]][0]);
                 if(is_h264){
-                    idct_add = h->h264dsp.h264_idct_add;
-                    idct_dc_add = h->h264dsp.h264_idct_dc_add;
-                    for(i=16; i<16+8; i++){
-                        if(h->non_zero_count_cache[ scan8[i] ])
-                            idct_add   (dest[(i&4)>>2] + block_offset[i], h->mb + i*16, uvlinesize);
-                        else if(h->mb[i*16])
-                            idct_dc_add(dest[(i&4)>>2] + block_offset[i], h->mb + i*16, uvlinesize);
-                    }
+                    h->h264dsp.h264_idct_add8(dest, block_offset,
+                                              h->mb, uvlinesize,
+                                              h->non_zero_count_cache);
                 }else{
                     for(i=16; i<16+8; i++){
                         if(h->non_zero_count_cache[ scan8[i] ] || h->mb[i*16]){

libavcodec/x86/Makefile

@@ -10,7 +10,7 @@ YASM-OBJS-$(CONFIG_FFT)                += x86/fft_mmx.o                 \
 MMX-OBJS-$(CONFIG_H264DSP)             += x86/h264dsp_mmx.o
 YASM-OBJS-$(CONFIG_H264DSP)            += x86/h264_deblock.o            \
                                           x86/h264_weight.o             \
-                                          x86/h264_idct_sse2.o          \
+                                          x86/h264_idct.o               \
 
 YASM-OBJS-$(CONFIG_H264PRED)           += x86/h264_intrapred.o
 MMX-OBJS-$(CONFIG_H264PRED)            += x86/h264_intrapred_init.o

libavcodec/x86/h264_idct_sse2.asm

-;*****************************************************************************
-;* SSE2-optimized H.264 iDCT
-;*****************************************************************************
-;* Copyright (C) 2003-2008 x264 project
-;*
-;* Authors: Laurent Aimar <fenrir@via.ecp.fr>
-;*          Loren Merritt <lorenm@u.washington.edu>
-;*          Holger Lubitz <hal@duncan.ol.sub.de>
-;*          Min Chen <chenm001.163.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
-;* 51, Inc., Foundation Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
-;*****************************************************************************
-
-%include "x86inc.asm"
-%include "x86util.asm"
-
-SECTION_RODATA
-pw_32: times 8 dw 32
-
-SECTION .text
-
-INIT_XMM
-cglobal x264_add8x4_idct_sse2, 3,3,8
-    movq   m0, [r1+ 0]
-    movq   m1, [r1+ 8]
-    movq   m2, [r1+16]
-    movq   m3, [r1+24]
-    movhps m0, [r1+32]
-    movhps m1, [r1+40]
-    movhps m2, [r1+48]
-    movhps m3, [r1+56]
-    IDCT4_1D 0,1,2,3,4,5
-    TRANSPOSE2x4x4W 0,1,2,3,4
-    paddw m0, [pw_32]
-    IDCT4_1D 0,1,2,3,4,5
-    pxor  m7, m7
-    STORE_DIFF  m0, m4, m7, [r0]
-    STORE_DIFF  m1, m4, m7, [r0+r2]
-    lea   r0, [r0+r2*2]
-    STORE_DIFF  m2, m4, m7, [r0]
-    STORE_DIFF  m3, m4, m7, [r0+r2]
-    RET