[OSM-dev] Re: osmeditor2 to Java, and a common Java OSM client library

[Ben Gimpert]

On Fri, 26 May 06 @11:24am, Nick Hill wrote:
> Ruby appears to have a very valuable, strong point; it's clean 
> architecture and the effect it has on coding encourages maintainable 
> code. HOWEVER, please forget the 3 million quid's worth and 10p. 
> Actually calculate values which can be applied on a knowable time frame.
> 
> My 3 year old athlon XP 2200+ cost £46 and performs like a 2.3Ghz P4. A 
> dual core P4 2.66 today costs £85.
> 
> Actual:
> Performance: Twice
> Cost:Twice
> Dissipation: 1.5-2x.
> 
> If the historical implications of moore's law were holding today over 3 
> year time frame:
> Performance: 4x
> Price Same
> Dissipation:Same
> 
> I am not suggesting that moore's law need stall, or that we are now at 
> physical limits. However, the evidence could lead to that conclusion. 

I agree that we may be approaching some physical limits for
silicon-based, electric / magnetic, single-pressing ("one CPU") chips.
But I also don't agree with the evidence of Moore's Law is slowing.

Instead, we're at the cusp of the next "big wave."  There was probably a
similar stagnation at the end of the vacuum tube era, just before
transistors.  I believe *that's* our historical precedent.  Very good
work is being done on optical chips, and grid motherboards -- with a
*multitude* of liquid-cooled CPU's -- are really not that far off.

> This is just as likely to be the levelling of demand for faster 
> processors on the desktop. There is no new money in faster processors 
> for the desktop.

I disagree, slightly.  There is massive demand for more processing power
on the desktop, but right now it's not targetted at Intel and AMD -- but
at nVidia and ATI.  It's easy to shrug off "just the gamers," but better
entertainment (read, video and audio codecs and 3D) is a seriously
financially-lucrative business.  If I were Intel, I'd be terrified.

We also shouldn't forget that with more computational power, we get new
problems that can *start* to be addressed.  The killer app for massive
numbers of CPU of the desktop might end up being healthcare -- run a new
analysis of your own genome every morning to optimize what to eat so you
don't get sick.  This shit is not all that sci-fi, and far more
near-term than flying cars and jetpacks.

> The new raw processing money will come from charging premium prices
> for applications which need concentrated processing power.
> 
> From these figures, if performing a mandelbrot-type task in C at a
> given rate cost £300 today, in 3 years time with Ruby will cost
> £120,000. (In actual terms, this could be considered a price for every
> 6 months considering HVAC+power+space. With projected fuel scarcity,
> the figures for 3 years time may be higher.).

I don't agree with including heat / power / dissipation in the equation.
We don't properly cool chips right now, and optical chips run extremely
cold and low-power.

> Processor manufacturers will continue to introduce new instructions
> and features to enhance those areas where the use of desktop computers
> still comes up against limits, such as games. Intel have made such an
> announcement. It is possible, but by no means certain that we can make
> use of these instructions.

Games are 3D are matrices tranforms are fast floating point.  GIS
software would *thrive* with super-fast floating point.

How long until the mobile phone makers demand a *REAL* low-power and
low-heat CPU -- and one that's worth paying for?  Bring on the optics!

		Ben