| Fri, 23 Nov 2001 18:25:09 +0000 |
alex |
detecting nanosleep
|
| Fri, 23 Nov 2001 17:16:43 +0000 |
alex |
changed to use cpudetect.c (to use change te #if 1 -> #if 0 :)
|
| Fri, 23 Nov 2001 16:35:51 +0000 |
alex |
compiling under qnx, hope it works on all qnx release :)
|
| Fri, 23 Nov 2001 16:34:04 +0000 |
alex |
sys/soundcard.h isn't needed for ALSA
|
| Fri, 23 Nov 2001 16:09:05 +0000 |
alex |
added MSGT_OSDEP
|
| Fri, 23 Nov 2001 16:08:44 +0000 |
alex |
converted to mp_msg and fixed my previous HAVE_SHM bug
|
| Fri, 23 Nov 2001 15:34:03 +0000 |
pl |
typo (1st found by Andr Dahlqvist <andre.dahlqvist@telia.com>)
|
| Fri, 23 Nov 2001 12:12:25 +0000 |
michael |
bugfix
|
| Fri, 23 Nov 2001 12:00:40 +0000 |
michael |
missaligned arrays, as nick requested
|
| Fri, 23 Nov 2001 01:41:45 +0000 |
pontscho |
bug fixs
|
| Fri, 23 Nov 2001 00:21:51 +0000 |
pl |
(on atmos's suggestions I found good :)
|
| Thu, 22 Nov 2001 21:53:25 +0000 |
pl |
--help did not show what was really autodetected
|
| Thu, 22 Nov 2001 19:40:38 +0000 |
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)
|
| Thu, 22 Nov 2001 19:22:49 +0000 |
michael |
newly allocated memory seems to point to only 1 zero filled 4k page or something so there is a near 100% cache hit rate ... not very realistic, writeing something in the source array fixes that so the benchmark scores are meaningfull now
|
| Thu, 22 Nov 2001 18:52:25 +0000 |
pontscho |
bocs, elfelejtettem feltenni :)
|
