log libvo/aclib.c @ 27111:4899f42d1c94

age author description
2007-06-10 lu_zero avoid utter breakage on non-x86, patch from Chris Roccati <roccati@at@pobox.dot.com>
2007-01-23 reimar Include string.h to make sure memcpy is not used without prototype
2006-11-01 reimar ARCH_X86 simplifications
2004-10-28 diego Handle "xxx.h" vs "../xxx.h" include paths in a consistent way.
2004-10-21 aurel adapting existing mmx/mmx2/sse/3dnow optimizations so they work on x86_64
2004-06-25 diego Unify the config.h #include, use "config.h" instead of "../config.h"
2004-05-20 reimar fix crash due to fast_memcpy calling itself instead of libc memcpy
2002-11-07 jkeil On non-x86 platforms, memcpy was re-implemented in mplayer and was called
2002-11-06 arpi *HUGE* set of compiler warning fixes, unused variables removal
2002-08-22 arpi removed nonsense 'inline'
2002-04-10 michael memcpy must return destination ptr patch by Adam <adam@cfar.umd.edu>
2002-03-19 michael fixing runtime cpudetect with pre SSE cpus
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)