(j3.2006) Is Moore's law over?

[Keith Bierman]

On Thu, Aug 21, 2008 at 6:38 PM, Van Snyder <Van.Snyder at jpl.nasa.gov> wrote:

> For a long time, software managers have depended upon Moore's law to
> avoid re-thinking software to improve its performance.



Moore's law is about density doubling, not about clock speed.

>
>
> My program runs on a 362-Pentium cluster, typically taking 15 hours to
> process each day's data.  Benchmarks with four-year-newer equipment
> suggest we could get by with 42 nodes, each with two quad-core Pentia,
> which works out to 336 cores, i.e., about the same.
> ....
> There isn't much of our program of the form "do n**3 things on n**2
> data."  Mostly (82% or so) it's "do n things on n data."  That is, it's
> mostly memory-bandwidth limited, not cache- or processor-bandwidth
> limited.


You might want to look at SiCortex.



>
>
> Will Moore's law save us, or do we need to re-think our program?


If the program can run in the appropriate timeframe with more nodes, the
nodes will (thanks to Moore's law) be smaller, fit in the same space (or
less) and offer more economical operation. If scaling to more nodes isn't
trivial, then (if you are relying on Moore's Law) you need to rethink your
algorithm and revise it for better scalability.

-- 
Keith Bierman
khbkhb at gmail.com
kbiermank AIM
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://j3-fortran.org/pipermail/j3/attachments/20080822/156ab9e9/attachment.html