[BabyPeanut]

Sun's Commitment to Eco-Responsibility (link)
Sun is committed to eliminating the digital divide so that everyone can participate on the network. But we know that as the number of people using computing devices grows so does our consumption of energy and natural resources. Consider these facts:

• Growing participation in the network: There are 1 billion people worldwide online today and that number is expected to grow by 35 percent, or 350 million people, in the next two years.
• Soaring energy costs: The costs of natural resources are escalating. With oil at $60/barrel (US) in October 2005, economies worldwide are experiencing strain.
• Infrastructure constraints: A global population on an exponential growth path is challenging governments and corporations alike to take a hard look at how the world's raw materials and space are being used.

[EnergySpin]

Why not FPGA devices?
Program hardware as software?

[BabyPeanut]

Why not FPGA devices?
Program hardware as software?

Oh, that'll fix everything right there!

BTW F-P-G-A is S-L-O-W

[turmoil]

well until everything is nano sized, there's a floor for power consumption i think. It will be a bit longer before we are running cpus on 14 watts like our brains do.

[EnergySpin]

Why not FPGA devices?
Program hardware as software?

Oh, that'll fix everything right there!

BTW F-P-G-A is S-L-O-W

Are you sure we are talking about the same devices?
Field Programmable Gate Arrays?
My engineering colleagues have used, not prototyped, I repeat USED FPGAs to speed up some really nasty Monte Carlo calculations ... some of them might save the lives of luddite-doomers around here.

[sjn]

Why not FPGA devices?
Program hardware as software?

Oh, that'll fix everything right there!

BTW F-P-G-A is S-L-O-W

Are you sure we are talking about the same devices?
Field Programmable Gate Arrays?
My engineering colleagues have used, not prototyped, I repeat USED FPGAs to speed up some really nasty Monte Carlo calculations ... some of them might save the lives of luddite-doomers around here.

While typically slower when used as fixed general purporse processing devices, they come into their own when you need to perform anticipated algorithms. Some models can be reprogrammed very quickly indeed and it is possible to reconfigure the device optimally for any given task; this way it easily out performs fixed funcion general purpose CPUs.

well until everything is nano sized, there's a floor for power consumption i think. It will be a bit longer before we are running cpus on 14 watts like our brains do

Er no. The CPU I'm using now uses far less than that: XScale-PXA270 (Sharp Zaurus SL-C3100 handheld).

EDIT: Fix spelling.

[turmoil]

Er no. The CPU I'm using now uses far less than that: XScale-PXA270 (Sharp Zaurus SL-C3100 handheld).

I guess I meant cpus like these, lol: http://www.intel.com/design/intarch/pen ... ntium4.htm

Although these (http://www.appleinsider.com/article.php?id=1169) use much less.

[EnergySpin]

While typically slower when used as fixed general purporse processoring devices, they come into their own when you need to perform anticipated algorithyms. Some models can be reprogrammed very quickly indeed and it is possible to reconfigure the device optimally for any given task; this way it easily out performs fixed funcion general purpose CPUs.

Correct .. we are using them to speed up random number generation for stochastic simulations of cells. There was a publication in Nature Biotechnology a few months ago which featured the implementation of the Gillespie algorithm on a chip. It is is up to hybrid sw/hw engineers to come-up with a system design (not a new technology platform) to start simulations in those babies. Once we do that ... it is going to be a new era for bio-engineering, material science etc.
I'm following developments just for the heck of it ...