log libvo/aclib_template.c @ 33545:38aee97cc4fc

age author description
2010-02-20 diego cosmetics: Remove pointless empty lines at EOF.
2010-01-03 reimar Do not assume that "long" is the size of a register.
2009-09-17 reimar Use ecx instead of ebx to avoid unnecessary issues with PIC.
2009-02-08 diego Add standard license headers, unify header formatting.
2009-01-26 diego HAVE_3DNOW --> HAVE_AMD3DNOW
2009-01-16 reimar Lots and lots of #ifdef ARCH_... -> #if ARCH_...
2008-10-16 diego Replace all occurrences of '__volatile__' and '__volatile' by plain 'volatile'.
2008-10-16 diego Change all occurrences of asm and __asm to __asm__, same as was done for FFmpeg.
2008-02-15 uau libvo: change asm syntax to use ASMALIGN and " # nop"
2007-05-27 michael HAVE_MMX1 -> HAVE_ONLY_MMX1 (makes more sense ...)
2005-06-04 gpoirier More gcc-4.0 fixes
2005-01-21 gpoirier Make this file compile with gcc-4.0.0. The old code was invalid C.
2004-10-21 aurel adapting existing mmx/mmx2/sse/3dnow optimizations so they work on x86_64
2002-08-22 arpi removed nonsense 'inline'
2002-04-17 michael prefer prefetchnta if its available
2002-04-17 michael pre mmx2/3dnow fix
2002-02-13 michael 101
2002-02-12 michael mem2agpcpy()
2001-12-09 michael runtime cpu detection
2001-11-22 michael 10-20% faster fastmemcpy :) on my p3 at least but the algo is mostly from "amd athlon processor x86 code optimization guide" so it should be faster for amd chips too, but i fear it might be slower for mem->vram copies (someone should check that, i cant) ... there are 2 #defines to finetune it (BLOCK_SIZE & CONFUSION_FACTOR)
2001-06-13 nickols_k Issues about P3 performance and SSE2 support.
2001-05-05 nickols_k Moving fast_memcpy to separate file (Size optimization)