Mercurial > mplayer.hg
annotate mp3lib/d_cpu.h @ 3077:99f6db3255aa
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)
author | michael |
---|---|
date | Thu, 22 Nov 2001 19:40:38 +0000 |
parents | 03b7e2955a20 |
children |
rev | line source |
---|---|
1 | 1 |
2 // -------------------------------------------------------------------------- | |
3 // Cpu function detect by Pontscho/fresh!mindworkz | |
4 // -------------------------------------------------------------------------- | |
5 | |
6 #ifndef __MY_CPUIDENT | |
7 #define __MY_CPUIDENT | |
8 | |
9 unsigned int _CpuID; | |
10 unsigned int _i586; | |
11 unsigned int _3dnow; | |
1245
03b7e2955a20
Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu.
nick
parents:
302
diff
changeset
|
12 unsigned int _isse; |
03b7e2955a20
Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu.
nick
parents:
302
diff
changeset
|
13 unsigned int _has_mmx; |
1 | 14 |
15 extern unsigned long CpuDetect( void ); | |
16 extern unsigned long ipentium( void ); | |
1245
03b7e2955a20
Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu.
nick
parents:
302
diff
changeset
|
17 extern unsigned long isse( void ); |
1 | 18 extern unsigned long a3dnow( void ); |
19 | |
302 | 20 #endif |
21 |