michael
|
5b46b234d2
|
HAVE_MMX1 -> HAVE_ONLY_MMX1 (makes more sense ...)
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@23396 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2007-05-27 21:45:33 +00:00 |
|
gpoirier
|
d853ecdc40
|
More gcc-4.0 fixes
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@15640 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2005-06-04 21:11:39 +00:00 |
|
gpoirier
|
ded52c0bc7
|
Make this file compile with gcc-4.0.0. The old code was invalid C.
(with the blessing of Rich)
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@14566 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2005-01-21 21:11:35 +00:00 |
|
aurel
|
798d2d1337
|
adapting existing mmx/mmx2/sse/3dnow optimizations so they work on x86_64
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@13721 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2004-10-21 11:55:20 +00:00 |
|
arpi
|
4f5e15a23a
|
removed nonsense 'inline'
patch by Joey Parrish <joey@yunamusic.com>
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@7073 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2002-08-22 23:28:33 +00:00 |
|
michael
|
65a12da973
|
prefer prefetchnta if its available
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@5663 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2002-04-17 19:11:52 +00:00 |
|
michael
|
09d06189af
|
pre mmx2/3dnow fix
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@5661 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2002-04-17 18:48:22 +00:00 |
|
michael
|
b89389845d
|
101
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@4685 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2002-02-13 00:17:16 +00:00 |
|
michael
|
7a4350e4c1
|
mem2agpcpy()
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@4682 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2002-02-12 23:17:14 +00:00 |
|
michael
|
1ec539d353
|
runtime cpu detection
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@3394 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2001-12-09 15:25:11 +00:00 |
|
michael
|
6c6cc954f5
|
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)
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@3078 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2001-11-22 19:40:38 +00:00 |
|
nickols_k
|
50f47cfd50
|
Issues about P3 performance and SSE2 support.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@1124 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2001-06-13 16:12:14 +00:00 |
|
nickols_k
|
ada40a6be6
|
Moving fast_memcpy to separate file (Size optimization)
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@699 b3059339-0415-0410-9bf9-f77b7e298cf2
|
2001-05-05 13:30:00 +00:00 |
|