Intel Plans A Common Socket For Xeon, Itanium

stonedonkey writes "According to EE Times, Intel is planning a common system platform for the Xeon and Itanium by 2007, "creating a unified 64-bit motherboard with a new, one-size-fits-all socket." Intel's Jason Waxman says , "It has been something that customers have been asking us for for a while now...the reseller [currently] has to have an inventory of both boxes on hand." Feeling the heat from the competition, cutting losses, or just friendly customer service?"

Comments

Not exactly new news...

[halo1982]

The Inquirer reported on something just like this nearly a year ago. Of course this is actually confirmed with a date, but the Inq still has a bit more information.

Common socket, gmpf!

[c0wan]

You still can't stick an AMD in there.

Re:Common socket, gmpf!

[NoodleSlayer]

If I remember correctly the reason why the Athlon and P4 have different sockets is because the two use radically different FSB technology, and between the Athlon 64 and P4 it would be nearly impossible.

Moving to their own socket was perhaps one of the best decisions AMD made for the Athlon, it allowed them to create their own technology instead of having to follow Intel's lead as far as motherboard design goes.

Of course to top it all off Intel claims that all of its bus technology is "proprietary", this is why nVidia hasn't made an nForce chipset for the P4 yet. AMD on the other hand has a much more open policy and actively encourages 3rd party motherboard and chipset makers. A policy which has worked very well for AMD to date.

Re:Common socket, gmpf!

[dpilot]

(sorry to add a serious comment to a joke)

The sockets diverged back in the days of Slot1. Intel didn't want to compete on the socket level, like back in the Socket7 days, so they tied things up in patents and such. That's what drove AMD to the SlotA, which they got from Alpha. Theoretically you could have motherboards into which you could put either a K7 or an Alpha, by changing the BIOS.

Actually, that same trick seems to be what Intel is trying to pull, here. But what seems and what is may be two different things. With today's market positioning, Xeon and Itanium are sold into different markets, and those markets would drive radically different types of boards.

So we have four possibilities:
1: Intel is trying to enable Itanium to creep downward into the Xeon market.
2: Intel is trying to enable Xeon to creep upward into the Itanium market.
3: Intel is confused, and trying to hedge their bets.
4: Beancounter have gained some ascendancy over the marketdroids, and have gotten fed up with the costs of 'socket differentiation.'

planning != doing

[chrispyman]

While it's nice to know that they're planning on doing something that will take away a few more headaches, whose to say that this will ever get out the door and to the consumers?

Re:planning != doing

[Anonymous Coward]

This is exactly why I support AMD instead of Intel on all of my purchases. Atleast AMD has a good idea of what they are going to be doing a few years from now. It seems like Intel doesn't and they change their minds too much, against the wishes of their customers.

A polite way of keeping Itanium

[Linus Sixpack]

I imagine Intel wants a polite way to keep the Itanium on the books for very special applications and to save face. Zeon will, at least in the near future, be the processor of choice and a common socket will keep it from eclipsing the Itanic.

There might even be a chance that the market will change enough to want the Itanic, but not if they have to maintain specialized hardware for a currently very niche market.

LS

Re:A polite way of keeping Itanium

[Anonymous Coward]

Disagree -- this helps Itanium much more than it helps Xeon.

Most current Itanium use is for larger systems, which is already entirely specialized hardware. Common mobos allow Itanium tomove "down market" into small servers and workstations by opening the whole range of mainstream chipsets at no additional cost.

I'm assuming these systems will use Intel's new platform-independant firmware.

Re:A polite way of keeping Itanium

[Jason Earl]

Exactly. This is all about making it easier for Intel to sell Itanium servers. Intel doesn't want to go through the expense of designing and QAing separate Itanium motherboards for the five or six people that actually want Itanium. If the Xeon and Itanium share the same motherboard then OEMs can stock one motherboard and "upgrade" customers to Itanium if that's what they want.

If AMD wasn't serious competition with their AMD64 chips then Intel wouldn't even release 64 bit Xeons, but as things stand they don't have much of a choice.

Re:A polite way of keeping Itanium

[sirsnork]

Both Xeon and Itanium suffer the same woes, this gives them a good chance to correct both at the same time, although it will take a massive engineering effort on their part.

Intel are going to have to drop their shared bus architecture and move to a point to point system like AMD or memory performance will suffer greatly, otherwise you can only run your memory at your FSB speed and adding more procs just means they all get less mem bandwidth. This is going to become more pronounced with the introduction of Dual Core CPU's. Also since Xeons are build on the core of the desktop CPU's they will also have to change to follow suit (assuming Intel are going to move to a P2P architecture). At that time one would assume we would be talking about the P5 and one would also have to assume Intel would move the memory controllers onto the CPU's like AMD have.

That is quite a lot of work for Intel to do when they are also talking about dual cores. It's a lot of tech to get right all at the same time, especially given the delays involved with the Nocona launch and the associated motherboards. Itwould give them some rather nice options though, rather than using Hypertransport they could use PCI-E to join CPU's and have controllers on the CPU like the Opterons. Also because the CPU's are joined with a serial bus you can move them onto riser cards and make the most of the real estate in the chassis meaning you should be able to pack more CPU's in a smaller space.

The thing here though is that at some level the CPU's need to talk the same language, at least for initialisation at boot, although we are presuambly talking about 2 completly new cores so ever that is within the realm of possibility.

missing poll option!

[J_Omega]

Feeling the heat from the competition, cutting losses, or just friendly customer service?

d) all of the above.

It's about time...

[GFLPraxis]

At the rate Intel is keeping pace, by the time they get a 64-bit processor out with a unified socket, we'll be running Athlon 128's and dual dual core PowerMac G6's (also 128-bit)...sigh...

Get with the pace, Intel, and get a consumer 64-bit processor out! That way we get your P4's for cheap :D

Sounds like they're admitting defeat.

[Anonymous Coward]

Something like this adds to the complexity of the system board. The odds are good that you'd only want to do this if the sales of one type of system were so poor, you'd prefer the increased complexity so you can gain increased economies of scale.

Eg: how does a system bootstrap itself from power on to the point where the OS is loaded? That's the job of the code in the BIOS (or OpenBoot, or equivalent). Do you believe that x86-32 BIOS code is going to work to get an Itanium CPU loading the OS? The only way you'll get a generic BIOS to work is if there's an opcode that will allow a jump to a given address in one CPU, whilst just incrementing the instruction pointer on the other.

Look at Athlon. The Athlon bus was designed so that you could, in theory, plug an Alpha into an Athlon board. How many boards were made available to do this? Zip (that I know of, anyway.)

Intel are desperate to increase sales of Itanic (typo deliberate ;) -- they're hoping that by doing this, the economies of scale will make Itanic more appealing. Sorry, Intel; I'd say that this is the beginning of the end. Your fortunes were built on backwards compatibility, and it looks like that's now the millstone around your neck, dragging Itanium down.

Re:Sounds like they're admitting defeat.

[NerveGas]

It's not admitting defeat, it's getting rid of something that hasn't made much sense.

The Xeon line has traditionally been both the more lucrative and the more "stable" line, on the idea that businesses wanted long-term stability. When you bought a Xeon motherboard, you knew that it would be compatible with some of the upcoming Xeons in FSB and slot, and with a VRM module, even for different voltages.

A very large side-effect is that the Xeon line was tied to slower FSB/memory rates, and a lot more expensive. In reality, most people don't upgrade their Xeon chips - they move to a new architecture (P2->P3->P4, etc.)

Looking at the P2/P3 Xeons, it was long after the shift to a 133MHz FSB when the Xeons played catch-up. And it's just now that the P4 Xeons are getting away from the 533MHz FSB.

So, they're taking their most expensive, most lucrative processers, and hindering the performance. While it worked while Intel was the 800-pound gorilla (and you had no other choice in 2-way, let alone 4-way machines), that's no longer the case. There's competition in the market - good competition. It was a real kick in the pants to shell out $5000 to $15,000 on Xeon systems that had a slower FSB than the $500 desktop counterparts!

So, now, they're going to have to do the sensible thing: Start giving actual performance in exchange for customer money. Rather than have the "high-end bus" and the "low-end" or "mid-range" bus, it makes a lot of sense to just have all of them use one bus design - theoretically, a fast bus.

The Athlon bus was designed so that you could, in theory, plug an Alpha into an Athlon board

I really don't think that was the idea. AMD was looking for a front-side bus design, and Intel's wasn't an option. The Alpha design was available for the right price, and so it was used.

Do you believe that x86-32 BIOS code is going to work to get an Itanium CPU

I believe that Intel has already stated that they want to make some radical changes to the way the BIOS works.

Sorry, Intel; I'd say that this is the beginning of the end.

Unless they're able to really shift direction, I'd agree.

steve

It's still not much better than a stop-gap...

[NerveGas]

With Opterons coming in much less expensive than the Itaniums, moving to a common socket with the Xeons isn't going to help much.

On the other hand, with Opterons offering far better scalability and performance than Xeons, moving to a common socket with Itaniums isn't going to help out much.

Even on 2-way machines, Opterons show much better scalability than Xeons. As the number of CPUs increase, the Opteron architecture (when coupled with a supporting OS) allows it to shine more and more. With 8-way Opterons coming out fairly soon, Intel needs to come up with something fast - they're losing one of their most lucrative markets to AMD.

steve

The beginning of the end for Itanium

[shizzle]

I think this is a sign of Intel cutting its losses... this will certainly save money, but at the cost of being able to differentiate Itanium platforms from Xeon platforms. One of the real distinctions between a high-end platform and a run-of-the-mill machine is memory bandwidth; if both types of chips plug into the same socket, they're going to have access to the same bandwidth, and Itanium will lose one of its few remaining advantages over Xeon.

Intel would only do this if saving money was more important to them than giving people a credible reason to buy Itaniums instead of Xeons... and I do believe that's the situation at this point in time. Not a good sign for the future of Itanium.

Uhhhhhh...

[Ayanami Rei]

Dude, Intel's got it's own OpenFirmware like doohickey already for the Itanium, it's called EFI.

Anyway, it's really simple. The processors will assert different "core-type" lines, which will control which ROM is memory-mapped to the default EIP pointer at boot time. I mean, Intel processors already signal their allowed clocking speeds by pins right now. Hell, they're probably different in x86-32 and Itanium, so they could both "be active" all the time, jumping to the appropriate memory-mapped physical address (both of which would be mapped at power-on to their own ROMs) and there'd be no need for an option line.

Interesting approach....

[carlmenezes]

AMD has lots of processors that do both 32-bit and 64-bit. Problem is the number of different sockets out there. This means you need to change your motherboard everytime you switch from one socket to another - big expense and something that makes u think a lot about which socket u want.

Intel says...use our 64-bit procs and you won't need to change the socket. This is a marketing thing. I don't think there will be much of a performance difference if the socket is changed. But it makes things more convenient for the customer.

Now, if AMD had done this...they would have grabbed market share. It might still not be too late to unify the sockets...but then it looks like it will be more difficult for AMD given the differences in the processors available across their entire range.

Re:Interesting approach....

[Tim C]

This means you need to change your motherboard everytime you switch from one socket to another - big expense and something that makes u think a lot about which socket u want.

Well, I've had a PC for about 8 years now, and have upgraded a number of times. I don't recall ever keeping the same motherboard when buying a new processor.

True, I imagine that if you buy them regularly, then you may well "reuse" a motherboard once or twice. But personally, by the time I need/can afford to upgrade, a new motherboard is a requirement if I want to obtain a decent performance increase. My old one simply won't support the newer chips.

So, for people who do go to the trouble and expense of incremental upgrades, yes, I can see that not having to buy a new motherboard may be a factor. But I think probably the majority of people leave it long enough between upgrades that keeping the same one simply isn't an option. YM, of course, MV.

Re:Why bother...

[dago]

no, even for that, IBM Power5 CPU got better SpecFP score.

And when you compare with all the factors, it doesn't mind if they're faster than opteron if they cost 4x the price and takes 2x the power (and generate 2x the heat).

Re:Common Sockets for differnt architectures?

[Graelin]

Not that slaping together server hardware is that dificult

It's not as easy as you might think. Maybe the dual proc you set up for the small biz you work for was simple, and it is, but that really doesn't qualify as a server anywhere near the league of an Itanium. Even high-end Dell machines go through a lot of QA to ensure the hardware and it's drivers play nice together. When you're talking about a $100,000+ machine with major support contracts and liabliity concerns - "slaping together server hardware" really isn't.

wouldn't you want boards that are optimized for use with either Xeon OR Itanium?

In this order, I want:
1) Stability
2) Performance

I don't care if the board is optimized for the Apple II. If it runs Itanium with equal or higher stability and equal or higher performance of the next best thing - I'll buy it.

Wouldn't creating compatability on this hardware reduce its performance? Or is this a non-issue?

Well, it's too soon to tell since nobody has one of these boards. And this is only a "plan" so it still may never happen. But I suspect the answer is "not necessarily."

If you can do tricks like this, then I would think there is hope you could create a board like this and not suffer any performance problems. (But I am not a chip designer so who the hell am I?)

Xeon, Itanium?

[circletimessquare]

Aren't those elements with one letter missing?

Xenon, Titanium... hmmm...

What next, the Intel Trontium? the Intel Kryton?