Overclocking a mobile Barton 2400+ to 2.6/2.7+ GHz on air
Picked up a mobile barton 2400+ ($77) from newegg, AQYFA 0343 WPFW, kind of an unknown stepping, not the best known stepping such as IQYFA 0343 MPMW.
Managed to run it at high voltage of 2.22 V to get to 2.79 GHz.
SLK-947U and 80mm Tornado (w/ fan speed control).
MB is NF7-S rev 2.0.
512 MB x 2 PC 3500.
Prime stable at 2.65 GHz, 2.15V, 48/18 C.
I think that is about it for this particular chip and stepping.
Will eventually run it 24/7 at 2.6+ GHz, 220+ FSB, with SLK-947U and 80mm Tornado w/ fan speed control.
From the Sisoft Dhyrstone Integer and Whetstone Floating Point benchmark,
it scores 7%+ higher than a P4C 3.2 GHz w/ 2 SMT, for both integer and floating point (w/o SSE2).
Since the Dhrystone IPC ratio for XP to P4C (w/ 2 SMT) is about 1.22:1,
so a 2.79 GHz Barton would perform about the same as a 3.4 GHz P4 in integer arithmetic.
At 2.71 GHz, 2.15 V, the temperature at light to medium high load is 33 - 45 C,
with winter CPU ambient temperature around 15 - 18 C,
80 mm Tornado between 3000-4000 rpm.
During full Prime95, load temperature would go up as high as 48 C with system ambient around 18 C (also winter room temperature), with the 80 mm Tornado at full rpm.
The 30 C temperature difference would translate into about 130 W power dissipation with a SLK-947 type of HS.
To get it stable under Prime95, preferred temperature is under 45 C, with 15 C ambient temp (winter).
At around 48 C, the heat related instability perturbation would limit further higher overclocking beyond 2.7 GHz at full load,
unless better cooling is incorporated.
stable_frequency = max_frequency - temp_sensitive_frequency_margin
Max_frequency is determined by Vcore, ....
If one could reduce the temperature related frequency margin by super cooling, then one could have the stable frequency approaching the max ideal frequency of the CPU at a given Vcore and temperature.