Moore's Law.

tech savvy

tech savvy

Active Member
A lot of experts have predicted that Moore's Law will reach an end soon because of the physical limitations of silicon microprocessors.

Also, as you know, CPU manufactures are always striving to pack as much as they can on a die, which puts us down to 22nm (Ivy Bridge). Atom's are 0.5nm, so wouldn't we hit a wall at 0.5nm?

The reason im bring this up is because we aren't far off.

Quantum computing technology is still in its early stages, and I don't think it will ready in time when we hit that wall.

Just want to hear ya'll thoughts on the matter.
 
I don't worry about it cause there's more that companies AREN'T telling us as far as progress. Computers do what I need them to do and that's all that matters.
 
Rit said:
I don't worry about it cause there's more that companies AREN'T telling us as far as progress. Computers do what I need them to do and that's all that matters.
Click to expand...

For the average user, yes. But for the hard core PC Enthusiast, more is always better. And we all strive to get as much as we can from or PC now. Scientist that's in astronomy, biology, and so on, always needs more juice to get the job done. It's never enough.
 
Last edited:
Rit said:
I don't worry about it cause there's more that companies AREN'T telling us as far as progress. Computers do what I need them to do and that's all that matters.
Click to expand...

You do realise that conspiracy theories are nonsense. The issue will come down to voltage leakage at such small sizes way before 0.5nm and even then, it will be the rarity of rare earth materials that will impact prior to size limitations.
 
Just want to say two things.

Moore's Law is a prediction of the future increase in technology where my concern is what do I get out of it now. My other point is it'll reach a stage where no one will care about further advancements. I remember when the number of colors leaped from 65,536 to 16.7 million (tru-color?) where a color more or less wouldn't make a difference to a monitor. And if you can download a movie in a second or a tenth of a second really wouldn't matter to anybody. So I'm saying that Moore's law will be remembered as a part of history.
 
tech explorer said:
Just want to say two things.

Moore's Law is a prediction of the future increase in technology where my concern is what do I get out of it now. My other point is it'll reach a stage where no one will care about further advancements. I remember when the number of colors leaped from 65,536 to 16.7 million (tru-color?) where a color more or less wouldn't make a difference to a monitor. And if you can download a movie in a second or a tenth of a second really wouldn't matter to anybody. So I'm saying that Moore's law will be remembered as a part of history.
Click to expand...

That's not what I got out of your OP. You seem worried we'll just hit a brick wall and not be able to advance further for some time and break Moore's Law.
 
bigfellla said:
You do realise that conspiracy theories are nonsense. The issue will come down to voltage leakage at such small sizes way before 0.5nm and even then, it will be the rarity of rare earth materials that will impact prior to size limitations.
Click to expand...

There's no conspiracy theory in regards to companies having an R&D departments working on things and them not revealing information to the public. I know, cause I'm an design engineer for an R&D department and we have models for products 3-4 versions in advance.
 
Rit said:
There's no conspiracy theory in regards to companies having an R&D departments working on things and them not revealing information to the public. I know, cause I'm an design engineer for an R&D department and we have models for products 3-4 versions in advance.
Click to expand...

Ever heard of roadmaps? Ever heard of the stockmarket? If a company has a fantastic and game changing technology it would release the news to the market immediately. Because share price is everything. You may be a design engineer, but 3 or 4 models isn't what we're talking about. We're talking about transistor density limitations, and if 'they' have something that defeats these limitations, trust me, if they were confident about it they would release the news.
 
bigfellla said:
Ever heard of roadmaps? Ever heard of the stockmarket? If a company has a fantastic and game changing technology it would release the news to the market immediately. Because share price is everything. You may be a design engineer, but 3 or 4 models isn't what we're talking about. We're talking about transistor density limitations, and if 'they' have something that defeats these limitations, trust me, if they were confident about it they would release the news.
Click to expand...

They won't do so, not until it's fully developed and protected. ;)
 
Rit said:
They won't do so, not until it's fully developed and protected. ;)
Click to expand...

That may be true for ikea, but intel has a massive budget, huge legal team and can 'protect' IP in a matter of hours.

In terms of roadmaps, they already announce un-developed technology, stuff where the fabrication hasn't even begun, thats the point. Thats what they have done for ages and will continue to do.
 
bigfellla said:
That may be true for ikea, but intel has a massive budget, huge legal team and can 'protect' IP in a matter of hours.

In terms of roadmaps, they already announce un-developed technology, stuff where the fabrication hasn't even begun, thats the point. Thats what they have done for ages and will continue to do.
Click to expand...

Unless you work for intel and can prove that, as you said it's all 'conspiracy theory'. Since I work at ATK and am not able to talk about work since I'd like to keep my DOD clearance. All I can say is that the military has alot of 'advanced' technology' that isn't even out in the 'real world yet', and it won't until it has the next 'fastest/greatest thing". And with DOD stuff, and almost no budget restrictions, you can't get it protected in hours ;)

And if you look at companies that are trying to 'beat' Moore's Law. They say they have an idea but won't tell us exactly yet, and like I said in my OP that you falsely called 'hogwash' , "there's more that companies AREN'T telling us as far as progress", which is the truth. If I'm wrong, you should be able to google any company, including Intel and find any information on their R&D department.
 
The original point, which you've decided to change was moore's law. Which is that every 18 months transistor density will double. That cannot be done in many places, and I would suggest since ATK don't own a foundry, and neither do the US military, Intel would be the next best.

Secondly, in terms of raw computing power (the next extension of moore's law), there are very little embedded military applications that need anything more than what is already on something like a desktop computer. Certainly aircraft avionics (which I was an engineer with the airforce), doesn't and anything that does probably has intel inside of it. BTW, overall for moore's law related (i.e. transistor shrink) R&D (the topic afterall), Intel spend nearly $2B, which is more than the US DOD by far.

Thirdly, very easy to google not only the DOD R&D budget, but Intel and others. So I guess you must be wrong ;)
 
Last edited:
bigfellla said:
The original point, which you've decided to change was moore's law. Which is that every 18 months transistor density will double. That cannot be done in many places, and I would suggest since ATK don't own a foundry, and neither do the US military, Intel would be the next best.

Secondly, in terms of raw computing power (the next extension of moore's law), there are very little embedded military applications that need anything more than what is already on something like a desktop computer. Certainly aircraft avionics (which I was an engineer with the airforce), doesn't and anything that does probably has intel inside of it. BTW, overall for moore's law related (i.e. transistor shrink) R&D (the topic afterall), Intel spend nearly $2B, which is more than the US DOD by far.

Thirdly, very easy to google not only the DOD R&D budget, but Intel and others. So I guess you must be wrong ;)
Click to expand...

How is the budget the same as the actual technologies they are researching :confused:. Re-read the quote that it appears you are trying to disprove:

If I'm wrong, you should be able to google any company, including Intel and find any information on their R&D department
Click to expand...

Looking at that document, I can't see a single thing to explain what is going to be in the next iteration of the Intel CPU's, or any of the ones after that which have technologies currently being developed, or for the DOD, or any specific details on R&D for any entity, so it just seems like a waste of time for you to search for it and to include it in your post.

I also don't see the point in posting it if you aren't even going to refer to it. The table on page 16 shows the R&D budget for Intel, which is more than 3x your "nearly $2bn". Where your number is plucked from is anyone's guess


On topic: All the time we are using silicon and copper, we will hit a wall for the smallest size we can get a single transistor. There are ways to use the space more effectively, like trigate transistors, but they don't change the fact that there is a finitely small size you can make an individual transistor, even if you do raise it in the third dimension to improve throughput and performance
 
bigfellla said:
The original point, which you've decided to change was moore's law. Which is that every 18 months transistor density will double. That cannot be done in many places, and I would suggest since ATK don't own a foundry, and neither do the US military, Intel would be the next best.

Secondly, in terms of raw computing power (the next extension of moore's law), there are very little embedded military applications that need anything more than what is already on something like a desktop computer. Certainly aircraft avionics (which I was an engineer with the airforce), doesn't and anything that does probably has intel inside of it. BTW, overall for moore's law related (i.e. transistor shrink) R&D (the topic afterall), Intel spend nearly $2B, which is more than the US DOD by far.

Thirdly, very easy to google not only the DOD R&D budget, but Intel and others. So I guess you must be wrong ;)
Click to expand...


Man you're pulling information out of that DEEP crevasse of yours... Again, you don't have hard facts, so it's all 'conspiracy theory' I guess. And if it's that easy, what is the name of the product(s) microsoft is going to release in five years and what does it do and how much is it going to cost?

I'll be waiting for an answer.;)


Back to topic like Aastii said...
On topic: All the time we are using silicon and copper, we will hit a wall for the smallest size we can get a single transistor. There are ways to use the space more effectively, like trigate transistors, but they don't change the fact that there is a finitely small size you can make an individual transistor, even if you do raise it in the third dimension to improve throughput and performance
Click to expand...

It seems like most companies are going to try different types of materials. If they are even able to find something, I just wonder what the cost is going to be since the material might not be readily avaiable/easy to make.

There is all kinds of R&D going on that we have no idea about. Anyone who thinks that all R&D is public knowledge is either nuts or just a pure noob.
Click to expand...

No you're wrong! It's all a conspiracy theory! *Goes back into my room with strings across my room trying to find the answer :rolleyes:
 
Wait.... if we run out of room to put transistors on a CPU, we could... make the CPU bigger! Problem = solved. You're welcome, internet.
 
Of course there are tons of R&D that we don't know about. The first reason that comes to mind about a non military research would be financial. Ideas are what gets you money so if you tell everyone about your idea, some company will probably develop it faster than you, therefore get all the money you should have got (never been as capitalist as I am now woow).
On the other hand, military research is far more secretive than civil research... Of course I have no proof, just logic and researches of what happened in the past.
 
You must log in or register to reply here.
Back
Top