On 01/16/07 10:06, Frank Hofmann wrote:
With your original "ftime" code, the clock resolution could falsify your
results. With "gethrtime", zero time taken means a bug on the OS where
that is reported. Two consecutive gethrtime() calls, even with nothing
in-between, may not report the same values.
That is not true - gethrtime is monotonic not strictly monotonic.
From the Solaris manpage:
NOTES
Although the units of hi-res time are always the same
(nanoseconds), the actual resolution is hardware dependent.
Hi-res time is guaranteed to be monotonic (it won't go back-
ward, it won't periodically wrap) and linear (it won't occa-
sionally speed up or slow down for adjustment, like the time
of day can), but not necessarily unique: two sufficiently
proximate calls may return the same value.
On sparc systems with a 12.5MHz STICK clock it is quite feasible
to obtain two identical STICK values (and hence gethrtime values)
with much higher cpu clock frequencies.
Gavin
_______________________________________________
opensolaris-code mailing list
opensolaris-code@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/opensolaris-code
