Replies to post #33463 on Advanced Micro Devices Inc (AMD)

[chipguy]

Active power= constant * frequency * voltage^2. Active power goes down as a fairly strong function of temperature.


Sorry but I have to disagree here. What physical parameter
do you think falls with temperature? Capacitance, voltage,
or frequency (not including clock throttling)?

[mas]

"The leakage power is pretty much a constant, but does go up as a function of temperature."

Most formulae I have seen also make it proportional to V.

[sgolds]

alan81, just one thing -

To enter the "Avalanche" processes that Pravin was talking about would require the silicon to be at or above 150C or so, which is very unlikely. Of course a P4 is going to throttle well before it gets anywhere near that temperature. I think throttling starts at 70 or 80C.. as such we don't really need to worry about those mechanisms we were discussing.

Throttling makes sense as a guard against a failed fan, but not really as a speed governor - kind of works against producing faster grades. For instance, if some chips start hitting runaway temperatures under load at 3.4GHz and throttling is 100% guaranteed when the processor is loaded then tell us again why we paid a premium for such a fast chip?

(Then there is the peculiar load called benchmarks...)

Thus I'd expect Intel to keep their release speeds under the point where excessive throttling would be needed under load.