Effect of Temperature on Power-Consumption with the i7-2600K

[blckgrffn]

Posts like this are what makes these forums special, IMHO.

Epic.

 

[pelov]

It only looks linear because I zoomed way-in on those couple of regions.

It is exponential with respect to temperature, but definitely you could form an easy rule of thumb to treat it as linear because the worse that will come of such an approximation is that you'd be off by a watt or two (no big deal).

Before I came to the realization that I needed to include the Poole-Frenkel effect I was treating the temperature effect as a linear one and it wasn't all that bad.

I was just kinda blown away, I was not expecting the magnitude of the effect, when I saw the data.

Take for example the 2GHz chip at 1.290V and a cool 47°C, it consumes 68W. But let those temps rise from 47°C to 96°C and the power-consumption rises from 68W to 91W.

Consider that this 23W represents a 33% increase in power-consumption D: I just had no appreciation for how deleterious higher operating temps were for the power-consumption of the CPU.

That's absolutely staggering. Awesome info, IDC. Thanks a ton 🙂 adding to favorites

Quick question: are issues like this a reason for the rise of dark silicon in chip manufacturing now? an offset of heat and consequently power consumption intertwined by allowing for larger die sizes and gaps? X part of chip does Y while the remainder is dark.

http://mirror.unila.ac.id/ITBCermin/167.205.30.228/computer.org/micro-2011-issue-4/05967003.pdf

Though the article is written with respect to servers and core counts + CMP scaling, I'd imagine the same principle applies.

 

[BoFox]

Just came across this thread thanks to Ryan Smith linking to it in his recent R9 290X review!

That was impressive, IDC! A few years ago, I saw how much temp-related leakage there was with my i7 920's @ 45nm (about 40W for every 20C when oc'ed to 4GHz), and was curious about whether 32nm processors improved on that or not.

Anybody know anything about leakage on 22nm? Intel said that they were working hard on mitigating it past 45nm - but as IDC showed, it is still a problem on 32nm (much more considerably at 3GHz rather than 2GHz).

 

[Idontcare]

Just came across this thread thanks to Ryan Smith linking to it in his recent R9 290X review!

That was impressive, IDC! A few years ago, I saw how much temp-related leakage there was with my i7 920's @ 45nm (about 40W for every 20C when oc'ed to 4GHz), and was curious about whether 32nm processors improved on that or not.

Anybody know anything about leakage on 22nm? Intel said that they were working hard on mitigating it past 45nm - but as IDC showed, it is still a problem on 32nm (much more considerably at 3GHz rather than 2GHz).

I am completely humbled and awestruck that Ryan linked my thread and credited my graph in his 290X review :$:$:$:$

And thank you for your kind words :$:$:$:$

For 22nm versus 32nm comparisons (as apples to apples as I could make them anyways), see this thread: i7-3770K vs. i7-2600K: Temperature, Voltage, GHz and Power-Consumption Analysis

 

[NTMBK]

I am completely humbled and awestruck that Ryan linked my thread and credited my graph in his 290X review :$:$:$:$

I'm certainly not surprised he did, this thread is a bona-fide classic. You should seriously start writing full articles for AT!

 

[BoFox]

Yeah! He's hardcore with these insane graphs! LOL..

I am completely humbled and awestruck that Ryan linked my thread and credited my graph in his 290X review :$:$:$:$

And thank you for your kind words :$:$:$:$

For 22nm versus 32nm comparisons (as apples to apples as I could make them anyways), see this thread: i7-3770K vs. i7-2600K: Temperature, Voltage, GHz and Power-Consumption Analysis

Thanks man! That's even better!