[clug] Effect of operating temps on life of integrated circuits

Ben Nizette bn at niasdigital.com
Sat Jan 23 01:43:21 MST 2010

On 23/01/2010, at 6:32 PM, steve jenkin wrote:

> I've been trying to track down any estimates/rules-of-thumb about the
> effect of increased junction temperature on expected lifetime of IC's
> like CPU's and RAM - and was hoping the Collective Wisdom of CLUG (and
> some better Google-Fu than mine) could come up with quotable figures.

I'd love to see "quotable figures" but I'd be a little surprised if you can actually find them.  In terms of thermal causes for semiconductor failure, absolute but within-maximum temperates are going to be a small factor.  Much greater than this is thermal cycle frequency and magnitude as this generates mechanical stress which fractures bondings, wires, packages etc.  Of course going over absolute max temperature also causes big issues.

I don't know about other CLUGgers but every single time I've had IC failure it's been after a long period of activity followed by down time; press the button again after than and the expansion is what kills you.

> While I've come up with pointers to the theory, I wanted some more
> specific numbers to use/chuck around :-)
> How much lifetime do you sacrifice by running your CPU hotter?
> Inversely, how slack can you be with your server room cooling and still
> expect a 5 year life?

A 5 year life out of your CPU?  The temp is going to be /much/ more critical for spinning media and electrolytic caps on the mobo or in the PSU

> One of the 'gotchas' is their inefficiency, for every Watt moved, they
> can consume  1-2 Watts. If you have a 60W CPU, you end up burning
> another 120W in cooling, needing a total of 180W dissipated by the
> heatsink! :-(

Yeah Peltiers are notoriously inefficient :-/

> Another cute factoid I ran into about Fans:
> Noise varies with *5th* power of fan speed.
> Running fans at half-speed is much quieter :-)
> Not sure about the power-draw of fans w.r.t. speed.
> I'd have thought cube of speed, but that article said "square law" :-(

This is another non-trivial eqn I'd think, as energy imparted to air would vary with the square of speed, energy lost to acoustic effects varies with the 5th power (as you point out, non-trivial at higher speeds) but maybe more importantly the reverse-EMF generated by the motor spinning itself causes the fan's efficiency to vary widely and in a non-trivial-to-calculate-in-a-general way. 


More information about the linux mailing list