moving another bit&1 out, this is as fast as with it in there, but it makes more sense with it outside of the loop


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6618 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6617 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

move the &1 out of the asm so gcc can optimize it away in inlined cases (yes this is slightly faster)


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6616 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

this is faster on P3, should be faster on AMD, and should be slower on P4
its disabled by default (benchmarks welcome so we know when to enable it)


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6615 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6614 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6613 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

reading 8bit mem into a 8bit register needs 2 uops on P4, 8bit->32bit with zero extension needs just 1


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6612 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6611 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6610 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6609 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

slightly faster on P3


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6608 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6607 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6606 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6605 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6604 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6603 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

first try of a handwritten get_cabac() for x86, this is 10-20% faster on P3 depening on if you try to subtract the START/STOP_TIMER overhead


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6602 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6601 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6600 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

remove bytestream_end checks, seems to work fine without them and the bitstream reader doesnt check for the end either


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6599 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

patch by Andrea Gianarro % giandrea AH gmail P com %
Original thread:
Date: Oct 9, 2006 11:55 AM
Subject: [Ffmpeg-devel] AC3 5:1 decoding as mono


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6598 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6597 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6596 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

rv10.c:494: warning: implicit declaration of function ‘ff_mpeg4_init_direct_mv’

Approved by Michael.



git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6595 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6594 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

opt.c:327: warning: no return statement in function returning non-void

opt_list return value is never checked.

Approved by Michael.



git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6593 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

parser.c:555: warning: implicit declaration of function ‘ff_cavs_find_frame_end’

Approved by Michael.



git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6592 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

mpegvideo.h:777: warning: ‘inline’ is not at beginning of declaration
motion_est_template.c:236: warning: ‘inline’ is not at beginning of declaration

Approved by Diego.


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6591 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6590 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

as a single long filename by the shell.
patch by Víctor Paesa, wzrlpy arsystel com


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6589 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6588 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

branchless renormalization (1% faster get_cabac) old branchless renormalization wasnt faster because gcc was scared of the shift variable (missusing bit variable now)


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6587 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6586 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6585 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6584 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6583 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

disable asm optims as the fastest depends on cpu type


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6582 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6581 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6580 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

Patch by yong ||| y0ngc |a| yahoo dot com |||



git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6579 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b