Re: [microblaze-uclinux] OT?, Performance

[Matthew Rubenstein <email@xxxxxxxxxxxx>]

	Transistor electromigration wears out logic chips; higher clock cycles
make it happen faster:
http://www.google.com/search?q=overclock+electromigration . And hotter
chips suffer other wear, such as at heterogeous chemical junctions,
stable at lower temperatures, can react at higher temperatures. Chip
cooling can reach only the surface, while the heat is generated inside,
where it has a chance to work on the components briefly before
conducting to cooler coupled components. There is also wear from
mechanical vibration, as electrical oscillations can cause that,
especially at mechanical microflaws in silicon die crystals, pin
junctures, adhered packaging, etc.


On Wed, 2004-05-12 at 18:41, jozsef imrek wrote:
> dear matthew,
> 
> On Wed, 12 May 2004, Matthew Rubenstein wrote:
> > chips can exceed. Overclocking does reduce the lifetime of the chip, as
> > it runs hotter, even if surface cooled. But with these experimental
> that's interesting. i'm pretty new in this fpga field, could you
> please point to some more information on this lifetime issue?
-- 


(C) Matthew Rubenstein

___________________________
microblaze-uclinux mailing list
microblaze-uclinux@itee.uq.edu.au
Project Home Page : http://www.itee.uq.edu.au/~jwilliams/mblaze-uclinux
Mailing List Archive : http://www.itee.uq.edu.au/~listarch/microblaze-uclinux/