On Thu, 12 Jun 2014 09:06:50 +0000, Steven D'Aprano wrote:
> On Thu, 12 Jun 2014 12:16:08 +1000, Chris Angelico wrote:
>> On Thu, Jun 12, 2014 at 12:08 PM, Steven D'Aprano
>> <steve+comp.lang.pyt...@pearwood.info> wrote:
>>> I'm just pointing out that our computational technology uses over a
>>> million times more energy than the theoretical minimum, and therefore
>>> there is a lot of room for efficiency gains without sacrificing
>>> computer power. I never imagined that such viewpoint would turn out to
>>> be so controversial.
>> The way I understand it, you're citing an extremely theoretical
>> in the same way that one can point out that we're a long way from
>> maximum entropy in a flash memory chip, so it ought to be possible to
>> pack a lot more data onto a USB stick.
> Um, yes?
> Hands up anyone who thinks that today's generation of USB sticks will be
> the highest capacity ever, that all progress in packing more memory into
> a thumb drive (or the same memory into a smaller drive) will cease
> effective immediately?
>> The laws of physics tend to put boundaries that are ridiculously far
>> from where we actually work - I think most roads have speed limits that
>> run a fairly long way short of c.
> "186,000 miles per second: not just a good idea, it's the law"
> There's no *law of physics* that says cars can only travel at the speeds
> they do. Compare how fast a typical racing car goes with the typical
> 60kph speed limit in suburban Melbourne. Now compare how fast the
> Hennessey Venom GT goes to that speed limit.
> Speed limits for human-piloted ground-based transport ("cars") are more
> based on social and biological factors than engineering ones. Similarly,
> there are biological factors that force keyboards to be a minimum size.
> We probably could build a keyboard where the keys were 0.1mm square, but
> what would be the point? Who could use it? Those social and biological
> factors don't apply to computing efficiency, so it's only *engineering*
> factors that prevent us from being able to run your server off a watch
> battery, not the laws of physics.
> It is my contention that, had Intel and AMD spent the last few decades
> optimizing for power consumption rather than speed, we probably could
> run a server off, well, perhaps not a watch battery, but surely a factor
> of 100 improvement in efficiency isn't unreasonable given that we're
> just moving a picogram of electrons around?
but a 20 year old server would probably take a week to do what a current
one does in an hour (random figures chosen for effect not accuracy).
How does the power consumption compare on those time-scales, not to
mention the cost of the wasted time?
I would agree that for the average desk-top users modern processor
performance exceeds that required by a considerable margin so perhaps
optimising for power consumption is now possible, wait a minute arn't
intel & AMD now developing lower powered processors?
Breeding rabbits is a hare raising experience.