32nm....what then?
Forum CPU & Components : CPUs - 32nm....what then?
this might help what your looking for. i cant tell you much technical detail on the information your asking, so wait till someone comes around with there info on that, but some of that might be answered in the link provided. (i would try and elaborate on some of the info in the link, but im about to go to bed and quite tired)
22nm is the next one down according to that article
http://www.dailytech.com/article.aspx?newsid=2649
hope that helps
EDIT:- JumpingJ beat me to it 
"Ill get you next time heman"
| Quote : There's a limit coming up to how small they can go with their current process, but they can switch materials (photons, single electrons, flux capacitor, whatever), etc... and perhaps go even smaller. But yes, no matter what they do they will hit a limit, the building blocks of our universe are only so big. |
Ahh....I always new flux capacitors were they way to go. 
My way out thoery is chips will switch to single atom vibrations powered by different powered and read by different wavelenghts of light ! kind of like a two sidded lazer powered abacus !!! lol ok so im nuts
Edit: On thinking about it maybe its not such a bad idea only switch to microwaves on one side light to read hmmm THz chip !!! fun to think about
After 32 nm comes 9 nm. 
| Quote : Intel has been very open about scaling down processors on new transistor sizes, but when will it end? Intel has talked about 32nm but nothing passed that. There is a physical limit to how small it can get before a processor leaks to much to be useful. Does anyone have an educated guess as to how small they can get before it needs to switch over to something more efficent and scaliable? Also how will Intel deal with them memory bandwidth issues of multiple cores? I mean in the sense that sooner or later they will also hit a wall with processor pins, how will they deal with that? Lucky for us both companies wont run into these problems for a while, just they are coming to be somewhat of a puzzle to me. |
The fact is that Intel will have lots of headaches going to 45nm becasue of the following issues:
1) They lack SOI-SiGE.
2) Their process manufacturing isn't as spectacular as AMD's.
AMD would only be 4-6 months behind intel in 45nm which means that intel's advantage over AMD in process shrinking will vanish. 
| Quote : Intel has been very open about scaling down processors on new transistor sizes, but when will it end? Intel has talked about 32nm but nothing passed that. There is a physical limit to how small it can get before a processor leaks to much to be useful. Does anyone have an educated guess as to how small they can get before it needs to switch over to something more efficent and scaliable? Also how will Intel deal with them memory bandwidth issues of multiple cores? I mean in the sense that sooner or later they will also hit a wall with processor pins, how will they deal with that? Lucky for us both companies wont run into these problems for a while, just they are coming to be somewhat of a puzzle to me. |
The fact is that Intel will have lots of headaches going to 45nm becasue of the following issues:
1) They lack SOI-SiGE.
2) Their process manufacturing isn't as spectacular as AMD's.
AMD would only be 4-6 months behind intel in 45nm which means that intel's advantage over AMD in process shrinking will vanish.
1) Intel has already stated it is not cost effective to use SOI until around 32nm. Additional Intel wishes to further the technology with regards to the fact that the current implementation of SOI is only a partial depletion. They are aiming for 100% depletion which takes time to research as well.
1-Why.
| Quote : Intel says SOI is still too expensive. A spokesman argued that even a small amount of extra cost, multiplied by the 100 million or so chips Intel produces per year, makes SOI's cost prohibitive... |
| Quote : The Terahertz transistor will contain three major changes, Willoner noted. First, the transistors will feature thicker source and drain regions, substructures inside individual transistors that allow electrical current to pass. Second, the company will embed an insulating layer, called Ultra Thin SOI, below the source and drain.
|
But the technology could find its way into 45nm nodes as well, with regards to Intel implementing tri-gate transistors at that node.
Research to development.
2) I would beg to differ with regards to Intel leading the pack by 4+ quarters is a significant achievement, and showed a smooth transition to the new node.
Why.
Typically a mature yield is described as being 85%-95% working silicon, but 60% for the 1st year of a new node is commonly considered mature as well so it's a coin toss as to what the real yields are at for Intel but I would have to think they would be in the 70%-80% range realistically.
My faith in AMD being 4-6 months behind Intel on the 45nm node is laughable as Intel is closing on the 1 year mark of 65nm node production while AMD is still trying to get 65nm online. How on earth will AMD be able to match the process shift set by Intel when they are clearly behind a node already?
| Quote : Intel has been very open about scaling down processors on new transistor sizes, but when will it end? Intel has talked about 32nm but nothing passed that. There is a physical limit to how small it can get before a processor leaks to much to be useful. Does anyone have an educated guess as to how small they can get before it needs to switch over to something more efficent and scaliable? Also how will Intel deal with them memory bandwidth issues of multiple cores? I mean in the sense that sooner or later they will also hit a wall with processor pins, how will they deal with that? Lucky for us both companies wont run into these problems for a while, just they are coming to be somewhat of a puzzle to me. |
The fact is that Intel will have lots of headaches going to 45nm becasue of the following issues:
1) They lack SOI-SiGE.
2) Their process manufacturing isn't as spectacular as AMD's.
AMD would only be 4-6 months behind intel in 45nm which means that intel's advantage over AMD in process shrinking will vanish.
This is EXTREMELY laughable!!
1. Doesn't Intel already use some form of SiGE? (i am not completely sure, just asking, i remember jack mentioning this). It also looks like AMD is having trouble moving SOI from 90nm to 65nm, maybe its a good thing Intel isn't using SOI.
2. Their process doesn't have SOI. That doesn't mean it is inferior to AMDs. In fact, Jack will argue that it is better. Do you want me to provide a link?
WOW, only 4-6 months? This is VERY highly unlikely! This would mean that AMD can ramp up 45nm in less than 1 year!!!! That would be absolutely CRAZY and EXTREMELY unlikely!
| Quote : Intel has been very open about scaling down processors on new transistor sizes, but when will it end? Intel has talked about 32nm but nothing passed that. There is a physical limit to how small it can get before a processor leaks to much to be useful. Does anyone have an educated guess as to how small they can get before it needs to switch over to something more efficent and scaliable? Also how will Intel deal with them memory bandwidth issues of multiple cores? I mean in the sense that sooner or later they will also hit a wall with processor pins, how will they deal with that? Lucky for us both companies wont run into these problems for a while, just they are coming to be somewhat of a puzzle to me. |
The fact is that Intel will have lots of headaches going to 45nm becasue of the following issues:
1) They lack SOI-SiGE.
2) Their process manufacturing isn't as spectacular as AMD's.
AMD would only be 4-6 months behind intel in 45nm which means that intel's advantage over AMD in process shrinking will vanish.
1) Intel has already stated it is not cost effective to use SOI until around 32nm. Additional Intel wishes to further the technology with regards to the fact that the current implementation of SOI is only a partial depletion. They are aiming for 100% depletion which takes time to research as well.
1-Why.
| Quote : Intel says SOI is still too expensive. A spokesman argued that even a small amount of extra cost, multiplied by the 100 million or so chips Intel produces per year, makes SOI's cost prohibitive... |
| Quote : The Terahertz transistor will contain three major changes, Willoner noted. First, the transistors will feature thicker source and drain regions, substructures inside individual transistors that allow electrical current to pass. Second, the company will embed an insulating layer, called Ultra Thin SOI, below the source and drain.
|
But the technology could find its way into 45nm nodes as well, with regards to Intel implementing tri-gate transistors at that node.
Research to development.
2) I would beg to differ with regards to Intel leading the pack by 4+ quarters is a significant achievement, and showed a smooth transition to the new node.
Why.
Typically a mature yield is described as being 85%-95% working silicon, but 60% for the 1st year of a new node is commonly considered mature as well so it's a coin toss as to what the real yields are at for Intel but I would have to think they would be in the 70%-80% range realistically.
My faith in AMD being 4-6 months behind Intel on the 45nm node is laughable as Intel is closing on the 1 year mark of 65nm node production while AMD is still trying to get 65nm online. How on earth will AMD be able to match the process shift set by Intel when they are clearly behind a node already?
Looks like a really good summary and can not argue against it. Intel has demonstrated working SRAM at 45nm, while AMD claims they have 45nm SRAM, they have not even claimed to have it working, let alone providing a picture of it. And they really expect to have 45nm within 4-6 months after Intel? I do not see AMD getting <1year behind Intel's nodes.
| Quote : what makes intels transistors faster?and someone mentioned quantum effects as transistors shrink,i have recently refreshed my memory on atomic structure and i am just not putting that together.
|
Quantum effects...
Electrons randomly change quantum states within an atom based upon total system energy. To make the math really simply, let's say that there is only one dimension - up and down.
If you have 10,000 atoms, the odds are staggeringly high that the numbers vibrating "up" with always be very similar to the number vibrating "down"
When you have 1000 atoms, the probabilities shift substantially, but the odds still favor massively a reasonable balance.
When you get to 100 or 10, the chance get much higher of a quantum alignment that displaces electrons in a disruptive way...
It's a lot more complicated than this, but it's a sketch of why...
| Quote : Intel has been very open about scaling down processors on new transistor sizes, but when will it end? Intel has talked about 32nm but nothing passed that. There is a physical limit to how small it can get before a processor leaks to much to be useful. Does anyone have an educated guess as to how small they can get before it needs to switch over to something more efficent and scaliable? Also how will Intel deal with them memory bandwidth issues of multiple cores? I mean in the sense that sooner or later they will also hit a wall with processor pins, how will they deal with that? Lucky for us both companies wont run into these problems for a while, just they are coming to be somewhat of a puzzle to me. |
The fact is that Intel will have lots of headaches going to 45nm becasue of the following issues:
1) They lack SOI-SiGE.
2) Their process manufacturing isn't as spectacular as AMD's.
AMD would only be 4-6 months behind intel in 45nm which means that intel's advantage over AMD in process shrinking will vanish.
I have only one answer: Economies of Scale. No matter how good you claim AMD's manufacturing capabilities, Intel will still have the upper hand because the quantity of their products makes up for it.
Now that NGMA has been released, maybe we should all just be happy at the good things to come instead of bashing each other.
9-inch, you don't want to be called a BS Accelerator right?
Next News in the Inquirer:
Announcing the BS Accelerator co-processor for AMD platforms codename 9-inch.
Just kidding
| Quote :
|
Hahaha.... man... if only professors used that explanation, college would have been much easier.... or atleast the basic concepts.
| Quote : this website you linked up to mentions 1t as a metric performance of transistors,it mentios it as a key guideline.and you say amds trensistors are slower.
|
Do you mean 1/t (with t being the gate delay)?
| Quote : but as shrinkage increases leakage follows in a certain percent due to the shrinkage,so oxidation becomes a factor?
|
You are confusing surface area and gate oxide thickenss shrinking the lateral dimension does not increase leakage, shrinking the thickness does due to quantum tunnelling.
Jack
Yeah, we need to amke sure we're talking about shrinking the node or shrinking the oxide thickness. The oxide thickness usually does not change that much, especially between processes. The node sizes are always trying to shrink. But if i remember correctly there are some other things in a die shrink that due increase leakage, but generally there is less leakage in a shrink.
| Quote : thats gotta be painful for amd |
Not necessarily; if after Conroe Intel will still sitting on their behind they'll go nowhere further. They've had this superior technology 4 years before AMD but made no superior products. In a programmed society like the one we live in, good will & hard work still prove to be the driving forces.
| Quote : but as shrinkage increases leakage follows in a certain percent due to the shrinkage,so oxidation becomes a factor?
|
You are confusing surface area and gate oxide thickenss shrinking the lateral dimension does not increase leakage, shrinking the thickness does due to quantum tunnelling.
Jack
Yeah, we need to amke sure we're talking about shrinking the node or shrinking the oxide thickness. The oxide thickness usually does not change that much, especially between processes. The node sizes are always trying to shrink. But if i remember correctly there are some other things in a die shrink that due increase leakage, but generally there is less leakage in a shrink.
This is not quite correct. The 90nm to 65 nm transistion was the first time in the history of the industry that Intel did not scale the oxide thickness. Link: http://www.semiconductor.com/resou [...] mber=13507
You can see the progression of oxide thickness scaling at 130, 90 and 65 nm nodes in my go-to summary table here:
http://www.realworldtech.com/page. [...] 01504&p=14
At 130 nm they were at 1.5 nm, at 90 nm they went to 1.2 nm (doesn't sound like much but it is actually a 20% scaling. At 180 nm I believe I recall Intel was at 2.0 nm I don't have a quick link for that sorry.
One thing to note from this table, is the Lg (gate length), Intel quotes and normally hits or exceeds the Lg, AMD quotes and normally misses their Lg at nominal conditions (again, a paper of I often link).
http://www.chipworks.com/resources [...] pworks.pdf
Jack
Ah, my bad, i thought Intel has been at the current thickness for a while. Thats why i am not a process expert.
Please mind
You are about to answer a thread that has been inactive for more than 6 months.
If you still wish to proceed, please ensure that your posting is original and does not duplicate or overlap any prior responses to this thread.
