HP Terminates Itanium Workstations 472
vincecate writes "The largest Itanium system maker,
HP, has terminated its Itanium workstations.
It seems their workstation customers have spoken in favor of x64.
In related news, Intel expects to ship
over 100,000 Itaniums in all of 2004
while AMD is estimating
1.5 to 2 million AMD64 chips in Q4."
Re:What about servers? (Score:2, Insightful)
The only way of getting even after losing money is losing more money?
That's actually quite sad (Score:5, Insightful)
Ok, many people don't like it. And OK, it's complex. And OK, many people are making other quite good 64-bit processors.
If its competition was Power or MIPS, then OK, I'd say that the worse it is, let IA-64 die, but x86 (and x86-64 as well) is UGLY and laden with all kinds of OLD JUNK. Come on, it will be junked sooner or later. Granted, Intel can make high-performance x86s, but that at a price of devoting over 1/3 of the stages for decoding!
Or, let's put it that way. It is a Good Thing (TM) to have several different architectures. If all we'll be stuck with will be x86, it'll be quite sad.
Re:So, question for the crowd... (Score:5, Insightful)
If there's one thing I've learned from working in high-tech, it's that no matter how smart and capable the grunts are (engineers, etc.) you always have a dim-witted marketing guy or manager steering projects in the wrong direction (and not listening to criticism).
Re:Low power CPUs? (Score:2, Insightful)
P4 based Celerons on the 400MHz FSB are crippled sad creatures. The latest revision which ups the bus to 533MHz (and the L2 cache? I forget) improves the situation somewhat, but I think they start at 2.8GHz (and being based on the Prescott core, they eat power like a geek drinks Mt.Dew). Celerons are cheap, and they are also cheap. I don't think they provide good value.
The only thing I agree with is that bleeding edge stuff is a fool's game.
Re:How Ironic (Score:2, Insightful)
Try a palmtop processor (Score:3, Insightful)
Even laptop processors run too hot.. The centrino uses a smaller amount of power, proportional to the computation being done. It also implements heat throttling, so I wonder how effective it would be if you remove the fan completely (probably not very effective at all) since the geometry is quite small and the heat density is high.
You could even try going with an Xscale, which runs nearly 1 GHz at 1+ watts. At that power dissipation, it doesn't really need a fan, just a heat sink. It also implements the throttling IIRC, so will not fry if you run it too hard. I don't know if you can buy an OEM board for it though.
Then there's your price issue. I don't think you are going to get all that power savings you want and at the same time save money.
It sounds like what you really want is a super-cheap system to get you by until your next super-cheap upgrade. You may want to permanently stay 5 years behind the consumer curve, which is way on-the-cheap. Try looking at pricewatch [pricewatch.com] for a complete system (your choice of OS). They have older models (such as a 2.0GHz P4, etc) for ~$250.
In other news, Honda outsells Bentley. (Score:4, Insightful)
The Opteron isn't in the same league as the Itanium, no matter how much AMDroids wish it were. AMD needs to be comparing Opteron/AMD64 sales to Xeon/Pentium4 sales. Itanium is a very high end processor and it's one of the best you can buy for certain high-end applications.
Not to say Intel didn't make a mistake in trying to push Itanium too early as a general purpose CPU - it's clearly not.
Re:How Ironic (Score:5, Insightful)
HP's current innovation strategy may be sumarized in the their unwritten Mission statement:
Carly Gets Paid.
Under Carly, the Calculator division has had the guts ripped out of it, the printer division has had the guys ripped out of it, the server division has had the guts ripped out of it.
Um.. what else does HP make?
And Carly gets her US$20m a year, despite the fact that none of her "innovations" have moved the company forward.
Re:There goes VMS on the desktop again... (Score:4, Insightful)
Re:So, question for the crowd... (Score:5, Insightful)
An architecture switch breaking x86 ISA compatibility (i.e. emulation is noticeably slower than the original item) would put it on a level playing field with other 64-bit workstation/server-class chips, yet they never seemed to offer either world-beating design improvements or substantial price benefits, or appear as though they would in the future.
Intel decided to break with the past and start fresh, in hopes that they could make a large leap forward. That's a good goal. But what actually happened was a couple of things:
1. Their experiment failed, in that they didn't get the monstrous across-the-board benefits they expected.
2. They started this back in the days of the Pentium, when it looked like the x86 CPU architecture and instruction set were the big problems. The Itanium design team didn't forsee the crazy lengths that would be taken--by both Intel and AMD--in order to speed up the crappy x86 architecture.
Honestly, you can't fault Intel for trying. Where did chips like the ARM and MIPS come from (two of the most popular non-desktop processors)? From designing a new architecture. That's the same kind of thinking that resulted in the amazing GPUs from ATI and nVidia.
As a footnote, it's somewhat sad to see radical advances in CPUs come to a halt. I'd love to see someone set the industry on its ear.
Re:Yeah, Itanium tanked... So what? (Score:5, Insightful)
2) These predictions were borne out by the fact that Itanium performance has always sucked, especially considering the enormous die size, cost and heat dissipation.
3) It looked like Itanium might win in the market despite its technical limitations, just because of Intel's vast marketing budget, its momentum, and its monopoly leverage forcing OEMs to stay away from technically superior alternatives like AMD64.
4) Thankfully this hasn't happened. The technically superior, open solution is winning. Thanks AMD.
Re:How Ironic (Score:2, Insightful)
Inkjet cartridges. She has decided on the Gillette business model and in the process killed off one hell of an R&D department.
Re:Yeah, Itanium tanked... So what? (Score:2, Insightful)
Is that a joke? How is IA-64 "proprietary and closed?"
IA-64 was never supposed to be a home desktop CPU anyways.
Compare AMD-64 sales to Xeon and Pentium 4.
Like another poster said, this is like being shocked that Honda sells more cars than Bentley.
Re:How Ironic (Score:4, Insightful)
Luckily some of the old HP spirit is left in Agilent.
Re:So, question for the crowd... (Score:4, Insightful)
I've heard rumours that Intel wanted to do something radical in the architecture because it would be harder for other vendors (AMD) to clone. That could have forced them into their VLIW design.
When IA-64 was conceived (mid 90s) some research groups (e.g. IMPACT at Illinois) were touting in-order VLIWs with compiler support as the way of the future. Their research had problems but perhaps some key Intel/HP engineers bought into it.
Now imagine that the IA-64 project got rolling and after a few years you've aligned the company around the project and sunk a billion dollars or two into it. Maybe you've even talked it up in the press or with analysts. Many of your best and most senior engineers have staked their careers on the project. Now suppose some of your people have doubts. How hard would it be for them to persuade the company to flush it? Near impossible, I suspect.
It's scary how close we all came to watching AMD go under and IA-64 taking over in spite its inferiority. It would have been a terrible example of monopoly power leading to bad outcomes. Fortunately at this point it's only a matter of time before IA-64 is cancelled. It can't compete with x64 chips which are essentially equivalent but ship in 10x-100x of the volume.
Re:A victory for 32 bit backwards compatibility (Score:5, Insightful)
If you really like what Apple and IBM are doing with and for Open source, support them by buying their hardware and running whatever operating system you wish (be it linux for PPC, one of the BSD's or OSX).
I laugh when I see open source advocated saying how evil MS is and yet they probably helped put MSFT in the position they are now in by not buying Corel/Wordperfect products instead of MS Office and buying PC's bundled with Windows instead of now dead platforms like the BeBox, Commodore Amiga, Next Cube. Even if they had bought macs from Apple, MS would not have the power it now has in the industry and Corel/Wordperfect would still have a significant portion of the office market.
I also feel that Open Office should stop trying to closely emulate MS Office and try to produce something much better.
Comment removed (Score:4, Insightful)
Re:How Ironic (Score:2, Insightful)
Re:Yeah, Itanium tanked... So what? (Score:3, Insightful)
Re:Yeah, Itanium tanked... So what? (Score:5, Insightful)
Their decision to support 32-bit mode in their x86 64 bit platform was a wise decisions and all of us knew that.
Furthermore, AMD keeps forcing Intel to innovate. As long as AMD is around, CPU's will get faster and better and do more per cycle.
Without AMD, we'd not have good competition, and Intel could comfortably cut their R&D costs to turn a bigger profit - their only rival would be PowerPC, and it's not a x86 platform. Let's not forget, Intel is first responsible to its shareholders.
Furthermore without competition, rest assured we'd already have DRM shoved down our throats too.
Re:So, question for the crowd... (Score:3, Insightful)
They started this back in the days of the Pentium, when it looked like the x86 CPU architecture and instruction set were the big problems. The Itanium design team didn't forsee the crazy lengths that would be taken--by both Intel and AMD--in order to speed up the crappy x86 architecture.
The architecture is actually rather nice now. It's only the instruction set that sucks, and that's a fairly small part of the transistor count.
Honestly, you can't fault Intel for trying.
Nope, but I can fault them for not knifing this thing in 97 or 98.
This is interesting, what's Intel going to do? (Score:3, Insightful)
Now I was bidding on a dual itanium on ebay a while back, it seemed like a cool piece of exotic hardware with decent performance (my alpha is nearing EOL..;) 40GB of SCSI drive, 2 800Mhz IA64s, 2GB of RAM. I bailed at $800 and it went for $975; original price of the hardware was $12k to $14k. The alarming thing was when I was searching IBM's site for information, it was practically non-existant. I asked some employees to look around inside, it's a real machine the specs are correct, no info because they literally sold under 500 of them.
There used to be all sorts of Linux on IA64 sites, they've been drying up. People are still doing stuff but it looks like some well backed projects have just dried up. Like the trillian project. Also, it doesn't seem like anybody is making an IA64 linux distribution anymore, there are some projects but all the big boys look like they have one they made back a couple years and never sold it and never updated it, SuSE has an 8. Redhat has a 7 (?!? RH 7? How old is that? Is that even a 21st century release?) and it looks like a RHEL 2.1 which is more reasonable, Mandrake has never been terribly strong off of IA32 but they have an 8.1 which is ancient and, Debian and Gentoo look like that have projects but they are kind of fossilized. I imagine that once the installer is done for most distros, it's mostly just a job of recompiling packages and then some kind of QA effort or a "beta" labeling goes on everything, not to make it sound easy or anything but once it's built it shouldn't require a huge team to maintain. Maybe Intel would kick in a few dollars too, they need Linux for IA64 internally and if they really want to sell the hardware they need some OS for it.
So Intel has pumped a trmendous amount of money in to IA64, a huge amount of time and they have all but decaired it their future architecture so presumably that leaves them at a bit of a disadvantage should they abandon it. SGI has bet on it. HP has bet on it. It's really down to POWER/PowerPC, x86 and x86-64, and then sort of Sparc. Does Intel keep kicking this dead horse? When does it turn the corner? and how? The next gen chips are all supposed to be socket compatible between the EM64 and IA64, if Intel starts shipping $400 Itaniums then maybe it will start to get some traction but why would you buy one when you can buy an em64 that will run Windows and tons of other software? I don't see how they back out, and I don't see how they can make it win, it looks like AMD has forced their hand and what that really does is make IBM the only contender in enterprise 64bit heavy duty computing right now.
Re:Just one little note... (Score:4, Insightful)
Not anymore it's not. Delete "workstation" from that sentence.
Whoever submitted this article seems to think that every AMD64 sold is going to be going into the high-end server market.
No, he just thinks that disparate total sales actually mean something. The AMD64 is good for workstations, servers, laptops, email, and videogames. Itanium is now server-only. The fact that AMD64 has so many consumer sales actually makes it more attractive for high end use, because the volume drives the per-chip cost way down, and boosts R&D reinvestment.
Re:Just one little note... (Score:3, Insightful)
Re:bring back alpha (Score:4, Insightful)
I just don't see that happening. Plus while it may not cost them much to reopen production lines, it would take them away from where they want the market to go, Alpha, as an architecture, was a lot more than just the chip, and performed accordingly. It wasn't just a Math Machine, but also an I/O Machine, for several of the choices made(like having a daughterboard and per-cpu memory in my many configurations, kept bus traffic low, and needed basically less Mhz for the same speed as long as cpu localization was enabled) increasing that trend. Alphas and SPARCs used to be favorite workstation chips for that very reason, not just calculations, but I/O(lots of applications require both, like finite elements). Servers are also I/O hungry, and it makes sense that a chip for one would do well in the other. Now I notice that the bang for the buck department, especially if you factor in I/O and other considerations, Itanic doesn't inspire HP, which, as the people who took their PA chips and merged them with Intel's, are the ones who had the most investment in its success, I can only conclude Itanic sunk...
With Intel selling cpus but having to license ASUS/VIA/ABIT etc... for motherboards, Intel would lose part of the profits. Itanic was a lot more than just a new chip, it was an attempt to kick competitors out, leaving HP and Intel with a dominant position. Thankfully for geeks everywhere, it mostly backfired.
I also believe Intel had to give up the alpha somehow, to a consortium of companies interested in the Alpha chip itself, leader of which was Samsung, at the time.
Re:How Ironic (Score:3, Insightful)
> serve-your-shitty-perl-app-over-the-web"
> processor.
Well that's too bad for Intel, because that's where the money is.
Re:Yeah, Itanium tanked... So what? (Score:4, Insightful)
Re:How Ironic (Score:5, Insightful)
Yes, and don't call me sloane.
Oh, right.
As an MBA in training, I can see exactly where MBA and technology diverge. MBAs are great for ideas on how to manage people, finances, suppliers, clients, to anticipate market trends etc etc... and a name school gets you great contacts (what I don't have.. but hey, its 1/10th the price of the Harvard BS course).
What it doesn't teach you is how to work R&D. The economics of R&D don't work the same way as everything else does. IBM get it. Xerox got it. AT&T may still get it. Sun hopefully will get it again.S
Stuff you do now may pay off for years. In some cases for IBM and AT&T, decades. MBAs don't think on those scales. Long term is 8 quarters... 2 years.
Carly might be great in charge of the Sales part of HP, the pure commerse stuff... but she doesn't have any idea about how to run and engineering firm because she's not an engineer.
Re:Workstations != Servers (Score:4, Insightful)
Predication's nice, but it wastes resources when you can predict branches accurately, which you can most of the time. And the big bottleneck is not branch misprediction pipeline flushes (~30 cycles), it's cache misses (100-1000 cycles). That's where Itanium really hurts.
But I know that people will keep talking about the "forward-looking" "greater headroom" IA-64 architecture right up until it gets cancelled.
Re:Lets all bash Intel (again) (Score:4, Insightful)
Re:How Ironic (Score:3, Insightful)
Um, to their benefit, Itanium was not, nor ever will be, a workstation processor. Heck, it's not even a "serve-your-shitty-perl-app-over-the-web" processor.
It's a HPC processor.
It's a low-volume proc. Intel will either watch as the Itanium is eclipsed by everybody+dog or lose money on the whole thing. Generic processors beat niche every time - that's how Intel made their fortune.
The low hanging fruit was picked decades ago. (Score:3, Insightful)
x = a->b->c also stumps hardware pre-loading.
itanium 2 doesn't do next-line prefetching, but it does read 2 bundles of instructions per cycle. This, depending on the density of those bundles, does everything that a prefetch might do, and more given available execution units.
Your contention is correct that itanium doesn't solve all the problems that face a modern risc architecture. Does that mean that no one should bother trying? Should processor makers churn out the same stuff and wait for moore's law to make things faster? Hope that multi-core cpus will somehow be better utilized than smps?
The simple fact of the matter is that there is a finite speed at which one can execute a serial sequence of instructions. One can try to execute pieces of code in parallel, but there is finite parallelism in most codes. Processors have been fighting for ways to minimize the percent of that parallel code that is mistakenly executed serially, but one is bounded by the actual structure of the code.
Loading data and instructions from memory remains an extremely expensive thing to do, and it's only getting worse. Really solving the problem would require some radical design that completely undermines current methods of programming. I applaud intel for being daring, and the end result is not a disaster, it simply fails to live up to the hype. As a replacement to pa-risc, alpha, and mips, I think itanium is a pretty reasonable choice. As a replacement for x86, not so much.
Why Carly got the job (Score:1, Insightful)
Here was HP, a real technology company that had produced real hardware for generations, and these gimmicky newcomer Web sites (essentially just a bunch of pages with hyperlinks), founded by gangly 20 year olds, were worth billions of dollars. HP's board probably thought, "We have to get in on this action, even though it completely defies logic."
Back in the Dot-Con boom, a lot of companies soared in the market place using "romantic" press releases about their companies' histories. Some of these histories were fakes, or overly simplified tall-tales, but who cared about journalistic integrity in the days of Henry Blodgett (a financial "analyst" who rated highly the companies that his employer was taking IPO) and day traders? To get a sense of the era and the attitudes of the day, look at the Real Video segment reported by Paul Solman in February of 1999 on the PBS news program, "The News Hour with Jim Lehrer" at http://www.pbs.org/newshour/bb/cyberspace/jan-june 99/internet_2-4.html [pbs.org]. In other words,
1. Create a "cool" story, which...
2. Attracts the press and media (always looking for good stories so that people will buy their rags or watch their financial "news" shows; more eyeballs means more advertising revenue), which...
3. writes exciting stories that capture the imagination of day traders and other amateur investors, causing them to invest (gamble) in the stock, which...
4. Causes the value of the stock to skyrocket, which...
5. Makes people want it more, which...
6. Goto 2. (Repeat infinitely until the world runs out of money. Or people wise up.)
Thus, Cisco Systems fabricated the story about its founders, Len Bosack and Sandra Lerner; according to the company history, Bosack and Lerner, who were married (how romantic!), wanted to find a way to communicate with each other across disparate networks so they could synchronize the feeding of their domestic cats (how cute!), and voila!, invented the routing technology that became Cisco. In fact, the technology had been started years earlier as part of a funded project before Bosack had arrived from the University of Pennsylvania -- but in the Dot Con boom, reality (and mundane histories) didn't mean anything. (See http://www.pbs.org/cringely/pulpit/pulpit19981210. html [pbs.org])
Likewise, EBay's humble beginnings were also faked, as detailed in Adam Cohen's book "The Perfect Store: Inside EBay" . According to EBay's websites, Pierre Omidyar wanted to sell his fiancée's Pez candy-dispensers, and voila! created the auction web site to solve his problem. The geek and the fiancée(how romantic!), the selling of Pez candy-dispensers (how cute!). Cohen reveals that the story was completely phony, concocted by a PR person, but it helped to encourage press editors to run stories and press releases about EBay.
Even billionaire Larry Ellison recognized the value of the press in warping the logic of the financial world. He hired a CNET journalist , Gina Smith, to become CEO of his New Internet Computer Company (NIC) (http://sanfrancisco.bizjournals.com/sanfrancisco/ stories/2003/04/21/story7.html?page=1) [bizjournals.com]. Who in their right mind would hire a journalist to become CEO of a technology company. NIC would tank after the Dot Con bubble collapsed. But it seemed logical during the era, didn't it? Who better than a journalist would be the master baite
Re:How Ironic (Score:3, Insightful)
And Alpha was *THE* 64 bit king. SGI only had a toe-up in the video world because of their top-notch video processing hardware, something that companies like Accelgraphics and Integraph were attempting to remedy on the PCI based alpha boxes (Those designed to run NT as well as VMS).
Sun continued to dominate simply because Solaris didn't suck as bad as Digital Unix/Tru64. HP was a complete non-starter performance-wise, hence their bet on Itanic/Intel. The fact that history would literally dump the EV6/EV7 architecture into their hands is ironic. And sad.
Snake Oil (Score:3, Insightful)
Luckily for intel, some companies were run by PHBs that didn't have a clue about processor design. In this way, intel managed to kill off development of Alpha (the fastest 64-bit processor in the world), MIPS and PA-RISC. What a way to nail your competition.
Some people were more forward-thinking and that's why POWER (and PowerPC), UltraSPARC (and SPARC64) and AMD64 survived or came about.
intel managed to completely and utterly fail to produce something that people wanted. It's expensive, hot, difficult to program, doesn't have an established software base (or operating system), and has lackluster performance on everything except the SPEC floating-point benchmarks. Thus it has found a niche amongst scientists and engineers with more money that sense and very good air-conditioning.
Over the years, intel and HP have tried very hard to silence the academic and professional itanic dissenters. Alas the PR and FUD machinery couldn't cope (as with all dictatorships) and the empire has crumbled.
It was really funny (and somewhat sad) when a couple of years back the IT press was talking about "the transition to 64-bit computing" when most people, except intel (actually, including intel, just not with itanic) had done it back in the '90s (DEC, SUN, SGI, Cray (maybe the 80's or 70's), HP).
Rather than being a radical new architecture, itanic [sympatico.ca] was actually based on theoretical supercomputer designs of the 1970s that were overtaken by developments in RISC processors in the 1980s by IBM, Sun, SGI, DEC, Fujitsu and NEC.
However, those with the $$$$$$ get to write history, and as I mentioned above, the FUD machine managed to silence many credible critics. Perhaps this will be forgotten. In this case, the market has spoken.
What really bothers me, is that back in 1988 intel produced an absolutely brilliant processor called the 80860 [sympatico.ca] and it died a death. It was genuinely ahead of its time, Unfortunately, poor marketting and MS-DOS sent it to an early grave.