• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Intel roadmap promises 10nm by 2018

Idontcare said:
Where's the "promise" from Intel?
Click to expand...

No promises, just a roadmap. It's just a way to sensationalize and some people don't know when to take that out of the equation when reposting news.

Wats after 10nm , then 5nm then 1nm. .. then thats it , weve reached peak.. no or notch..troobly mooble...hackey sack multiplex..gg..
 
wall at 4nm might as well hit it ASAP to get more time for carbon as semiconductor, 3d chips, etc. Just business as usual. They'll hit it by then I guarantee it. Intel means what they say.
 
BTRY B 529th FA BN said:
The material used to make chips will change is what i'm thinking.
Click to expand...

only a few options though, carbon the only real promising one I believe (promising = worth jumping ship to for cramming more resistors on).

Though we could move to some of those expensive materials that let you hit like 30ghz.
second thought too much heat.

I stand by what I said, we're limited at 4nm, carbon will extend that a bit (IDK know how far???), but from there there's little future until biological computing (whatever the word is...bio..something) takes hold.

Going to need quantum entanglement to do much better, then you could just make the chips bigger no problem.
 
soccerballtux said:
only a few options though, carbon the only real promising one I believe (promising = worth jumping ship to for cramming more resistors on).

Though we could move to some of those expensive materials that let you hit like 30ghz.
second thought too much heat.

I stand by what I said, we're limited at 4nm, carbon will extend that a bit (IDK know how far???), but from there there's little future until biological computing (whatever the word is...bio..something) takes hold.

Going to need quantum entanglement to do much better, then you could just make the chips bigger no problem.
Click to expand...

Yep, without quantum entanglement the problem is the speed of light is just too slow when you want largish (triple-digit mm^2) chips to operate at tens upon tens of GHz.

I'm not worried though. The last time the world was in a similar situation where we thought we had the limits of physics figured out and the future was going to be boring in our view of it at the time a person by the name of Max Planck came along and turned it all upside down.

I don't know what we'll be using 50yrs from now in place of xtors, I just know it'll be indistinguishable from magic if I fail to improve upon my 20th century education in the meantime.

Clarke's Three Laws are three "laws" of prediction formulated by the British writer and scientist Arthur C. Clarke. They are:
  1. When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong.
  2. The only way of discovering the limits of the possible is to venture a little way past them into the impossible.
  3. Any sufficiently advanced technology is indistinguishable from magic.
Click to expand...
 
-Slacker- said:
I thought 11nm was the limit for silicon ...
Click to expand...

Who knows. It's just numbers that we throw around cause we read somewhere that PhD dude XYZ said it's not possible.
I've heard 4/5 most places though.

IIRC with carbon nanotubes the goal is to use a single layer of atoms to make your transistor; when it's a 1D structure it behaves like a superconductor. Or something.
Thinnest nanotube is ~4angstroms; the silicon lattice constant is ~5 angstroms, so that would let us drop from 5nm to half a nanometer. That would be a lot more transistors...maybe Intel's not so close to the wall...

I think it'll be interesting if/when some of these companies will billions in cash (google, Apple esp with 75B) stop pulling a profit (if). What will they do with their holdings? I guess the shareholders will just demand the company stop operating and pay out the cash. That would be the final shift of wealth out of the middle class. That probably belongs in P&N though.
 
Last edited:
-Slacker- said:
I thought 11nm was the limit for silicon ...
Click to expand...

soccerballtux said:
Who knows. It's just numbers that we throw around cause we read somewhere that PhD dude XYZ said it's not possible.
I've heard 4/5 most places though.
Click to expand...

Pathfinding research efforts have demonstrated the 11nm node. So we'd call that "proven possible".

The 4/5nm talk comes from theoretical framework that we are confident speaks to the limits of scaling silicon-based xtors (where the channel itself is formed of doped-silicon).

We haven't established a proven path to get to those length-scales but the physics seems solid enough to suggest we should be able to do it provided we can get the economics to justify us attempting to do it.

Post-4nm though and we have to abandon silicon as the active channel...we need to go graphene, nanotube, III-V, etc...there's a whole periodic table of elements to go after.

What we expect is that after 4nm the scaling will no longer be dimensional (as in traditional shrinking), rather it will be in terms of scaling the material composition itself.
 
The issue isn't whether a silicon chip will work at that scale, but whether the industry can continue to turn a good profit on them in mass production. It is pushing the theoretical limits for silicon, but they've already invested hundreds of billions in fabrication facilities and developing the technology. Going smaller still is likely to require self-assembly techniques and new materials that are only now beginning to be developed.

A billion parts on a chip is just a ridiculous number anyway. All the cache and ram and extra cores and whatnot are there to make the technology cheaper among other things. An optical circuit can operate at 60thz, while a silicon chip might do 5ghz. Its just no competition and along with learning how to do more with fewer parts there's still plenty of ways forward without Moore's law still being in effect.
 
soccerballtux said:
Who knows. It's just numbers that we throw around cause we read somewhere that PhD dude XYZ said it's not possible.
I've heard 4/5 most places though.

IIRC with carbon nanotubes the goal is to use a single layer of atoms to make your transistor; when it's a 1D structure it behaves like a superconductor. Or something.
Thinnest nanotube is ~4angstroms; the silicon lattice constant is ~5 angstroms, so that would let us drop from 5nm to half a nanometer. That would be a lot more transistors...maybe Intel's not so close to the wall...

I think it'll be interesting if/when some of these companies will billions in cash (google, Apple esp with 75B) stop pulling a profit (if). What will they do with their holdings? I guess the shareholders will just demand the company stop operating and pay out the cash. That would be the final shift of wealth out of the middle class. That probably belongs in P&N though.
Click to expand...


I think we're a long way off from that. Assuming these machines aren't indestructible, and the number of users keep growing, we'll still need new ones. Not to mention that there is still lots of room for improvement above and beyond the CPU. Just take a look at SSDs. They're absolutely amazing given what we had 10 years ago. Although, I guess those would suffer from scaling problems as well...
 
Idontcare said:
snip
3. Any sufficiently advanced technology is indistinguishable from magic.
Click to expand...

I can still hear Leonard Nimoy saying that in Civ 4.

Wake me up when we get quantum computing.

Idontcare said:
Pathfinding research efforts have demonstrated the 11nm node. So we'd call that "proven possible".

The 4/5nm talk comes from theoretical framework that we are confident speaks to the limits of scaling silicon-based xtors (where the channel itself is formed of doped-silicon).

We haven't established a proven path to get to those length-scales but the physics seems solid enough to suggest we should be able to do it provided we can get the economics to justify us attempting to do it.

Post-4nm though and we have to abandon silicon as the active channel...we need to go graphene, nanotube, III-V, etc...there's a whole periodic table of elements to go after.

What we expect is that after 4nm the scaling will no longer be dimensional (as in traditional shrinking), rather it will be in terms of scaling the material composition itself.
Click to expand...

If nanotubes or some other material can act as a superconductor then that would enable enormous increases in ghz, right? How high could you go then, will we see humongous rooms of linked servers with an underground reservoir for cooling? 1 thz? Or 60 thz as Wulherion stated? Aren't we going to have to find a way around the speed of light at some point if we want to keep increasing computing capacity?
 
Last edited:
bryanW1995 said:
If nanotubes or some other material can act as a superconductor then that would enable enormous increases in ghz, right? How high could you go then, will we see humongous rooms of linked servers with an underground reservoir for cooling? 1 thz? Or 60 thz as Wulherion stated? Aren't we going to have to find a way around the speed of light at some point if we want to keep increasing computing capacity?
Click to expand...

Quantum computers aren't some kind of magic bullet that will replace all other computers. That's a star trek type fantasy. They are unbeatable for processing some types of programs, and slow for others.

Theoretically spintronics can combine the best of both worlds in hybrid computers using both classical and quantum circuitry. Instead of pushing current through circuits, they use the spin of the electron. In this way they can approach the speed of light using very small amounts of energy and without frying everything in sight or be entangled for quantum computing.

The trick is engineering precision. Just as shrinking circuits or making them faster requires greater precision, so does designing spintronic devices. Modern hard disk drives are spintronic devices, but the ability to make complex circuits is still some years away. Room temperature superconductors, carbon nanotubes, graphine, plasmonics, etc. all have potential, but have their theoretical limitations that spintronics don't.
 
Last edited:
Soundmanred said:
No promises, just a roadmap. It's just a way to sensationalize and some people don't know when to take that out of the equation when reposting news.

Wats after 10nm , then 5nm then 1nm. .. then thats it , weve reached peak.. no or notch..troobly mooble...hackey sack multiplex..gg..
Click to expand...


I like your post OMG I said that once too on here. Too funny.

We are 7 to 8 years away from a Intel 10nm fab... Then maybe in 2024 it will be 1nm process. :awe:😛
 
tweakboy said:
I like your post OMG I said that once too on here. Too funny.

We are 7 to 8 years away from a Intel 10nm fab... Then maybe in 2024 it will be 1nm process. :awe:😛
Click to expand...

i doubt that, they are planning to release their last silicon chip by 2025
 
soccerballtux said:
the mark of the beast isn't about that. The devil isn't stupid enough to do exactly what all the Christians are expecting him to do.
Click to expand...

I got a friend who swears its going into the hand or forehead i loved your response so much ill pay him a visit today to tell him how stupid he is for thinking the devil is gonna do what everyone knows he will do.

😉 Love messing with this guy and your my new best friend.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top