Intel Plans A Common Socket For Xeon, Itanium 157
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?"
planning != doing (Score:5, Insightful)
A polite way of keeping Itanium (Score:5, Insightful)
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:planning != doing (Score:4, Insightful)
Re:A polite way of keeping Itanium (Score:5, Insightful)
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 (Score:5, Insightful)
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:Common socket, gmpf! (Score:4, Insightful)
I remember not so many years ago when intel and AMD processors really did use the same socket... I wish history would start repeating itself real soon, I'm sick of different sockets.
Re:intel still wont get anything out of this (Score:4, Insightful)
I don't think that AMD will ever beat out Intel completely, but if they keep making the right moves, they will be able to force Intel to radically change how it does business.
Intel has traditionally enjoyed very, very healthy profit margins. AMD, on the other hand, has traditionally lost money - it's only been in the last quarter or two that they've even posted a profit. To bring a company from the times of the K6 and K6-2 to having an incredible offering like the Opteron, while having to be so cautious with money, shows that AMD can be resourceful, and compete even when it's an uphill battle.
Intel, on the other hand, has enough infrastructure, capital, partners, investment, and diversification that it will never be beat out entirely. However, as AMD starts to make more and more profits (by eating into Intel's most lucrative market!), they'll (theoretically) be able to step up the competition and give Intel an even stronger opponent. If they do that, Intel will have to start being much more frugal and resourceful.
Up until a few years ago, the AMD-Intel battle was pretty one-sided. Now, things are going to be a lot more fun to watch.
steve
Re:Sounds like they're admitting defeat. (Score:5, Insightful)
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
Re:A polite way of keeping Itanium (Score:5, Insightful)
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.
It's that or no more motherboards (Score:4, Insightful)
Actually, the real question is how much longer Microsoft will support the Itanium. Remember when NT supported MIPS, Alpha, PowerPC, and x86? Actually, Microsoft only supports the Itanium in a very limited way. The OS, and a few server side apps, run native. But that's it. The desktop apps all run in emulation, as far as I can find out.
Re:friendly customer service my ass (Score:3, Insightful)
The problem has been that in the high-dollar area (Xeons), they've been sticking the consumer with slower busses than the desktop line. Until recently, when there was no other option in the price range, people just sucked it up and dealt with it. Now that there is good competition, that's going to have to change. This is probably a way for them to get some fast busses into their high-dollar (Xeon and Itanium) lines without it looking like they could have done it all along.
steve
Interesting approach.... (Score:5, Insightful)
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:Why bother... (Score:5, Insightful)
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:A polite way of keeping Itanium (Score:3, Insightful)
Whats stopping them putting 2 BIOSes onto the motherboard and then just switching between them depending which CPU you have in the box?
Re:Common Sockets for differnt architectures? (Score:5, Insightful)
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 [slashdot.org], 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?)
Re:Common socket, gmpf! (Score:5, Insightful)
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.
Actually.... (Score:3, Insightful)
If you want to support innovation remember it was a fairly gutsy thing to do dropping the legacy x86 hardware support from it. The cost performance-wise of maintaining support has impacted on every processor intel's built since early Pentiums.
Re:planning != doing (Score:2, Insightful)
AMD: We're still going to be trying to get more than 20% market share.
Intel: Um...trying to get further into the server market, and keeping ahead of AMD?
Win: AMD.
But if you mean in terms of sticking to their own previously announced plans for the next year, no. AMD's been playing the socket shuffle for a couple years now with sockets 754, 940, and 939. They've also decided to introduce 32-bit-only bargain CPUs (codenamed Sempron), after announcing that all their chips after the AthlonXP/MP would use x86-64. All that Intel's done in the same period is drop the intended successor to Prescott (called Tejas), and switch their desktop roadmaps to the Pentium M chips.
Win: Intel.
In an industry like this, it's not exactly easy to make predictions more than a couple years in advance and expect them to be entirely accurate.
Xeon ~ P4 + IA-64 = danger (Score:3, Insightful)
For me this looks like the last attempt to screw things up for AMD and x86-64 architecture in high-end workstations / servers.
Let's assume that you are a pretty big boss in a normal company. Your company has decided to upgrade their High-End computers. You have basically two options:
Either you recommend 100% Intel Hardware that runs current 32-bit stuff fine and is ready to be upgraded or is even compatible with IA-64 stuff. x86-64 compliance is hardly mentioned in specs. If there even is such compatibility. 64-bit thing is important for future. Not probably yet, but in future. (Xeon/Itanium mixed platform)
or
"50% Intel compatible" AMD platform which runs current 32-bit stuff very well, but the x86-64 instruction set is non-compatible with Intels High-End IA-64 infrastructure. So only partial Intel compatibility, sounds bad... Thats like 50% Intel incompatible... (A64 / Opteron platform)
You are really going to have hard time convincing yourself and your even bigger bosses, that Non-Intel compatibility is good for your business. Mainly because Intel compatibility has been THE most important thing for last 15 years or so...
Then Intel just starts it's advertising/lobbying campaings and hopes that this is enough to turn the tide for them...
ps. if there are typos just blame the damn internet-cafe's german kezboard... somebody has swapped mz Z and Y.
OT: Color Change (Score:3, Insightful)
Re:Itanium is an "Edsel" (Score:3, Insightful)
That all said - support is king. If you can't 1. get the solution desired in place and 2. support it for 10 or 15 years (or more) you aren't going to get to Step 3: Profit.
-Most- Linux providers aren't there yet, and will never get there. There really is too much infrastructure involved to support multi-billion dollar long term contracts for RedHat or Novell to pull off effectively. IBM, HP - these companies (and IBM -especially-) have built -huge- support divisions into their companies, and it's what has allowed them to make it through all of the recent economic problems.
In other news... (Score:3, Insightful)
a) A unified Xeon/Itanium socket for Tukwila has been on Intel's official roadmap for at least a year now, and obviously has been in the works for much longer. This is not news and indeed Intel has been hyping the hell out of it for some time now.
b) The point of this is not to somehow "retire" Itanium (what, by giving Itanium customers the option to "upgrade" to Xeon??) but to drive it into the mainstream by dramatically lowering platform costs. Intel claims Itanium will get 2x the performance on the same socket as Xeon in 2007. Obviously this will depend on the workload, but with Tukwila going against an dual-core MPU based on the ancient NetBurst core, it's not unlikely either. Of course the reason to stay x86 will be for binary compatability, but in many if not most server situations IA-32 EL on Tukwila should provide better x86 performance than the top end Xeon. The point of a unified socket is to phase out Xeon, not Itanium.
Meanwhile, Slashdot has managed to miss today's announcement [yahoo.com] that the likely future fastest supercomputer in the world [realworldtech.com] will be running Linux. Seems like a slam dunk, right? Linux running the fastest single-image computer in the world? What's the catch? It's running on Itanium, of course.
Must be tough trying to come up with a negative spin on that one. From the but-if-it-was-opteron-it-would-cost-$100,000-less dept., perhaps??
platform (Score:3, Insightful)
we have a pair of them and it works wonders. the system is very good design that the entire system is very easy to service (swap everything from pci boards, memory boards, processors, management, etc.) and of course good in the reliability and stability side.
the primary feature is reliability, manageability, and servicability. speed is secondary in these systems.
for opterons, their processors are good but i am still doubting on the entire platform (but it is slowly fading away.) i coudn't just buy a server because it is fast without much consideration into servicability, stability and manageability of the system.
by combining the xeon and itanium2 product lines, they will be able to increase these factors more. the resources will now be bigger to validate in the two configurations and design will be much simplified. for example, if an oem manufacturer creates an fc hba, testing will be much faster and better. there may be a separate software code base for the xeon and itanium2. i have seen lots of good plans from intel (though some are still plans but some of them are maturing and i can't say them due to nda.)
in operating a datacenter, this will have huge benefits. if we will get spares, we will only get field replacable units (fru) for the server and we can practically interchange components with our system. this is cost saving but the greater advantage is allowing us to quickly place a server only due to faulty components as they are standardized. in the future, we can have a same server board and all components and spare cpus. aside from hardware efficiency, it will be better for management. the management system will not have to deal with different type of systems. faster fault detection and resolution without much overhead costs of purchasing all the enterprise products. and when deploying new applications, you can have your own internal validation for hardware and software knowing that you will have the same configuration throughout.
by doing this, intel stands to create better platforms realizing from the strengths of both processor architecture. hopefully they will be able to deliver it and even better as planned.
john
and to amd's demise right now, Microsoft just delayed their release of Windows Server 2003 and Windows XP for x86-64 to mid 2005.
craig barett also created a memo on improving on engineering efficiencies in intel. he doesn't like what's happening right now.