[ntp:questions] questions Digest, Vol 114, Issue 25
martin.burnicki at meinberg.de
Wed Apr 16 13:03:19 UTC 2014
Terje Mathisen schrieb:
> James Gibb wrote:
>> Is there still a need to tie the timing threads in Windows 7/8 to a
>> single processor? The MSDN makes it sound as though the TSC should be
>> identical across multiple processors.
> On modern cpus there is a second TSC which is independent of sleep
> states and temporary turbo mode cpu overclocking, as well as some hw
> support to allow the counters to be synchronized (within the read
> overhead time) between cpus. At that point there is no need to go
> offchip to get a stable interval count.
>> It also says the QPC frequency is unaffected by power saving CPU clock
>> mode changes so it would seem there's no need to have the direct _rdtsc
>> option instead of just relying on QPC these days.
> See above, QPC have always been intended to be stable, so on many Win*
> machines it has used some kind of low-frequency bus clock, running at
> 1-3 MHz, but we are obviously moving in the direction of
> high-resolution/low-overhead clock sources.
Hm, some time ago it was mentioned here that the TSC clock on modern
CPUs is derived from the front side bus clock instead of the CPU clock,
and thus it isn't sensitive to CPU clock changes anymore.
However, AFAIK the front side bus clock can also be changed, in which
case the TSC clock would also change, and we had the same problems with
varying TSC clock frequencies back if "someone" did this.
From what I've read in some forums it looks like some overclockers
twiddled with those settings and then wondered why their
timings/benchmarks were messed up. ;-)
More information about the questions