[HARDWARE] Cost of crunching (was: Mac Questions)
dan_oetting at uswest.net
Wed Mar 13 14:01:11 EST 2002
on 3/13/02 12:23 PM, John L. Bass wrote:
> > It doesn't matter if the cycles/energy are done today, or tomarrow, if
> > are used there is no savings.
> Not true, If they are done 'tomorrow' then there will be a saving on
> electricity because the more powerful computer of tomorrow will crunch much
> faster than todays. And possibly with miniaturisation at a lower power
> consumption to boot.
>That is an interesting point. Have you noticed that the new 1.x GHz
>their companion chipsets/memory are nearly 100W, nearly linear the power
>slower processors which used to be 20w or so?
In my original post I used ballpark guesses for some of the source
numbers. If we're going to compare processors it should be done with real
numbers. I'm using only the CPU power in the calculation since this
number is available, it's the only component really utilized by the RC5
cruncher (spinning up the disk after every block is another issue) and
represents the difference between letting the processor idle or crunching
cira 93-94 68030 33Mhz. [From www.lowendmac.com]
RC5: 9725 k/s (0.13 blocks/hr) [From d.net speed chart]
CPU power 2.6w max (@40 Mhz?) [From motorola product summary]
$1US = (aprox) 10,000 watt hrs = 3846 CPU hrs = 500 blocks.
Can we get enough of these data points to plot crunching costs over time?
-- Dan Oetting
To unsubscribe, send 'unsubscribe hardware' to majordomo at lists.distributed.net
More information about the Hardware