Almost all CPU targets use -mcpu=xx to set architecture type,
register usage, choice of mnemonics, and instruction
scheduling parameters, except x86, MIPS, HPPA which uses -march=xx

Originally committed as revision 6736 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6735 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 variable less in decode_cabac_residual() no speed change (but less vars means less things gcc can load and store redundantly)

Originally committed as revision 6734 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6733 to svn://svn.ffmpeg.org/ffmpeg/trunk

x86 is 4% faster on P3
C sign stuff + x86 code for everything else is also faster then before (sorry forgot to test pure C)
... and if i replace the second occurance of the sign decoding in decode_residual by the asm too then everything gets slower iam starting to think that it might be best to write the whole function in asm, playing this avoid random deoptimizations game with gcc is not fun at all

Originally committed as revision 6732 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6731 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6730 to svn://svn.ffmpeg.org/ffmpeg/trunk

Note that previous implementation (--tune) wasn't consistent with regards to setting -march/-mcpu/-mtune whereas current --cpu now is
Original thread:
Date: Oct 17, 2006 3:20 PM (patch) || Date: Oct 13, 2006 12:03 PM (suggestion of configure clean-up)
Subject: Re: [Ffmpeg-devel] [PATH] test if cpu supports CMOV

Originally committed as revision 6729 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6728 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6727 to svn://svn.ffmpeg.org/ffmpeg/trunk

Patch by Jindrich Makovicka makovick A gmail P com
Original thread:
Date: 08:21 AM
Subject Re: [Ffmpeg-devel] Weird line in cabac.h

Originally committed as revision 6726 to svn://svn.ffmpeg.org/ffmpeg/trunk

copy cabac context onto the stack for the c code in decode_cabac_residual() (15% faster on P3 but still slower then the current asm)

Originally committed as revision 6725 to svn://svn.ffmpeg.org/ffmpeg/trunk

x86 asm version of the decode significance loop (not 8x8) of decode_residual() 5% faster decode_residual() on P3

Originally committed as revision 6724 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6723 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6722 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6721 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6720 to svn://svn.ffmpeg.org/ffmpeg/trunk

allowed to select an architecture, not a specific cpu

Originally committed as revision 6719 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6718 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6717 to svn://svn.ffmpeg.org/ffmpeg/trunk

   * Fixing a bug in how SPEED was encoded for AAUX ASC

Originally committed as revision 6716 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6715 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6714 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6713 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6712 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6711 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6710 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6709 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6708 to svn://svn.ffmpeg.org/ffmpeg/trunk

fix !CMOV_IS_FAST case (iam not really happy with the fix but i didnt come up with a better one quickly)

Originally committed as revision 6707 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6706 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6705 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6704 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6703 to svn://svn.ffmpeg.org/ffmpeg/trunk

shift CABACContext.range right, this reduces the number of shifts needed in get_cabac() and is slightly faster on P3 (and should be much faster on P4 as the P4 except the more recent variants lacks an integer shifter and so  shifts have ~10 times longer latency then simple operations like adds)

Originally committed as revision 6702 to svn://svn.ffmpeg.org/ffmpeg/trunk

Patch by Ramiro Polla angustia A arrozcru P no-ip P org
Original thread:
Date: 14.10.2006 05:44
Subject: [Ffmpeg-devel] xvid ignores -vtag

Originally committed as revision 6701 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6700 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6699 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6698 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 6697 to svn://svn.ffmpeg.org/ffmpeg/trunk