Mail Archives: djgpp/2001/04/01/19:33:56
Thanks Tom !
>> So i think that the CPU clock may vary, but i don't know how much.
>
>Typically it's about 10%. My athlon 1200mhz runs at "supposedly" 1211mhz
>according to various programs.
You're right, I have a PIII 733 and an Athlon 800 with the same behaviour.
Their clocks is almost the nominal clock (PIII reports 737 Mhz and Athlon
806
Mhz).
What i'm asking is about the fluctuation of the clock along the time. I
think
that the PC clock generator don't have any stabilization method to
compensate
fluctuations on the crystal voltage/temperature that would change the
computer
clock rate.
In this way, the computer sometimes runs at 800 Mhz... its clock will vary
from, say, 799.3 Mhz to 810.5 Mhz... This kind of oscilation may create bad
effects on my simulation...
>Using RDTSC to sync programs is a bad idea since RDTSC may take a variable
>amount of cycles to complete.
On my tests i discovered that the RDTSC instruction takes from 12 to 20
clocks
to complete. On an Athlon 800 Mhz this delay is a few nanoseconds... which i
may forgive in my application...
Thank you for all.
Eduardo TUDA DocHell Lorenzetti Pellin
PEA - Electrical Energy and Automation Department
USP - Politechnical School of Sao Paulo University - BRAZIL
http://www.pea.usp.br/~epellini
---------------------------------
And if you have a time to loose,
an open mind, and right to choose,
would you care to take a look,
or can you read me like a book...
time's is allways on my side...
--------------------------------- (Up the Irons !!!)
- Raw text -