On an otherwise idle Linux system, I've been noticing that the
per-iteration speed has been varying during the course of a single
primality test.  Until Saturday afternoon I'd been getting a fairly
consistent 0.188/0.189s time when the system was idle.   It then increased
to around 0.206s.  It fell again last night to around 0.199s (see logs
below - percentages trimmed for 80-character neatness).

Any ideas?  It's a Duron 700 desktop system with 512MB PC133 RAM.  All I
can think of is that something is having a small but noticeable affect on
memory access speeds.  I can't think of anything I've changed over the past
few days on the system: kernel, libraries, etc are all the same.

Not a major problem, I'm just curious :-)

[Jan 12 02:52] Iteration: 4750000 / 13355561 Per iteration time: 0.190 sec.
[Jan 12 05:29] Iteration: 4800000 / 13355561 Per iteration time: 0.189 sec.
[Jan 12 08:07] Iteration: 4850000 / 13355561 Per iteration time: 0.189 sec.
[Jan 12 10:48] Iteration: 4900000 / 13355561 Per iteration time: 0.193 sec.
[Jan 12 13:34] Iteration: 4950000 / 13355561 Per iteration time: 0.199 sec.
[Jan 12 16:26] Iteration: 5000000 / 13355561 Per iteration time: 0.207 sec.
[Jan 12 19:20] Iteration: 5050000 / 13355561 Per iteration time: 0.208 sec.
[Jan 12 22:13] Iteration: 5100000 / 13355561 Per iteration time: 0.208 sec.
[Jan 13 01:07] Iteration: 5150000 / 13355561 Per iteration time: 0.208 sec.

[Jan 14 11:05] Iteration: 5750000 / 13355561 Per iteration time: 0.199 sec.
[Jan 14 13:51] Iteration: 5800000 / 13355561 Per iteration time: 0.199 sec.
[Jan 14 16:37] Iteration: 5850000 / 13355561 Per iteration time: 0.199 sec.
[Jan 14 19:24] Iteration: 5900000 / 13355561 Per iteration time: 0.200 sec.
[Jan 14 22:11] Iteration: 5950000 / 13355561 Per iteration time: 0.200 sec.
[Jan 15 00:53] Iteration: 6000000 / 13355561 Per iteration time: 0.194 sec.
[Jan 15 03:35] Iteration: 6050000 / 13355561 Per iteration time: 0.194 sec.
[Jan 15 06:16] Iteration: 6100000 / 13355561 Per iteration time: 0.194 sec.

-- 
--------------- Robin Stevens  <[EMAIL PROTECTED]> -----------------
Oxford University Computing Services ----------- Web: http://www.cynic.org.uk/
------- (+44)(0)1865: 273212 (work) 273275 (fax)  Mobile: 07776 235326 -------
_________________________________________________________________________
Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm
Mersenne Prime FAQ      -- http://www.tasam.com/~lrwiman/FAQ-mers

Reply via email to