GlobalFoundries roadmap slips?

[Mechromancer]

AMD has a lot of headroom on 45nm with Revision C3 and Revision D silicon yet to come. AMD has yet to even implement high-K dielectrics or metal gates on 45nm. As AMD has limited resources, they need to concentrate on getting that tech to us ASAP so 32nm can wait.

Focusing on process tech really is focusing on the wrong metric to measure AMD with too. What matters is are they on track to release their next gen microarchitecture on time. Orochi/Interlagos (Bulldozer family) are 2011 parts so as long as they're not pushed back anymore than they have been, all is well.

[JumpingJack]

You must have heard Otellini's claim last Tuesday then:

"Two years ago Intel introduced the world's first 45 nanometer process, and to date the competition - that is to say AMD - has shipped zero."



http://www.tgdaily.com/content/view/44057/135/
http://www.tgdaily.com/content/view/44061/103/


Regards, Hans

So I went and watched the IDF webcast, Otellini was misquoted.

He referred to high-k metal gate transistors at 45 nm, so he was factually correct.

I still laugh at it though.

[saaya]

AMD has a lot of headroom on 45nm with Revision C3 and Revision D silicon yet to come. AMD has yet to even implement high-K dielectrics or metal gates on 45nm. As AMD has limited resources, they need to concentrate on getting that tech to us ASAP so 32nm can wait.

can it? why is high k so important? more important than 32nm? why?

[ubuntu83]

can it? why is high k so important? more important than 32nm? why?

Yeah SOI is fine. There were doom and gloom stories about SOI before 45nm but after seeing how good it is at 45nm there are high hopes for it at 32nm too.

[ajaidev]

can it? why is high k so important? more important than 32nm? why?

AMD will not implement high K in 45nm, IBM said its not important for 45nm, so did AMD for 45nm but 32nm is suppose to come with High K and IL.

With high k implementation each chip will cost more to make than rite now other than the initial costs. But the wonders like i3 with low lowpwer consumption would be hard to make without high k. 80W fully loaded is insane .... AMD better have a Athlon x3 with low loaded and stand by consumption but most likely it will eat like the x4 does

[terrace215]

You must have heard Otellini's claim last Tuesday then:

"Two years ago Intel introduced the world's first 45 nanometer process, and to date the competition - that is to say AMD - has shipped zero."



http://www.tgdaily.com/content/view/44057/135/
http://www.tgdaily.com/content/view/44061/103/


Regards, Hans

Unfortunately, that's not what Intel said. tgdaily messed it up, by omitting a little detail that makes it true: HK/MG 45nm.

See here:

http://download.intel.com/pressroom/..._FactSheet.pdf

[terrace215]

This is some great doublespeak:

''Our roadmap for 32-nm SOI has not slipped,'' according to a spokesman for the company. ''Yes, the timeframe for introduction has been altered slightly compared to the roadmap we showed you in July, but that is not because of any issues with the technology. The roadmap has simply been adjusted to align with AMD's product needs.

Our roadmap has not slipped! It has been.... altered! and... adjusted!... because AMD doesn't really need a new process until... an altered point in time!

[Sparky]

Unfortunately, that's not what Intel said. tgdaily messed it up, by omitting a little detail that makes it true: HK/MG 45nm.

See here:

http://download.intel.com/pressroom/..._FactSheet.pdf

But the HK/MG isn't that big a deal, not on 45nm anyway.

[terrace215]

But the HK/MG isn't that big a deal, not on 45nm anyway.

A big enough deal that, despite their "me too" announcement a day after Intel, IBM failed to get it into their 45nm production lines... and after failing, labeled it "not necessary".


Remember?

http://www.eetimes.com/showArticle.j...leID=197002148

In a separate announcement, IBM Corp. also tipped its high-k and metal gate development efforts. Working with Advanced Micro Devices, Sony and Toshiba, IBM claims to have found a way to construct a critical part of the transistor with a new material, clearing a path toward chip circuitry that is smaller, faster and more power-efficient than previously possible.

Like Intel, IBM did not disclose what type of hafnium-based material it will use for high-k. IBM did say it has inserted the technology into its semiconductor-manufacturing line in East Fishkill, N.Y. The chip maker will apply the material to integrated circuits with line widths as small as 45 nm starting in 2008.

... not!

[Sparky]

My point simply was it has proven to not be necessary. After all the SOI bashing that was going on here for a while (and yeah 65nm SOI wasn't too great on the Phenom) 45nm proved to be fine without HK-MG.

It just sounds like intel is like "ha ha we got HK-MG 45nm you don't." So?

[Solus Corvus]

A big enough deal that, despite their "me too" announcement a day after Intel, IBM failed to get it into their 45nm production lines... and after failing, labeled it "not necessary".


Remember?

http://www.eetimes.com/showArticle.j...leID=197002148

In a separate announcement, IBM Corp. also tipped its high-k and metal gate development efforts. Working with Advanced Micro Devices, Sony and Toshiba, IBM claims to have found a way to construct a critical part of the transistor with a new material, clearing a path toward chip circuitry that is smaller, faster and more power-efficient than previously possible.

Like Intel, IBM did not disclose what type of hafnium-based material it will use for high-k. IBM did say it has inserted the technology into its semiconductor-manufacturing line in East Fishkill, N.Y. The chip maker will apply the material to integrated circuits with line widths as small as 45 nm starting in 2008.

... not!

Except that SparkyJJO is right. Despite whatever talk IBM and AMD made in the past, the fact is that hk/mg aren't that critical just yet. AMD has just fine transistor performance this round, it's the aging architecture that's holding them back.

Your choice of words is quite telling. How exactly do you know that they failed putting high-k metal gates in? Unless you have access to their testing facilities. To the outside observer failing and choosing not to do something would appear the same. Perhaps they decided that transistor performance would be fine this round without HK/MG and so they put those resources into 32nm.

[informal]

This is some great doublespeak:

''Our roadmap for 32-nm SOI has not slipped,'' according to a spokesman for the company. ''Yes, the timeframe for introduction has been altered slightly compared to the roadmap we showed you in July, but that is not because of any issues with the technology. The roadmap has simply been adjusted to align with AMD's product needs.

Our roadmap has not slipped! It has been.... altered! and... adjusted!... because AMD doesn't really need a new process until... an altered point in time!

Yeah it slipped from end of Q2 to Q3 for risk production,major slippage there..

[terrace215]

Except that SparkyJJO is right. Despite whatever talk IBM and AMD made in the past, the fact is that hk/mg aren't that critical just yet. AMD has just fine transistor performance this round, it's the aging architecture that's holding them back.

Your choice of words is quite telling. How exactly do you know that they failed putting high-k metal gates in? Unless you have access to their testing facilities. To the outside observer failing and choosing not to do something would appear the same. Perhaps they decided that transistor performance would be fine this round without HK/MG and so they put those resources into 32nm.

That's right, I generally assume that when a company promises something in a PR and then doesn't deliver, it is because something went wrong. But you're right, it could simply be that IBM, GloFo and AMD are merely continuing to "choose" to not use / delay / delay things.

So assuming first Bulldozer silicon in Q3 2010, that would mean, what, 12-18 months for a new architecture to be respun/validated before launch (particularly on a new process), so Q3 2011-Q1 2012 launch frame? So it competes with 22nm Ivy Bridge / Haswell ?

[informal]

That's right, I generally assume that when a company promises something in a PR and then doesn't deliver, it is because something went wrong. But you're right, it could simply be that IBM, GloFo and AMD are merely continuing to "choose" to not use / delay / delay things.

So assuming first Bulldozer silicon in Q3 2010, that would mean, what, 12-18 months for a new architecture to be respun/validated before launch (particularly on a new process), so Q3 2011-Q1 2012 launch frame? So it competes with 22nm Ivy Bridge / Haswell ?

2012 for Bulldozer? Yeah if they run into design problems,no if they don't. It has always been Q1/Q2 2011,and now that we see a tape out for 32nm SOI is scheduled for Q1 2010 and risk production is Q3,the Q1 or Q2 2011 for desktop BD parts is very reasonable.

[Solus Corvus]

That's right, I generally assume that when a company promises something in a PR and then doesn't deliver, it is because something went wrong. But you're right, it could simply be that IBM, GloFo and AMD are merely continuing to "choose" to not use / delay / delay things.

So assuming first Bulldozer silicon in Q3 2010, that would mean, what, 12-18 months for a new architecture to be respun/validated before launch (particularly on a new process), so Q3 2011-Q1 2012 launch frame? So it competes with 22nm Ivy Bridge / Haswell ?

IBM talked about 45nm + HKMG products, not necessarily AMD processors. Did AMD ever say that they were including HKMG in 45nm?

You think that bulldozer will be out in 2012? Lol.

[god_43]

http://www.xbitlabs.com/news/cpu/dis...Bulldozer.html

[JumpingJack]

can it? why is high k so important? more important than 32nm? why?

SiO2 can't scale any more, it is as thin as it can go. High-k restores that scaling, and brings PMOS closer to NMOS in performance (that's the metal part actually).

[Vozer]

At first, of course they have to say that they will be able to catch up (or almost catch up) to Intel... and then of course it is postponed...

[RussC]

Its looking more and more to me that BullDozer better be the cats meow, or AMD may really be kaput.....?

RussC

[saaya]

This is some great doublespeak:

''Our roadmap for 32-nm SOI has not slipped,'' according to a spokesman for the company. ''Yes, the timeframe for introduction has been altered slightly compared to the roadmap we showed you in July, but that is not because of any issues with the technology. The roadmap has simply been adjusted to align with AMD's product needs.

Our roadmap has not slipped! It has been.... altered! and... adjusted!... because AMD doesn't really need a new process until... an altered point in time!

sad... just sad... i thought with amd and gf seperate gf could catch up with intel... wasnt that the plan? amd asking gf to delay their new tech... wow... those idi0ts need to get some sense btchsl4pped into them...

[Hans de Vries]

A big enough deal that, despite their "me too" announcement a day after Intel, IBM failed to get it into their 45nm production lines... and after failing, labeled it "not necessary".


Remember?

http://www.eetimes.com/showArticle.j...leID=197002148

In a separate announcement, IBM Corp. also tipped its high-k and metal gate development efforts. Working with Advanced Micro Devices, Sony and Toshiba, IBM claims to have found a way to construct a critical part of the transistor with a new material, clearing a path toward chip circuitry that is smaller, faster and more power-efficient than previously possible.

Like Intel, IBM did not disclose what type of hafnium-based material it will use for high-k. IBM did say it has inserted the technology into its semiconductor-manufacturing line in East Fishkill, N.Y. The chip maker will apply the material to integrated circuits with line widths as small as 45 nm starting in 2008.

... not!

This old story is such a total distortion of what actually occurred....


1) It was the day that that SEMATECH announced the results of its
precompetitive research in HK/metal gates. The results achieved by
a group including cooperating researchers from both Intel, IBM, AMD
and many other SEMATECH member companies.

2) As the date of this announcement was made available to the
member companies of SEMATECH then Intel decided to make the
HK/metal gate aspect of their 45 process public at the same day,
while IBM gave some of their researchers the opportunity to present
their own work.

Intel got all the headlines of course. All the work and contributions of
SEMATECH became completely overwhelmed and ignored....


Regards, Hans

[informal]

The news from Op aren't really news since "risk production"(not tape out) is moved "from end of Q2" time frame to sometime in Q3. That's all.

[Hornet331]

SOI and HKMG adress different things. One takes care of the gate leakages and one of the channel leackage...

With smaller processes the gate leakage overwhelms the channel lakage. SOI was an advantage when the channel lakeage was bigger then the gate leakage at bigger process structure, but now that we have gates that are only a view atom layers thick, gate leakage is the major concern.

[BrowncoatGR]

And they're also not mutually exclusive. GFs 32nm SOI will use HK/MG

[JumpingJack]

And they're also not mutually exclusive. GFs 32nm SOI will use HK/MG

Neither is ultra-low k, a combination of those three can be very potent I would suspect. SOI for junction leakage, high-k for gate leakage, and ULK for low wire delay... will be interesting to see the result.