Overclock.net banner

1 - 12 of 12 Posts

·
Registered
Joined
·
402 Posts
Discussion Starter #1
So I started thinking the first nanometer processors were introduced about 6 years ago at a nice whopping 90nm if I can recall right and 6 years later we have gone all the way down to 32nm and rapidly approaching 22nm and smaller. So what happens when we get to 1nm size processors? Well we get to the picometer. Is making a proccesor with a lets say 90picometer or 90pm process technology even possible? If so how long do you think until we start seeing them? Less than 5 years? 5 years? 10 years?

Disclaimer: Sorry if I sound ******ed these small scales I'm not familiar with.
 

·
Registered
Joined
·
295 Posts
I personally think we are reaching physical limits at like 22nm>X>5nm. This is a big question that only patience can answer.
 

·
Registered
Joined
·
2,079 Posts
according to moores law and intel it should be within the next decade
 

·
Registered
Joined
·
1,223 Posts
Quote:

Originally Posted by roberts91 View Post
So I started thinking the first nanometer processors were introduced about 6 years ago at a nice whopping 90nm if I can recall right and 6 years later we have gone all the way down to 32nm and rapidly approaching 22nm and smaller. So what happens when we get to 1nm size processors? Well we get to the picometer. Is making a proccesor with a lets say 90picometer or 90pm process technology even possible? If so how long do you think until we start seeing them? Less than 5 years? 5 years? 10 years?

Disclaimer: Sorry if I sound ******ed these small scales I'm not familiar with.
22nm they will just call it

220 picometer
 

·
Premium Member
Joined
·
4,386 Posts
I'm not an engineer, but we've seen how fragile the 32nm processors are. 22nm will probably be made of glass and toothpicks, and anything under that is probably beyond the physical limit.

Personally, I think we'll see a completely new type of processor before we see a 90pm processor.

Oh, and, side note - Moore's "law" is such BS. It's not a law at all, just speculation.
 

·
Registered
Joined
·
295 Posts
Quote:

Originally Posted by ayeyo View Post
i'm not an engineer, but we've seen how fragile the 32nm processors are. 22nm will probably be made of glass and toothpicks, and anything under that is probably beyond the physical limit.

Personally, i think we'll see a completely new type of processor before we see a 90pm processor.

Oh, and, side note - moore's "law" is such bs. It's not a law at all, just speculation.
this ^^^^
 

·
Registered
Joined
·
220 Posts
Biggest problem is heat. You could make it smaller true, but it could become as hot as the exhaust from a rocket.

EDIT: I agree with AyeYo as well. A new design/type of processor will probably come out before it get smaller.
 

·
Premium Member
Joined
·
4,386 Posts
What I don't understand is why there's such reluctance towards making the die bigger. I understand the benefits of making the process smaller, but there has to be a limit somewhere, and it would seem easier/more cost effective to just make the die bigger. Who's idea was it to have this completely arbitrary general die size and attempt to always stuff more transistors onto it?

If you have a 5mm x 5mm die with 500 million 90nm transistors, you can either halve the process size to 45nm to get 1 billion transistors or you could just double the die size to 10mm x 10mm... Aside from heat and power consumption, why wouldn't that work?
 

·
Hold on to your butts!
Joined
·
3,213 Posts
We are reaching nm boundaries. 22/16/11nm will probably be the end.

To answer ayeyo's question, people always want smaller. Till we find out how small we can make chips, we wont really increase the size of them.
 

·
Registered
Joined
·
220 Posts
Quote:

Originally Posted by AyeYo View Post
What I don't understand is why there's such reluctance towards making the die bigger. I understand the benefits of making the process smaller, but there has to be a limit somewhere, and it would seem easier/more cost effective to just make the die bigger. Who's idea was it to have this completely arbitrary general die size and attempt to always stuff more transistors onto it?

If you have a 5mm x 5mm die with 500 million 90nm transistors, you can either halve the process size to 45nm to get 1 billion transistors or you could just double the die size to 10mm x 10mm... Aside from heat and power consumption, why wouldn't that work?
I'm assuming to keep it a standard as well as keeping the process the same maybe. Honestly I think it's just a technique to keep pushing the bar higher. To push newer designs and such.
 

·
Premium Member
Joined
·
4,386 Posts
Quote:


Originally Posted by Sneaky07
View Post

I'm assuming to keep it a standard as well as keeping the process the same maybe. Honestly I think it's just a technique to keep pushing the bar higher. To push newer designs and such.

Yea, make sense. Like the guy above you said, might as well keep pushing smaller until they can't push anymore. High-K already allowed them to go smaller than they thought possible; hopefully there will be more of those advances.
 
1 - 12 of 12 Posts
Top