Intel announces Tri-gate "3-D" transistors for upcoming Ivy Bridge based processors

[Nemesis 1]

I was wondering where Mike Magee was going to pop up next.

Man me and you have gone around on this. Its not on 32nm as intel thought it would be but its alive .




New Transistors for 22 Nanometer Chips Have An Unprecedented Combination of Power Savings and Performance Gains

NEWS HIGHLIGHTS

Intel announces a major technical breakthrough and historic innovation in microprocessors: the world’s first 3-D transistors, called Tri-Gate, in a production technology.
The transition to 3-D Tri-Gate transistors sustains the pace of technology advancement, fueling Moore’s Law for years to come.
An unprecedented combination of performance improvement and power reduction to enable new innovations across a range of future 22nm-based devices from the smallest handhelds to powerful cloud-based servers.
Intel demonstrates a 22nm microprocessor – codenamed “Ivy Bridge” – that will be the first high-volume chip to use 3-D Tri-Gate transistors.

AMD is up a creek

 

[TuxDave]

Intel Reinvents Transistors Using New 3-D Structure

http://finance.yahoo.com/news/Intel-Reinvents-Transistors-bw-4288465347.html?x=0&.v=1

World’s First Demonstration of 22nm 3-D Tri-Gate Transistors

The 3-D Tri-Gate transistor will be implemented in the company’s upcoming manufacturing process, called the 22nm node, in reference to the size of individual transistor features. More than 6 million 22nm Tri-Gate transistors could fit in the period at the end of this sentence.

Today, Intel demonstrated the world’s first 22nm microprocessor, codenamed “Ivy Bridge,” working in a laptop, server and desktop computer. Ivy Bridge-based Intel® Core™ family processors will be the first high-volume chips to use 3-D Tri-Gate transistors. Ivy Bridge is slated for high-volume production readiness by the end of this year.

It's good stuff.

 

[busydude]

Intel Reinvents Transistors Using New 3-D Structure

http://finance.yahoo.com/news/Intel-Reinvents-Transistors-bw-4288465347.html?x=0&.v=1

Thanks, updated OP and the title.

 

[formulav8]

interesting

 

[drizek]

This 3D fad is getting old...

 

[dma0991]

Interesting to see that Ivy Bridge will not be a die shrink only.

 

[Majic 7]

Now we can look forward to months of wait for Ivy Bridge posts. Turnabout is fair play. Does get boring, though. And of course the will my motherboard support it.

 

[piesquared]

this is intel's biggest announcement of 2011? lol wow ok, so damage control then. looks good for Bulldozer and Llano.

 

[ender11122]

Now we can look forward to months of wait for Ivy Bridge posts. Turnabout is fair play. Does get boring, though. And of course the will my motherboard support it.

Not a chance in hell.

 

[Nemesis 1]

http://www.youtube.com/watch?v=SB706hhCDZc&feature=player_embedded

 

[Nemesis 1]

this is intel's biggest announcement of 2011? lol wow ok, so damage control then. looks good for Bulldozer and Llano.

Dream on!

 

[Majic 7]

Not a chance in hell.

Wasn't expecting it to. Just expecting the question.

 

[aphelion02]

this is intel's biggest announcement of 2011? lol wow ok, so damage control then. looks good for Bulldozer and Llano.

Why are you so dismissive? This is pretty big news.

 

[Nemesis 1]

this is intel's biggest announcement of 2011? lol wow ok, so damage control then. looks good for Bulldozer and Llano.

Damage control . LOL . Ya there will be damage alright to the highend SB 2011. who would be dumb enough to buy these when IVY is following closely behind its launch with its own

 

[Nemesis 1]

Why are you so dismissive? This is pretty big news.

It is hugh news . I wouldn't be surprized if BD is finfet. IBM has been working on the process along time and some memory already uses it.

 

[piesquared]

1. not only that, but the 22nm schedule seems to have slipped from what tortolini has been telling analysts.
2. let's see some closeup shots of the rendering in that game demo. why did they choose a dx9 game?
3. clear sailing for bulldozer and llano.

Stop trolling
-ViRGE

 

[Soleron]

Intel gets their news from Semiaccurate

http://semiaccurate.com/2011/04/07/intel-goes-finfet-on-22nm-somewhat/

A month ago.

 

[Nemesis 1]

We have all read things in hardware forums that is just retarded. Here is a quote from another site this guys is completely ignorant and shouldn't post in hardware forums.


Oh didn't knew intel already is using trigates in manufacturing... i knew they where researching it... But on the other hand, that tech is already nearly a decade old..


That tech is 10 years old he states . Who fabbed it . Its been in reserach for better than 10 years. RESEARCH. IVy is going to be a monster. With the newIGP on ivy and the clock increase I expect on the IGP to be right at 2ghz or higher. DX11 and cpu clocks should go up at least 20+%

 

[Nemesis 1]

Intel gets their news from Semiaccurate

http://semiaccurate.com/2011/04/07/intel-goes-finfet-on-22nm-somewhat/

A month ago.

Bad info is bad info period . FinFet and trigate are not =. So if he got that wrong its likely he got other things wrong . Like cache only using 3D transitors

 

[Soleron]

Bad info is bad info period . FinFet and trigate are not =. So if he got that wrong its likely he got other things wrong . Like cache only using 3D transitors

BBC article says they are the same thing. I think it's a marketing term difference, Intel wants to look different by calling it "3D" but it's still fins.

http://www.bbc.co.uk/news/technology-13283882

Charlie just posted a correction.

http://semiaccurate.com/2011/05/04/like-semiaccurate-said-intel-goes-finfet3d-on-22nm/

"It also sounds like we were wrong about it being cache only as well."

There is a need for both kind of sites: those that post months early and get some stuff right like S|A, and sites that stick to the NDA like Anandtech.

 

[Majic 7]

BBC article says they are the same thing. I think it's a marketing term difference, Intel wants to look different by calling it "3D" but it's still fins.

http://www.bbc.co.uk/news/technology-13283882

Charlie just posted a correction.

http://semiaccurate.com/2011/05/04/like-semiaccurate-said-intel-goes-finfet3d-on-22nm/

"It also sounds like we were wrong about it being cache only as well."

According to Intel Finfet and tri-gate are different.http://www.intel.com/technology/silicon/tri-gate.htm?iid=tech_silicon_pipeline+body_transistors

 

[Soleron]

According to Intel Finfet and tri-gate are different.http://www.intel.com/technology/silicon/tri-gate.htm?iid=tech_silicon_pipeline+body_transistors

Thanks. I don't know enough to comment, then.

 

[Majic 7]

Thanks. I don't know enough to comment, then.

Me neither, just saw the link on another forum.

 

[pm]

Although it's confusing because literature and the media often use FinFet to mean any non-planar device, and frequently use the terms interchangeably, the original FinFET design from UC Berkeley is a non-planar ("3D") dual-gate transistor. Intel's tri-gate design is a non-planar tri-gate transistor.

The paper that I consider to be the one that named the "finFET" is this one:
"Sub-50nm P-channel FinFET" Quejue Huang et.al, IEEE Transactions on Electron Devices, Vol. 48, No.5, May 2001.
In the abstract: "High-performance PMOSFETs with sub-50-nm gate length are reported. A self-aligned double-gate MOSFET structure (FinFET) is used to suppress the short-channel effects."

If you Google it, you can read the paper. Like I said, I find it confusing too - first because a finFET looks like a tri-gate when you look at the electron microscope photos, and second because people seem to use the term "finFET" to mean any non-planar multigate transistor. To me, when I hear the term "finFET" I think of the paper from 10 years ago and then the subsequent dual-gate papers from TSMC and this is a distinctly different design from Intel's tri-gate.

* Not a spokesperson for Intel Corp. *

 

[Black96ws6]

So hypothetical future:

Present Day: Sandy Bridge 2500k chips = best bang for the buck

June 2011: Bulldozer unveiled, AMD re-takes best bang for the buck crown with chips slightly cheaper than 2500k SB and on performance with 2600k SB. Bulldozer also re-takes performance crown with their high end BD chip (but at a price).

2nd Half 2011: Sandy Bridge-E unveiled. Performance crown back to Intel or about even with BD (but at a price).

1Q 2012: Ivy Bridge unveiled. 22nm process and 3D transistors = ~37% increase in performance, Intel releases mainstream versions at same price points as SB, AMD no longer best bang for buck. Higher end IB chips also unveiled, performance crown squarely back to Intel.

Remainder of 2012: AMD's answer????