Print 31 comment(s) - last by Ammohunt.. on Apr 18 at 5:24 PM

Intel's sales forecasts (blue, green) for Itanium were vastly greater than the platform's actual sales (orange).  (Source: Arch Dude)

Itanium's Tukwila architecture landed 3 years late, and is pretty pricey.  (Source: Xbit Labs)

Even as Oracle, Microsoft, and Red Hat abandon support for Itanium, Intel and its partner HP plan to go down with the ship.  (Source: Flickr)
"I'll never let go, (Itanium). I'll never let go."

Little known to most, Intel Corp. (INTC) actively supports a rival architecture to x86.  Built on the Explicitly Parallel Instruction Computing (EPIC) reduced instruction set computing (RISC) architecture, Intel's Itanium CPUs fulfill a variety of niche needs from high-end medical data processing to financial sector applications.  The architecture's inherently parallel design makes a perfect fit for certain kinds of applications and has led to consistent, low-volume sales for Intel.

Lately, however, enthusiasm for the task of supporting Itanium has waned and several software partners have jumped ship, including Oracle Corp. (ORCL).  Most recently, Microsoft Corp. (MSFT) and Red Hat, Inc. (RHT) announced that they would be killing support for Itanium in future versions of their operating systems. 

With no clear OS provider lined up, some have speculated that Intel may preemptively kill Itanium and focus efforts on its Xeon line.

But in the wake of its most recent Xeon launch, Kirk Skaugen, VP and general manager for Intel's Data Center group, commented at a press conference, "Instead of Itanium at the top and Xeon at the bottom of the lineup, we're going to have them side by side."

I. An Inglorious History

Whereas the Xeon line -- the direct server counterpart to Intel's consumer PC chips -- was widely lauded, Itanium was negatively received since its launch.

Intel had originally hoped for Itanium to replace x86 as its parallel-optimized, 64-bit addressable architecture.

But the project just didn't turn out well.  When Intel released its first Itanium design, codenamed Merced in 2001, it only mustered half the performance of Intel's mainline consumer/server architecture of the time, Pentium 4.  And according to some reports, x86 emulation tools were so poor that the chip performed like a 100 MHz first-generation Pentium processor.

Undeterred, Intel mustered onward.  Firmly behind it was the world's largest computer maker, Hewlett-Packard, Comp. (HPQ).  Not only did HP build Itanium systems and try to push them in the corporate IT ecosystem, but it also began to co-develop the chips with Intel.

The first joint design was the "Itanium 2" codenamed McKinley, released in 2002, built at 180 nm.  In 2003 Intel released a 130 nm Itanium 2, codenamed Madison.

Then it began to make big claims in 2005 about a design called Tukwila, which would not only pack four cores but would also replace Itanium's bus.  At the time Intel's first generation PC-side Core architecture (codenamed Conroe/Merom) was still a year away, so this claim sounded pretty exciting.

But 2007 rolled around and the chip never came.

In 2006 Intel had released the chip Itanium 9000 Series, codenamed Montecito and in 2007, rather than the promised Tukwila, it delivered the Itanium 9100 Series, code-named Montvale.

Sales reflected this poor performance.  In 2007 8.4 million x86 servers were sold, but only 55,000 Itanium servers shipped, according to Gartner, Inc.  This was bad, even for RISC-servers, which shipped 417,000 units in total.

While exact numbers are sketchy at best, due to lack of official reporting, it is estimated that Itanium was heavily outsold by Sun Microsystems (now owned by Oracle) SPARC chips and International Business Machines' (IBM) POWER architecture.

In February 2010 Tukwila finally landed, officially branded the Itanium 9300 Series.  Three years late, the processor still sported some tempting features like double-device data correction to prevent memory corruption.  These features made it a promise buy for mission-critical applications.

But for the mass market, Tukwila was late to the party and lacked the performance to truly impress

Famous tech news figure John C. Dvorak wrote in 2009, "[Itanium] continues to be one of the great fiascos of the last 50 years" in his piece "How the Itanium Killed the Computer Industry."

II. Tukwila v. Xeon

With the launch of Intel's latest "EX" Xeon processor line, a 32 nm die shrink of Nehalem codenamed Westmere-EX, Xeon had a new chip that could match the memory bandwidth of Tukwila.

A 4-core Itanium processor clocked at 1.73 GHz costs $3,838 USD per chip in quantities of 1,000, while the newly released 10-core 2.4 GHz Xeon E7-2870 costs $4,227 USD, in quantities of 1,000 (note: due to the different architectures, the clock speeds are not directly comparable). 

Given the comparable price it's hard to see the merits of Itanium, which packs less cores, other than from an error-correction/mission-critical standpoint.  Given the vanishing software support for the platform, the picture becomes even dimmer for the platform.

Intel is promising a cheery outlook for the future of Itanium.  Mr. Skaugen bragged that the next generation Itanium core, codenamed Poulson, would bring 8 cores built at 32 nm and more than double the performance of the Itanium 9300 Series.

And an even more distant chip, codenamed Kittson is also reportedly being worked on.

The problem is that even Westmere-EX is a questionable proposition.  Given the availability of 12-core Opteron 6168 chips for $750/USD, the much more expensive 10-core E7-2870 becomes a tenuous buy.

And even among Intel processors, the E7-2870's higher cost per core count is cause for pause, given that there are far cheaper Sandy Bridge-based quad-core Xeon chips (the recently released E3 Series).  The situation is complicated slightly by the fact that some software is still licensed on a per-chip basis, meaning that the E7 chips would yield a net savings if you look exclusively at Intel's offerings.  

Given the switch of many software vendors to per-core (rather than per-chip) licensing, the E7 may find less traction, though, than its E3 series brethren.

And the situation is even worse for Tukwila, which is even more expensive and by Intel's own admission trails the E3 and E7 series in performance.

III. Intel and HP -- Resigned to go Down With the Ship?

Given the poor outlook, it seems pretty incredible that Intel would continue to devote resources to the eternally disappointing Itanium project.  The project recently observed its 10-year anniversary, but given how Intel's ever-shrinking sales predictions continue to overestimate the Itanium 's dismal real-world sales, it was hardly cause for the chipmaker to celebrate.

With the SPARC and POWER RISC-style architectures deeply entrenched and a hungry ARM coalition waiting in the ranks Itanium's future is not bright.

But Intel has clearly stated that it remains loyal to its post and will stand by the platform for years to come -- even if it continues to sink.

Comments     Threshold

This article is over a month old, voting and posting comments is disabled

Its a shame
By Ammohunt on 4/11/2011 2:17:28 PM , Rating: 2
I blame HP there was nothing wrong with PA-RISC(no reason at all to switch to itanium) and at the same time not long after that they bought the Alpha architecture. Hopefully they gather some sense and revive Alpha or PA-RISC and let itanium die.

On a side note if i were Intel i would be working with Open source makers of KVM to imbed a version of their hypervisor onto a flash chip coupled with enchanced VT extensions to make processors archtecture a moot point. Hardware based hyper visors that are processor and OS agnostic are the future.

RE: Its a shame
By DanNeely on 4/11/2011 3:02:28 PM , Rating: 2
PA-RISC/Alpha resurections aren't going to happen. The cost to essentially redesign from scratch is impossibly high. Longer term the Sparc/PPC architectures will likely end up falling as well due to competition from high end x86 chips as well. The need for monster servers continues to shrink, pushing the per unit R&D costs ever higher for the remaining customers. Eventually they're all going to reach the tipping point and fall.

RE: Its a shame
By vol7ron on 4/11/2011 11:26:53 PM , Rating: 2
Or they'll just license ARM and adapt with the rest of the market.

I also like the sound of a hardware based hypervisor :) Then again, I'd also like to see it coupled with a USB or eSATA chip.. something to plug in anywhere.

RE: Its a shame
By Ammohunt on 4/13/2011 3:35:00 PM , Rating: 2
that was my thought too; esata ssd drive encrypted and secured biometrically with my entire Operating environment plugging into an internet enabled hardware agnostic provider.

Imagine suspending the OE on the SSD on your hardware at home then plugging it into your smarphone while you travel then suspending and plugging it into your hardware at work the only difference being horsepower and capability between mobile and fixed hardware.

RE: Its a shame
By CharonPDX on 4/11/2011 7:52:30 PM , Rating: 2
Uh, HP was developing an EPIC CPU before Intel was. Intel just joined in and took over.

No, Alpha and PA-RISC are right and truly dead. They may have been good architectures in their time, but they are dead. To try to revive them would be just plain stupid.

RE: Its a shame
By Ammohunt on 4/18/2011 5:24:00 PM , Rating: 2
HP-UX Still runs on PA-RISC.....

Why do people say it's dead?
By CharonPDX on 4/11/2011 7:50:20 PM , Rating: 5
Even if it's *ONLY* sold by HP, it would still make money.

Sparc and POWER are still very successful niche products. Itanium is in the same niche. (And outsells Sparc in it.) It's not as "mass market" as Intel had hoped early on, but it is still chugging along, making money. If they were to just cut the line, they would both severely piss off HP (because it would severely piss off HP's HP-UX customers,) and stop future revenue.

Itanium is no more dead than Ferrari is. Just because Ferrari doesn't sell as many cars per year as Toyota (or even Lexus) doesn't mean Ferrari is doomed to failure.

RE: Why do people say it's dead?
By wut on 4/11/2011 8:41:14 PM , Rating: 2
Because some people like to have any excuse to laugh at Intel. That, and it makes a good topic for people who don't know any better.

RE: Why do people say it's dead?
By Sunner on 4/12/2011 1:17:50 AM , Rating: 4
Aside from the more hysterical Intel-haters, most people aren't so much claiming it's actually dead right now as they're more than a little uncertain about it's future.
Most sales are HP-UX, NSK or VMS replacements or upgrades, I think the question is how long these platforms will live. VMS will eventually die, while it's current users may be purchasing upgrades for years to come the number of actual new installations is virtually nil.
NSK, I will admit I'm not sure, but I rather doubt things are much different here.
Which leaves HP-UX, which will no doubt slowly be cannibalized primarily by Linux just like the other "Old UNIX'es".
Betting Itanium's future on three OS's of which two are for all intents and purposes walking dead and the last with a bleak bleak future seems risky at best.

Of the boutique CPU's I'd say POWER is the only one with reasonable chances of mid-long term survival, at least with a pSeries box you're truly getting exceptional performance to go with equally exceptional RAS features and such, and IBM is so far firmly committed, there isn't the same uncertainty as with IA64 and SPARC.

By silverblue on 4/11/2011 1:03:07 PM , Rating: 3
by Intel's own emission

Either a mistake or a clever pun; you make your own minds up.

RE: ?
By FITCamaro on 4/11/2011 1:28:12 PM , Rating: 3
As it runs it lets out a fart stench.

RE: ?
By silverblue on 4/12/2011 5:25:25 AM , Rating: 2
I can't believe I got rated down for that twice. It wasn't that bad.

By icemansims on 4/11/2011 3:38:17 PM , Rating: 5
I just find the Architecture designation particularly funny....EPIC-RISC (Epic Risk), given their current situation......

What do you want? I'm bored, okay?

RE: Architecture
By JediJeb on 4/12/2011 1:19:20 PM , Rating: 2
I noticed that too, :) Doomed to fail from the very beginning and was aptly named.

One-sided reporting
By wut on 4/11/2011 5:56:17 PM , Rating: 4
Dailytech never reports on how this is hurting Oracles's own partners, and how much they hated this very move.

Bill Loupakos, senior vice president at American Digital in Arlington Heights, Ill., is one of them. The solution provider, which covers a five-state area, is both an HP and an Oracle partner. He was surprised by the Oracle announcement earlier this week.

"We think they are getting desperate," Loupakos told Channel Insider. He noted that back in February Oracle/Sun announced a "Cash for Clunkers" program to encourage customers to trade in their HP-UX servers for Sun SPARC servers. The campaign was laughable, Loupakos said, because customers are mostly looking to trade in their Sun servers for something else.

"All the Sun hardware customers are looking to migrate to HP platforms," he said.

I want to turn the attention of your readers to that. Your reporting is heavily biased, without regard to what the Oracle customers are actually going through.

RE: One-sided reporting
By DanNeely on 4/12/2011 9:08:58 AM , Rating: 2
Unless Oracle backtracks on its plan to abandon development for the Itanic most of those plans are probably dead in the water. Whether they end up staying with Sparc, or going to IBM is an open question, but if new versions of OracleDB aren't going to be made available for Itanium/HP-UX you'd need to be insane to migrate your database servers to it now.

By sprockkets on 4/11/2011 8:59:25 PM , Rating: 2
Intel was too busy trying to kill AMD with their good processors and bs business tactics. For that matter x86-64 didn't help matters either with the Itanic.

RE: heh
By Belard on 4/12/2011 9:00:54 AM , Rating: 2
Yep... AMD came out with their 64bit server class CPUs and quickly sold more 64bit servers in a month than Itanium in the previous years. After about 2 years, Intel adds 64bit memory support into the crappy P4 design.

Itanium was very much down hill after AMD64. $200~500 per chip vs $2000~4000 for an Itanium?

RE: heh
By BSMonitor on 4/12/2011 10:47:37 AM , Rating: 2
And not a single one of those CPUs actually ran a 64-bit OS. Since no such thing existed for 2-3 years after that. And even then, almost no drivers supported it.

AMD and its cheap thrills.

HMS Itanic.
By Mr Perfect on 4/11/2011 12:39:34 PM , Rating: 5
It typically referred to as the Itanic. Seems appropriate now.

They are rickrolling themselves...
By Motoman on 4/11/2011 12:54:12 PM , Rating: 4
Never gonna give you up, never gonna let you down...

Self-rickroll FTL.

By bldckstark on 4/11/11, Rating: 0
RE: What?
By snakeInTheGrass on 4/11/2011 8:58:47 PM , Rating: 2
The E7-2870's cost per core causes pipeline stalls across all TLBs due to its inability to pre-flight enough instructions when dealing with too many dollars. Unless some per-chip software remains exclusive to Intel, not ARM. Look.

What? Hey, I tried, OK?

RE: What?
By SilthDraeth on 4/11/2011 11:36:08 PM , Rating: 2

Great translation.

This again?
By MrTeal on 4/11/2011 4:53:41 PM , Rating: 2
And even among Intel processors, the E7-2870's higher cost per core count is cause for pause far cheaper Sandy Bridge-based quad-core Xeon chips (the recently released E3 Series). The situation is complicated slightly by the fact that some software is still licensed on a per-chip basis, meaning that the E7 chips are if you look exclusively at Intel's offerings.

The price difference isn't just based on the number of cores or the individual CPU performance. The E7 series also supports 2,4 and 8 way configurations for multiple socket servers. With the E3, you don't get that. MP chips have always been more expensive than UP/DP chips. This hasn't changed with this generation, and it likely won't change with the next.

RE: This again?
By mfenn on 4/11/2011 6:55:44 PM , Rating: 2
Yep, another swing and a miss from Mick. He still doesn't quite understand the difference between software that can scale-out and software that must scale-up.

Intel looks kind of bad over the next decade
By Shig on 4/11/11, Rating: 0
By greylica on 4/11/2011 3:31:55 PM , Rating: 2
I agree a bit with you, but there are some points to be discussed here. One of them, is the numa ( as far as I know, there is no direct numa support in GPUs parallel cores outside of their ''domain'', unless specified by the programmer to offload results in main system memory, and post offloaded in a higher order of a cluster ). The other point is some services that aren't present in most of the common server environments offered in X86 computers, like hotswap changing dead processors and memory, and more than this, microkernel architetures engineered to use devices as ''small servers''. Most of the servers made to work in those mission critical environments are engineered to use X86 only as their secondary ''nodes'', not primary ones. Freeze a cluster and you have a great problem...

Let's hope they lose a bundle
By Beenthere on 4/11/2011 5:15:33 PM , Rating: 2
It would be good for Intel to lose a bundle of cash on Itanic. Maybe Wall Street would wake up?

By BSMonitor on 4/12/2011 10:50:19 AM , Rating: 2
The chart of sales doesn't make any sense. The orange, "sales", line only goes from 2003-2006. They haven't sold a single Itanium system since?

JM you crack me up with your flame baiting.

By Pirks on 4/11/2011 12:31:51 PM , Rating: 1
Rest. In. Pain.

"If you can find a PS3 anywhere in North America that's been on shelves for more than five minutes, I'll give you 1,200 bucks for it." -- SCEA President Jack Tretton

Most Popular ArticlesAre you ready for this ? HyperDrive Aircraft
September 24, 2016, 9:29 AM
Leaked – Samsung S8 is a Dream and a Dream 2
September 25, 2016, 8:00 AM
Yahoo Hacked - Change Your Passwords and Security Info ASAP!
September 23, 2016, 5:45 AM
A is for Apples
September 23, 2016, 5:32 AM
Walmart may get "Robot Shopping Carts?"
September 17, 2016, 6:01 AM

Copyright 2016 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki