|
From: Maritimus <rea...@ih...> - 2004-10-29 05:53:06
|
Jake Hamby wrote: > I am busy preparing my next "mega-patch" for the kernel which will: > be great > I'm also halfway done with integrating the latest TSC timer code from > Linux which uses the Pentium internal clock to give sub-microsecond > precision to the udelay() and get_system_time() calls. It's necessary > to have the best possible accuracy for gettimeofday() in order for > LMbench to give accurate results in a short benchmarking run. Right > now, LMbench says it is only accurate to 1000000us, compared to 5000us > precision under Linux, which is the best possible result (1000000us is > the worst possible result). Ok I don't really know this stuff, but will this have a fallback if i586 time stamp code doesn't work with a particular x86 CPU? This looked interesting: http://www.cs.helsinki.fi/linux/linux-kernel/2001-31/0542.html |