IBM Says Alliance Set for 28nm

Status
Not open for further replies.
Well, Tom's bought the typical IBM bait and switch... "s stated by IBM, the low-power 28nm technology platform can provide a 40 percent performance improvement when compared to the larger 45nm chip, and more than 20 percent reduction in power"

Notice they are comparing 28nm to 45nm... but no mention of 32nm which is also "supposed" to be ~ 40% better. The 28nm is just about shrinking optically - you'll notice no performance comparison BETWEEN 32nm and 28nm, because some folks might say why bother when you consider the cost of masks and qualification time. IBM pulled this same crap on 65nm when they were comparing the process to unstrained devices claiming huge increases and yet when it was compared to 90nm... no so much....

If folks do the products at 32nm, it will be a hill to climb to convince them to move to 28nm.... Perhaps IBM is trying to convince folks to jump to 28nm from 45nm, but then why bother with 32nm? Again when IBM talks about 32nm to 28nm they talk about it being "easy", but no mention of the performance jump (which will be minimal) in that case. IBM doesn't understand that if you are not making high volumes of parts, it really doesn't make economic sense to do a migration of a half node.
 
[citation][nom]woolovertheeyes[/nom]Well, Tom's bought the typical IBM bait and switch... "s stated by IBM, the low-power 28nm technology platform can provide a 40 percent performance improvement when compared to the larger 45nm chip, and more than 20 percent reduction in power"Notice they are comparing 28nm to 45nm... but no mention of 32nm which is also "supposed" to be ~ 40% better. The 28nm is just about shrinking optically - you'll notice no performance comparison BETWEEN 32nm and 28nm, because some folks might say why bother when you consider the cost of masks and qualification time. IBM pulled this same crap on 65nm when they were comparing the process to unstrained devices claiming huge increases and yet when it was compared to 90nm... no so much....If folks do the products at 32nm, it will be a hill to climb to convince them to move to 28nm.... Perhaps IBM is trying to convince folks to jump to 28nm from 45nm, but then why bother with 32nm? Again when IBM talks about 32nm to 28nm they talk about it being "easy", but no mention of the performance jump (which will be minimal) in that case. IBM doesn't understand that if you are not making high volumes of parts, it really doesn't make economic sense to do a migration of a half node.[/citation]


Well put my friend...very well put.
 
Half node between 32nn and 22nm. while it mostly isn't used for increased performance the lower power requirements will be great for mobile devices. AMD's graphics are designed around the half node so good news for them and the ATI team.
With the multi core race this could be used as a half increase in cores from 4 to 6. Generally tho it takes full node just for increase performance on the CPU side so maybe just wishful thinking.
 
Could it be because we're approaching the theoretical minumum, that the half-nodes are seeming a bit smaller than they used to? If this were the difference of 3200nm to 2800nm, we'd be high-fiving IBM for shaving a whopping 400nm off the transistor size.
 
Looks like a scheme from IBM to make people buy their products. They are mainly targeting the computer noobs in the world.

Excuse this noob of a question but what is nm (nanometer?)? and what's a node?
 
[citation][nom]Upendra09[/nom]Looks like a scheme from IBM to make people buy their products. They are mainly targeting the computer noobs in the world. Excuse this noob of a question but what is nm (nanometer?)? and what's a node?[/citation]
I hope you're kidding...
 
[citation][nom]elbert[/nom]Half node between 32nn and 22nm. while it mostly isn't used for increased performance the lower power requirements will be great for mobile devices. AMD's graphics are designed around the half node so good news for them and the ATI team. With the multi core race this could be used as a half increase in cores from 4 to 6. Generally tho it takes full node just for increase performance on the CPU side so maybe just wishful thinking.[/citation]
Dont forget its also cheaper materials wise as more chips can be made per wafer... suppose there is the higher failure rate...
 
mr.cHeesle,

i am not hjoking, I aknowledge the fact that it is a pretty simple question but it is one of the most often things i hear and i just want to know. I do know a good enough amount on computers but not on the engineering part of it. So please answer the question if u have an answer.
 
[citation][nom]Upendra09[/nom]Looks like a scheme from IBM to make people buy their products. They are mainly targeting the computer noobs in the world. Excuse this noob of a question but what is nm (nanometer?)? and what's a node?[/citation]
if your being serious a nm is a nanomater, a one time ten to the power of minus nine of a full meter (i.e. x10^-9 or /10^9 of a metre also one billionth of a metre) if you only know imperial suck...

I know what a node is, its a region where there is no change in potential (i.e. the stationary points on a wave and the like), but I dont know how it fits in with the term half-nopde in circuttry)

 
[citation][nom]Upendra09[/nom]mr.cHeesle,i am not hjoking, I aknowledge the fact that it is a pretty simple question but it is one of the most often things i hear and i just want to know. I do know a good enough amount on computers but not on the engineering part of it. So please answer the question if u have an answer.[/citation]
I know it's a full week later, but I had to respond.

Upendra, you're connected to the greatest resource and venue for the sharing of information in the history of mankind. Content exists on a multitude of topics, most of it free of charge; sites including Wikipedia.org.

The internet is a wonderful resource. Make use of it!
 
Status
Not open for further replies.