Intel Previews 32nm Itanium "Poulson" Processor

This week, at ISSCC (International Solid-State Circuits Conference) Intel unveiled its next-generation Itanium processor, codenamed Poulson. This new octal-core processor is easily the most significant update to Itanium Intel has ever built and could upset the current balance of power at the highest-end of the server / mainframe market. It may also be the Itanium that fully redeems the brand name and sheds the last vestiges of negativity that have dogged the chip since it launched ten years ago…

Intel Previews 32nm Itanium "Poulson" Processor

Via:  HotHardware
kid007 3 years ago

32nm = WOW! I wonder how small will they get 10 years from now? anyone wanna guess?

coolice 3 years ago

10nm if not smaller... but i wouldnt be surprised if enterprise wide quantum-light processors hit the market or are just about to hit the market.... Unless 2012 dooms day, or a post apocalyptic-zombie world, or google-skynet-watson controlled earth where the humans are batteries that power the robots after we blacken the sky etc

acarzt 3 years ago

20 something nm is next. I think 22?

They will probably switch to fiber and the manufacturing process will get bigger again, and then start shrinking from there all over again.

And then a switch over to Quantum computers.

Computers are going to start changing drastically. We will all have to relearn a lot of thing :-P

realneil 3 years ago

As long as I can play Spider Solitaire,..........

coolice 3 years ago

[quote]As long as I can play Spider Solitaire,..........[/quote]

and Free Cell! i'm with ya on this one haha.

rapid1 3 years ago

Hey coolice that "google-skynet-watson" scenario might mess up Apples plan to take it over (the world).

rapid1 3 years ago

Wow those forecasters must have been hanging with someone and drunk or otherwise inebriated when they wrote that forecast, that was of by a country mile +10!

caspencer 3 years ago

Intel is actually building a 14nm fab facility, supposed to be done in 2013:

Joel H 3 years ago

I recently went back and read a thread on CPU predictions from tech forum members in the year 2000. An astonishingly large number of people thought we'd seriously be using things like quantum or light-based computers.

The fact is, scientists in 2010 are still thrilled when someone demonstrates a way to use 5-10 atoms to hold some bit of data. At the same time, Intel's current version of Lights Peak (the supposed optical interface) is currently using copper wire.


I'm not knocking LP, but if even Intel hasn't figured out how to deploy the optical interface is a cost-effective manner, we're likely 20 years or more away from the sorts of things most techies like to predict are coming "just down the road."  Furthermore, I don't think we'll see a real push into such areas until conventional manufacturing methods simply run out of room.

Post a Comment
or Register to comment