Intel to slip future Xeon E7s, Itaniums into common socket

They may be coming a little bit later than expected, but the next generation of Intel's server processors, code-named "Poulson" and sold under the Itanium 9500 brand, are out. Intel has also finally disclosed its plans to more fully converge the Itanium and Xeon server platforms, giving Itanium a more secure footing in the data …

[Anonymous Coward]

Hardly the sound of an industry leader.

They're only now starting to do what IBM has been doing for several generations now? Well, congratulations.

Maybe it's the cynic in me, but I do get the feeling we'll see but modest wins on the system board front. End-users still won't be able to swap out itanic for x86-64 because the startup code will be all wrong, and anyway next generation there'll be yet another different socket. So it's again a shared itanic/x86-64 socket, how nice, but it'll be different from the last generation, so you have to replace all your kit anyway. Yay, what wonderful savings this sharing brings. Enjoy!

[James 100]

Converging, or shoe-horning?

My inner cynic suggests this is more a case of tweaking the Itanium chips to fit into a Xeon board so Intel don't have to keep cranking out Itanium-specific components any more, just the chips themselves.

The "core-out" design, memory controllers and other bits are essentially borrowed from the Xeon as well: just how much new design effort is Intel putting into Itanium at this point - and how much of that is the result of HP pressure, rather than a real business case for doing so?

On the other hand, will the commonality cut both ways - so it will be easier for HP to put Xeons in their future Integrity kit instead of Itaniums? (The software's already done one architecture switch, from Alpha to Itanium, so another wouldn't be a huge shock.)

[stupid-frakking-handle]

Ivy-Bridge EX

Ivy-Bridge-EX will have PCI-e on the processor, and since that's not something in the current EX processors it means there will definitely be a new socket for Ivy-Bridge EX

[Allison Park]

Where do we get our money back for Tukwila systems?

We were promised

"Moving forward, Intel has said Tukwila will be socket-compatible with the next two generations of Itanium, known as Poulson and Kittson."

We were lied too and 2009 was not that long ago. Why do we find out on Poulson announce day that it is the last of the line in this box when the Oracle doc's said this is the exact case a year ago?

Furious at HP and looking at Pure.

To-da-loo

[tpm]

Re: Where do we get our money back for Tukwila systems?

Well, there is another option. That there was no Sandy Bridge-EX because Ivy Bridge-EX was too close and that Ivy Bridge-EX and Maybe even Haswell-EX will go into what we would have called an Itanium socket.

I am not saying this is the case--Intel has not said. But putting Xeon E7 in an Itanium socket is just as plausible as the reverse.

[Shaun Hunter]

Re: Where do we get our money back for Tukwila systems?

"The sockets for the Tukwila chips, which support the new Poulsons, already had this speed bump designed into them."

RTFA

[Anonymous Coward]

Where are the people complaining that 2x-4x performance increase is impossible?

I am amazed to see people saying it was impossible for Oracle to get ~6x performance boost with their new M4 processor, but not seeing the same people complaining here that it is impossible for Intel to get 2x-4x performance improvement!

Come on, where's the love?

[Phil 4]

Re: Where are the people complaining that 2x-4x performance increase is impossible?

Yeah typical. And no one is questioning why theres not a single *public* benchmark released on Poulson systems and many of the HP Integrity sites are still not showing the Poulson update. Was this rushed to market to make it before end of 2012 so HP/Intel cant be called liars?

[Shaun Hunter]

Finally

These chips are even price in E5 ranges. Now if HP would stop disabling cores and charging huge premiums for hardware and subscription price for their OS's the Itanium could get somewhere.

Does anyone else feel that Mark Hurd's vision for WebOS on every PC should have extended to servers. These are a prime target for proliferation via Linux. Kinda like the ARM ISA is doing now.