[mos6507]

Processing power will never be "good enough" for quite a few people. It isn't just the gamers and graphics artists who want more, it is also the engineers and scientists.

Back in the day scientists used mainframes and personal computers were for the average person (well geeks at least). Now a supercomputer is nothing more than a bunch of high end desktop CPUs running in parallel.

[vision-master]

Processing power will never be "good enough" for quite a few people. It isn't just the gamers and graphics artists who want more, it is also the engineers and scientists.

Back in the day scientists used mainframes and personal computers were for the average person (well geeks at least). Now a supercomputer is nothing more than a bunch of high end desktop CPUs running in parallel.

Along with higher maintenance costs and less security.

[Jotapay]

So some of them are having financial problems, how is this related to Moore's law?

I agree. Individual companies' financial solvency and world-wide technological advancement are two completely different things.

Just because some tech companies went out of business in 2000-2001 had zero impact on research and development world-wide.

[efarmer]

Hitting the physical boundaries of affordable semiconductor
technology is not that scary since we have very satisfactory
computing and semiconductor parts at this point. If the
semiconductor arena stops yielding decent improvements,
perhaps we will finally get the impetus to create operating
systems and tighter coded applications to march forward again.

I think there is still a very big bag of nickels for operating
system software innovation if the old saw of throwing
faster and cheaper silicon at everything ends due to
price or fabrication limits.

Imagine the idea of having a hardware system for 10
years but jumping at the chance to upgrade to faster
software 2 or3 times during the system lifetime.

I feel so old, I worked on vacuum tube card sorters and
RTL machines from the early sixties when I first started
in 1974 and now you see a 1 MIPS processor in your
coffee maker. Being close to folks in the crystal pulling
biz, I can assure you they are still making beacoup raw
material, and Moore or his assigns are still making bucks
from the industry.

[outcast]

http://www.physorg.com/news148054154.html

Moore's Law observed that the density of transistors on an integrated circuit doubles every two years. Components have shrunk over time to achieve this, but experts believed that when the characteristic transistor size reduces below ~ 20 nm, heating and quantum effects will become so severe that they will not be of practical use.

In a paper published in one of the most cited scientific journals, Nano Letters (ISI citation factor is 9.627), researchers at NPL looked at solutions to this problem as part of a project dealing with magnetic phenomena at reduced dimensions.

In the paper NPL's scientists reported on their research on single crystalline Mn-doped Ge nanowires that display ferromagnetism above 300 K and a superior performance with respect to the hole mobility of around 340 cm2/Vs and other industrially relevant parameters, demonstrating the potential of using these nanowires as building blocks for electronic devices.

Senior Research Scientist at NPL Dr Olga Kazakova said:

'The solution lies in changing not only the material but also the structure of our transistors. We have worked mainly with germanium nanowires that we have made magnetic. Magnetic semiconductors don't exist in nature, so they have to be artificially engineered. Germanium is closely compatible with silicon, meaning it can easily be used with existing silicon electronics without further redesign. The resulting transistors based on NPL's germanium nanowire technology, which could revolutionise computing and electronic devices, could realistically be 10 years away."

Sorry guys, but it doesn't look like we've reached the end of innovation.

[emailking]

Moreover, quantum computing has the potential to blow all this wide open.

[Quinny]

Just thought I'd post a picture of my new cheap as chips ultra portable Fedora system.



Tried it on quite a few PC's seems to boot fine. Allows me to save documents and then re-use when I get home - It's a bit easier than lugging my laptop around.

[outcast]

I remember when the best one of those you could get was only about 64 MB......and that was in 2002.

[EnergyUnlimited]

Moreover, quantum computing has the potential to blow all this wide open.

How likely it is that useful quantum computers will ever be built in your opinion?

Can we realistically expect to go beyond 20-30 q-bits in working quantum computer?

Interesting article on quantum computing:
http://www.sciam.com/article.cfm?id=qua ... -with-ions

Anyway, are there many classes of problems other than factorizing of large numbers, where quantum computing would be of particular merit?

[smiley]

Hitting the physical boundaries of affordable semiconductor
technology is not that scary since we have very satisfactory
computing and semiconductor parts at this point.

640k ought to be enough for everyone - Bill Gates

But seriously. Flash memory is experiencing some problem. The problem is that there were too many foundries built: investment overshoot.

Until some of these go bankrupt or the volume catches up with production volume there will be somewhat less money available for investment of new technology.

But that doesn´t mean that the technological progress is in real danger.

Lithography is still progressing in accordance to Moore's law. EUVL is set for the 22 node, while immersion (in combination with) double patterning are already available for the higher nodes.

Beyond theat it becomes difficult. Except for the challenges sketched above it is going to be extremely tough to find for instance the right resists (foto development layer), or to contain overlay problems (alignment of patterns).

And I don't think that quantum computing is ready to take over in 2013 or so (if ever).

But even for that there is also a solution. Go vertical. They are going to cheat their way out of Moores law. Stacking of structures still allows for an increase of the number of units per chip, while keeping the feature size similar.

[mos6507]

If they can't go smaller and go increasingly parallel they will run into energy consumption issues again, which is going to be more and more important in the future. Power per watt is going to be key.

[mattduke]

Recently a fundamental advancement in electronics was made, with the first implementation of the memresistor, the fourth fundamental passive component, whose existence was theorized decades ago. Highschool textbooks must now be rewritten, and the future is WIDE open once again for both analog and digital circuit design.

[yippleflipple]

so computer power is still growing exponentially... how will it be effected by the economy and peak oil?

can't they get all the energy they need from the sun? if not, can't they just spend more time computing solutions on more efficient ways to capture said energy?

[smiley]

, can't they just spend more time computing solutions on more efficient ways to capture said energy?

Interesting question

I think we're already doing that. I mean most of the great discoveries of the past decades would have been impossible without computers. Not only do we use computers as an extension of our natural thinking capabilities, but it also has allowed swift communication of idea's. Newton was sending his manuscripts by horse to Leibniz in Germany. Nowadays he would sent an e-mail.

I know that many here are skeptical to technology. But to be fair it is the same technology that allows us to communicate here. It is also the same technology which made us aware of many of man's current problems like climate change and the energy predicement.

And I think it is only fair to assume that if there is a way out of here (other than to let half the population die), that same technology is necessary to guide us. Because man is not smart enough to figure it out alone.

[Ludi]

And I think it is only fair to assume that if there is a way out of here (other than to let half the population die), that same technology is necessary to guide us. Because man is not smart enough to figure it out alone.

Are you saying "technology" will somehow enable humans to continue to exist in a condition of overshoot?

Also, are you saying "technology" is more intelligent than the humans who invented it?

[outcast]

PostPosted: Wed Dec 17, 2008 7:58 am Post subject: Re: Moore's law comes to a halt?
smiley wrote:

And I think it is only fair to assume that if there is a way out of here (other than to let half the population die), that same technology is necessary to guide us. Because man is not smart enough to figure it out alone.


Are you saying "technology" will somehow enable humans to continue to exist in a condition of overshoot?

maybe it can, if used properly

Until some of these go bankrupt or the volume catches up with production volume there will be somewhat less money available for investment of new technology.

Not necessarily, Intel has been doing a great deal of research in this stuff, as well as solid state drives.

[Dezakin]

Also, are you saying "technology" is more intelligent than the humans who invented it?

Not yet...

[Dezakin]

PostPosted: Wed Dec 17, 2008 7:58 am Post subject: Re: Moore's law comes to a halt?
smiley wrote:

And I think it is only fair to assume that if there is a way out of here (other than to let half the population die), that same technology is necessary to guide us. Because man is not smart enough to figure it out alone.


Are you saying "technology" will somehow enable humans to continue to exist in a condition of overshoot?

maybe it can, if used properly

Don't get drawn into that discussion, its a defiinition trap. By definition you can't sustain a condition of overshoot. If you're sustaining your condition you arent in overshoot. Then the argument goes into catton and the environment and why nature never does this and allways does that and how technology is irrelevant.

[Dezakin]

Moreover, quantum computing has the potential to blow all this wide open.

How likely it is that useful quantum computers will ever be built in your opinion?

Can we realistically expect to go beyond 20-30 q-bits in working quantum computer?

As we understand how to engineer them now? No. If we somehow manage to create multi-thousand qbit systems that are entirely isolated from their environment... I can't see how we'd do that but it would be a neat trick.

Interesting article on quantum computing:
http://www.sciam.com/article.cfm?id=qua ... -with-ions

Anyway, are there many classes of problems other than factorizing of large numbers, where quantum computing would be of particular merit?

Yes.

http://en.wikipedia.org/wiki/Quantum_computer

Besides factorization and discrete logarithms, quantum algorithms offering a more than polynomial speedup over the best known classical algorithm have been found for several problems, including the simulation of quantum physical processes from chemistry and solid state physics, the approximation of Jones polynomials, and solving Pell's equation.

Which in itself is interesting but what is often overlooked:

Grover's algorithm can also be used to obtain a quadratic speed-up over a brute-force search for a class of problems known as NP-complete.

I find this startling that this is often added as an afterthought. Theorem provers would become more than just toys.

[outcast]

Don't get drawn into that discussion, its a defiinition trap. By definition you can't sustain a condition of overshoot.

You can if you bend the rules, which is what GM gives us the potential to do.