Slashdot Mirror
HP, Intel Call it Quits on Itanium Partnership
envisionary writes "Hewlett-Packard Co. and Intel Corp. have ended their partnership to co-develop the Itanium 64-bit processor line, according to a report from Reuters. The move follows disappointing sales for servers based on the processor, according to the report. Intel and HP developed the processor about 10 years, but the chip has been a flop due to delays, cost overruns and lackluster demand."
The success of AMD in the 64 bit market has clearly had an effect. It will be interesting to see how the market takes this news.
comment directly in my journal
I think it's pretty clear the Intanium is dead. I predict that within
3 years HP will officially abandon it and Intel will stop making it.
That said HP had made a 3 billion dollar commitment to Itanium?
"Dual use", you know...
Karma: Terrible - and proud of it!
"Intel and HP developed the processor about 10 years, but the chip has been a flop due to delays, cost overruns and lackluster demand."
Maybe it's just me, but I thought it was because it cost $900 for a CPU that did about a much as a 1-2 Ghz 32-bit processor.
Any sufficiently advanced influence is indistinguishable from control.
The Register coverage: Who Sank Itanic?
Everyone has been saying that Itanic will sink for quite a while now; it's about time that HP and Intel realized they were pouring money down a drain and pulled the plug on the project.
How am I supposed to fit a pithy, relevant quote into 120 characters?
Did it keep them in a lower tax bracket or something though?
Someone set us up the bomb, so shine we are!
Now that HP won't be selling the Itanium, will they bring back the alpha? I heard they never sold the last model because it would compete with the Itanium.
Not entirely unexpected after IBM wiped the floor clean with a 3 times increase in the TPC benchmark. This is something HP cannot even dream to match for a year or two with the current Itanic designs.
So much for the idea of killing alpha and HP's own risc processors and betting the ship on Itanic. If that sore cost cutting looser did not kill alpha 3 years ago it may have been able to compete with IBM now while Itanic never had the chance.
All I can say - it is nice that reason finally triumphed over marketing and believing own's PR, but it is sad that so much talent and people's time has been wasted for nothing.
Baker's Law: Misery no longer loves company. Nowadays it insists on it
http://www.sigsegv.cx/
However, I would venture to say that they lost a LOT of (at least casual) sales due to lack of backwards compatibility a la x86-64.
Slashdotters said something was going to die, and it actually did...
I think I'm selling my iBook.
an enormous success as a space-heater.
...Digital's Alpha died for this miserable farrago.
an ex-Deccie.
Seriously - I laughed out loud when I read the headline on the piece. This is a pretty significant public acknowledgement about the failure of this project, which considering how much $, publicity, etc was behind it, results in a lot of egg-covered faces.
...
Hopefully, this will only push the market and competition forward
The shooting should start with Palmer - remember him? He's the one that trashed Digital.
Not that funny. Even "But does it run BSD?" would be funnier. Something about a petrified Natalie Portman and hot grits would have a chance of actually being funny, to UID#400000 Slashdotters.
--
make install -not war
I feel sorry for those who bought machines with
this processor. It's almost like having a VCR
wiith *NO* tapes avalable for it whatsoever
Didn't they just EOL the PA-RISC line, in FAVOR of the Itanium? Who's running HP these days, Willy Wonka? Or are they going to walk the Path of DEC, CA and others, where they actually make nothing, but try to sell services that nobody needs, or could get from the real vendors themselves? Where is HP headed?
I want to delete my account but Slashdot doesn't allow it.
Does this open up a vacuum in the 64bit chip market? Or have the present players already staked their claim? Is 64bit Windows desktops any closer or further away?
Fairwell Itanic, we hardly new thee.
HP used to have an executive named Rick Beluzzo who sowed destruction and chaos wherever he went, much like Don Rumsfeld. My experience with him started 10 years ago when he was head of the computer group at HP - he liked Windows so much he decided that HP would become an NT server company, and would neglect Unix (a mistake that took years to correct.) And he made the Itanium deal with Intel, which ended up sucking billions out of Intel. Beluzzo then left for SGI, and drove it into the ground by stopping IRIX development and turning SGI into another NT clone builder. Beluzzo was then hired Microsoft (reward for loyalty?), and became their president - and was bounced a couple of years later. He's now the CEO of Quantum the hard drive manufacturer - good luck to them!
Back when DEC owned Alpha, it routinely pounded all others in the benchmarks, yet still came in 4th place in the RISC market.
You fanboys need to realize Alpha's was on the chopping block since the mid-90s. Nobody could justify the R&D for a narrow-market single-source CPU just for benchmark supremecy. Ultimately it doesn't matter if it was replaced by Itanium or by Opteron (see Sparc) -- Alpha was roadkill and would ditched by something commodity.
Someone with mod points, please correct this. This is a valid post.
Apparently, Itaniums are good for sending email. A Beowulf clusters joke might be too pertinent, not absurdist enough here. All your Itanium belong to us!
So does this show that AMD is going to take over the processor industry?
Intel had success with the x86 processors and built a path way for AMD to build new technology for the future. Good day for AMD fans!
While this move may be the top of the iceberg, it is hardly the end of the Itanic. Instead, this looks a whole lot like more of Fiornia's insane plan to divest HP of all technical talent and turn it into one huge organization of sales and contracts people.
According to the article, HP will continue to use itanium chips and will spend at least $3B over the next 3 years on development of systems using it.
If you look at the specfp numbers, Itanium is neck and neck with IBM's Power5 and everything else is significantly slower, like 30-40% slower. So it isn't as if Itanium is a total flop.
When information is power, privacy is freedom.
- IBM selling its PC business
- Cell workstations
- POWER5 amazing benchmark records
- IBM incents Linux on Power app development
- Launches a Power architecture coalition
- IBM and Red Hat begin certifying apps for Linux
- IBM ups its Desktop Linux push
I know it's tinfoil hat talk, but I must wonder if IBM isn't about to make an end run around Intel AND Microsoft for a new generation of desktop computing...Linux on POWER.HP getting out of bed with Intel could free it up from certain obligations it had to them and open them up to using the Power architecture.
I know, I know...it's just too crazy to think it's anything more than coincidence...
"No one should ever need more than 64k memory" -Billy Gates
A slashdotter who didn't build his own computer is like a Jedi who didn't build his own lightsaber.
You mean OS X?
Interesting, if you do a google search on "itanic" it asks you "Did you mean: itanium
With IBM and Sun continuing their RISC chip developments and HP's sinking UNIX/RISC market share they might be changing their marketing strategies (again). I wonder if HP is going to revive PA/RISC development and perhaps a dual core version like Sun and IBM's?
I don't know if Netcraft will confirm it anytime soon, but I think the Itanium has been dying for a long long time...
Although the Itanium couldn't match the competition in production, it was an innovative (or at least different) idea in the processor arena.
The AMD64 (and it's evil clone the EM64T) which whupped the Itanium still have reasonably strong blood ties to the 8080 from the late 70's along with the "exciting" design decisions that were made with the x86 line. (Yes, I know they've added a load of registers, introduced superscalar out-of-order execution and a load of other neat stuff, but at the core you're still maintaining backwards compat. with some very old kit)
I'm not saying the Itanium's design was perfect or even particularly good, but I liked having a bit of diversity in the processor market. It's particularly sad that the Alpha died for the ultimately doomed Itanium to exist too.
Ho hum. At least we still have the Power I guess.
Come on down NOW to your local HP dealer, and pick up a HP Itanium server or two. SUPER SUPER ULTRA SALE! LIQUIDATION BLOWOUT! They'll be here for one week only, so come in NOW, and save MONEY!!!
Spare us the excuses ok?
Itanium RIP.
Not that i have anything against Intel, but i wonder if they aren't in a bit of trouble these days.
Wasn't this supposed to be the Year of the itanium? Were they banking on the fact that it would be the year of the itanium?
And with the story right below this one about how well Intel is going to do with the dual core processors, something which nobody has had a good look at them actually working yet, a few warning bells go off in my head.
Whether you agree with this person's post or not, it is not anyone's place to mod down a post just becuase you don't like thier opinion or tone.
Whatever happened to responding instead of just modding down? That's weak and I hope the moderator responsible has the balls to justify himself here.
The high cost was an artifact of low volume. There's no particular reason Itaniums should be expensive to manufacture. It's surprising that Intel didn't sell Itaniums at lower prices to try to build market share.
The real failure was that Intel marketing was unable to shove this bad idea down everyone's throat. Marketing thought they could. They were wrong.
I bet this makes all the slashdot amd zealots happy nevermind most of them don't have a clue what an itanium was or even where it was used. Unfortunatly for intel it seems their investement in research in this field has fallen flat. The fact that amd fans rejoice anytime something bad happens to intel is a disturbing trend. If it had not been for intel we would not have the x86 architecture. On one side we have intel which puts millions into furthering all kinds of processor technologies and then we have amd producing the cheaper knock off and putting next to no money in RD. Amd will not be the one fielding light transistors on the market in the next decade no that will be intel and then amd will once again knock off a cheap copy.
I Wonder what this realy means for the Roadmap to OpenVMS 8.x... Is this the first plug they pull out ? Yes, I hear you think OpenWhat ? But there are still milions of geeks working daily on this stable, secure OS.
Alpha was the training ground for the Athalon designers. If only DEC could have done such a project in house.
Its interesting to see that HP are dropping the Itanium even though they have got HPUX on the Itanium. Are they going to continue with the alpha or are they going to re-look into the PA-RISC?
It is really a shame that poorly performing CEOs like HP's Carly Fiorina get a pass for bad performance.
HP's board should get a new CEO and then get a new board.
You may not remember the Intel 432, a truly fascinating chipset which flopped more miserably than the Itanic. Intel had developed the 8086 as a backup interim chip until the 432 smothered the world, and that's why we are stuck with it now. For some similar reason, they came out with the brand spanking new Itanic, and for the life of me, it makes no sense ...
... If end users were forced to migrate from x86 to some brand new architecture, why would Intel assume it had to be Intel? Did they think their cavalier treatment of end users created loyalty?
... Intel can copy the amd64 instruction set and stay in the game. I wonder what would have happened if the AMD64 had not come along ...
Intel had lockin with end users who could not migrate from the x86 instruction set as long as it was king of the hill. No SPARC, no PA-RISC, no Alpha, no PPC
Seems to me a good argument could be made that AMD saved Intel's bacon, in that respect
Infuriate left and right
DEC did attempt to make the Alpha a commodity CPU (see Windows NT, see Multia boxes). The problem is that nobody was buying.
As for Athalon(sic) designers, as many if not more Alpha people went to Intel. The high-clock P4 is more of a spirtual successor to the Alpha than the K7/K8 are.
clearly the centrino line of CPU's kick ass over the Itanium line, so it's about freakin time. it just goes to show how good the pentium pro core design was. it really is a solid design and has lasted much longer than I would have expected.
This is just one of those things that were so obviously a bad idea that even Slashdotters could tell
There's this thing about stopped clocks, they have to be right about something eventually
As for Sun, it has been eclipsed by a supernova: IBM.
What is lost in all this competition is the fact that the Power4 and Power5 were predominantly designed by American engineers, not H-1Bs. IBM tends to echew H-1Bs unless they have a Ph.D. By contrast, Intel favors H-1Bs from China and India. Intel and Sun claimed that they absolutely need H-1Bs in order to be competitive. Guess what happened? Good old-fashioned American ingenuity by a bunch of American "hicks" wiped out the product designed by elite "slick" Indian engineers and Chinese engineers.
The under-reported second half of TFA:
Under the terms with Intel, HP's Itanium development team, which includes several hundred engineers, will be acquired by Intel and remain in Ft. Collins, Colo., according to the report.
"HP will continue to use Itanium chips in its servers and will pledge $3 billion over the next three years in developing Itanium as a competitor in the $20 billion high-end server market," according to the report. "HP is winding down its other microprocessor architectures and getting out of that business entirely, having settled on using Intel's Itanium, Xeon, Pentium and Celeron processors, as well as Advanced Micro Devices Inc.'s Opteron, Athlon and Sempron chips."
For great justice.
What is to be learned from the Itanium story is that faster CPUs are not the critical factor in successful computer business. And it is not a critical factor, for the following reasons:
1) backwards compatibility. This reason can't be stressed enough. I just can't believe Intel couldn't put a x86 core on the Itanium chip.
2) compiler support. VLIW CPUs like the Itanium are extremely fast when programmed by hand in assembly, or when the compiler is extremely clever. It is difficult to make such a compiler, though. VLIW CPUs have multiple operations in the same instruction, and instruction optimization is left to the software.
3) C code and pointers. The problem of pointer aliasing creates a huge problem for optimizations. You can't just load the 128 registers of the Itanium with data, when you don't know if that data are to be changed via a pointer or not.
4) Memory, hard disks, the outdated buses and slow network connections are the real problem. No matter how hard the Itanium compiler optimizes the code, the benefits are not that important, compared to its price. The bottleneck is on the data transfer between different components of the computer, not in the CPU. Most of the time, CPUs starve for data.
5) The programming language world changes fast. Programming language vendors are more interested in providing security and lots of features for their products, rather than a super-duper compiler.
6) cheaper hardware is preferrable for most businesses. It has a smaller life cycle; it can be upgraded more easily when something better comes out.
The releases don't say HP is dropping Itanium - they say HP is no longer co-developing the chip with Intel. No more dual, redundant design teams. Intel continues development, and HP continues to sell Itanium as a replacement for Alpha and PA-RISC.
Ten plus years ago, I sat through some HP and Intel presentations about their long term product strategy which would sink Sun. They quite clearly stated that they were going to work with Intel on a new generation of processors which would be both PA-RISC and x86 compatible. And that the new processor would come to dominate both the PC and workstation markets because it would run HP-UX and Windows natively. Somebody in the audience gave some numbers - HP was selling perhaps 250,000 PA-RISC chips per year while Intel was selling many millions of x86 chips - if any engineering or design comprise had to be made which would impact compatibility, which architecture would Intel choose. Silence from both presenters. Now we know the answer.
The line direct from our HP sales and engineering contacts is...
1) This continues HP's post-merger philosophy of getting out of the microprocessor business.
2) PA-RISC microporcessor design and fabrication is already enough of an issue. Eventually, they're ending that as well.
3) Itanium is second only to the X86 in terms of numbers of microprocessors on the market, so it doesn't qualify as a flop.
4) HP's participation was holding back other HP competitors from co-operating with Intel on Itanium design.
5) Itanium and Opteron only compete in a small space. Opteron won't compete with compute-intensive or database-critical applications.
Those don't represent my opinions, and many sound like a real stretch. But, #1 would have been enough for me. If I was HP, I'd want to get out of the microporcessor business as well. Doing it well simply costs too much money. And, it hapers their ability to, say, play AMD vs. Intel games.
Amateurs discuss tactics. Professionals discuss logistics.
Granted, HPUX & VMS [and poor ol' DEC/OSF UNIX] might not have the market share of Windows, Linux, Solaris, or OS390, but there are a heckuva lotta very old, very stable, very mission-critical products designed for those platforms that now have no upgrade path.
Itanic was supposed to have been the successor to both HPUX/PARISC and VMS/ALPHA - where do people with those systems turn now?
And don't say "The Penguin" - you can't re-engineer 20 years worth of enterprise software customization in any kind of reasonable time frame.
The Itanium is not just a 64bit processor, it was simply designed to be 64bit as they saw the market moving to 64bit when the processor was concived. EPIC is very interesting, and they haven't spent 10 years working on it for nothing, it gets results good enough results for NASA and SGI to invest in it, twice.
EPIC, or something based on EPIC, most likely IS the future, Intel took a big gamble to take on such a project. What has AMD done for innovation? They've spent their existance copying what others have done; I have no respect for that company. More and more we're seeing the research that once made America the greatest technology power on the planet looked upon as a "waste of money", and "not practical". We're so driven by wallstreet that all we look at is price/performance and stock dividen returns. Well if you WANT India to become our replacment then go ahead, keep bashing everyone who takes a risk... nothing is ever perfefect when it first comes out... I don't think you guys realize the amount of work that need to go into something like making the Itanium a reality.
Furthermore, HP ending its partnership is NOT the end of the Itanium line, in contrast it will probablly be better for the Itanium line. I don't see Intel "dropping" a project thats been 10 years in the making and is ACTUALLY GETTING RESULTS.
The AMD push to move to 64bit for the desktop has really hurt the Itanium, because people think of the Itanium as a 64bit chip, and the opteron as a cheeper replacment... AMD64 is nothing amazing, its obvious, and its badly designed... 64bit was a chance to replace a bad arch (i386) but instead they extended it and gave it new life.
EPIC has suffered a lot because it doesnt have an OS really written for it... if an OS that is designed to run on EPIC pops out you'll see quite the performance advantage, based just on a few tests we have done at my University you're looking at double diget percentage performance increase (in case you didn't know the Itanium has still been beating out processors running software designed for them).
HP grew to the point where it was the #2 company in practically every tech category - servers, pcs, everything. Once that happened, these nutcase board members decided it'd probably be c00l PR on wall street if they were #1 for a quarter - so they merged with Compaq -- but had ZERO plans for "long term" planning (like 2-quarters out).
But long term be damned, they were going to be #1 for a quarter.
Too bad wall street saw through the bullshit, and noone cared. Then it was a disfunctional organization where HP Cupertino and HP texas each had redundant groups and neither one knew which would be releaseing a product.
One quarter later, they decide "gee, running two companies is expensive", so they flip-flop about axing all those product lines - causing custoemrs to all flee to Sun and IBM - and slipping back to #2 to Dell or IBM in all the categories within half a year.
In the mean time, this one-quarter-vision strategy requires that they abandon everything tech related ; and try to become a low-cost manufacturer like Legend or Samsung to compete with Dell -- but without the manufacturing centers in the right parts of the world to play that game. So what did HP become? A high-price reseller of Windows and re-branded whiteboxes it has other companies make for it.
No. Carly didn't lay me off - but HP and Compaq were two of my biggest customers pre-merger (and I guess they still are - just less so) - but it is sad to see how far the once great company has fallen. I can't really blame Carly, though... I think the problem goes one level higher in the management chain. Hewlett was right.
"AMD did the smart move of extending the x86 platform with their new CPU architecture (complete with backward compatibility), and covering with it a lot of price segments."
/.'ers see Microsoft doing when trying to preserve the Windows legacy. But then Microsoft gets accused of "bloatware" and carrying with it a terribly complicated legacy architecture. But this x86 lineage is exactly that, a terribly complicated backwards compatibility register/alu model. Face it, AMDs support to continue this funky software/processor architecture is just as bad for us. At this point it looks like we should really be jumping to the Power architecture. Intel and HP aren't the only ones who've lost out on the Itanium deal. I would guess part of the reason Microsoft has considered the Power chip is because it lost a lot of time and effort trying to make Windows work on the Itanium. They must have wasted thousands of man-hours and millions of dollars on that effort.
Funny, this is the same thing that most
In my opinion, the whole problem with Itanium for me was the silly change to the new VLIW software model. That model was simply unproven in the industry, yet Intel and HP let a bunch of PHD level PHBs prove to them it was. I'm not at all sad to see the Itainum go, and I'm happy that Intel and HP got knocked down by little AMD.
We need to switch to a new CPU architecture though. The switch needs to be sooner than later. We need a clean, well thought out, and efficient design that scales well into the future. Hopefully it won't be anything like the ugly Intel register model. I used to love the Motorola 68xxx series chips way back in the day. They were very clean. If a new CPU is invented (doubtful, the cost of raising a child from zero these days is too high) it needs to run circles around whatever the currently fastest legacy chips are.
HP has been fighting to streamline their high performance catalog for over a year and surprise surprise: they have not pleased everyone.
Uhh, let's see: They sold off Agilent, they killed PA-RISC, they killed Alpha, and now they've abandoned Itanic.
Remind me again, just what exactly is their high performance catalog?
I read about a nice Opteron platform over at the Register, but it's not all that much spiffier than what you could assemble yourself with parts from Tyan.
Why are people acting like this has anything to do with the success or failure of Itanium? 64-bit systems are indeed the future, and Intel now has a great team of senior designers to help them make Itanium better or produce a completely different 64-bit line.
some of the posters asked about HP going back to Alpha and PA-Risc, but there really isn't any going back because:
1) The new HP has burned many of there best designers by slashing R&D and so they won't want to go back and
2) You just can't hire a bunch of newbies as replacements. After having teams develop technology for years and gaining a huge amount of individual and collective experience, you just can't buy that type of synergy. It would take years just to train a new crew.
As I have stated before, HP is rapidly becoming just another wintel box shifter. This is insane as they cannot compete with Dell on price and have nothing left to differentiate themselves in the market. There are even signs that Dell may be caving in and selling AMD64 on the sly (if you buy enough). So they may end up not even having that advantage.
If they are going to survive at all, they need to kill off everything but printers (which is the only thing keeping the company afloat these days) and focus just on printing. A sad end to a once great company. The lesson? Never trust a "business professional" with your company.
putting the 'B' in LGBTQ+
It's too bad HP didn't already have a long term successful 64 bit chip, all the engineers that designed it from the ground up, and 10 years of history with something like the DEC Alpha chip.
From someone who left HP R&D last year (not WFR'd, got tired of my job and moved to a different company):
They had better than that. The folks that just joined Intel designed PA-RISC processors before moving to Itanium (sometimes refered to as PA-RISC 3). Those folks are top notch designers that have shipped succesful microprocessor products for 20 years. They already saved Intel's ass a few times in the Itanium collaboration. They designed Itanium2/McKinley entirely, and the upcoming Montecito is mostly a Fort-Collins design that replaces yet another Intel project failure (the codename and some of the most unpleasant parts of the design is all that remains), similarly it is rumored that Intel's Tukwila design (from the "famed" Alpha folks) is being ditched and will be replaced by yet another rescue design from Fort-Collins.
One of their managers was fond of saying that those folks could create a Sparc processor that would top the performance charts (Sparc has been performing pretty poorly for the last 10 years). I believe that.
Back when Alpha was in competition for the best performing microprocessor, its only real competition was PA-RISC. It was a leapfrog game between the two architectures. Since PA-RISC was never 'sexy' (few HP products are), the public only remembers Alpha, but reality was different.
As to keeping Alpha, remember that PA-RISC had a marketshare about 5x the one of Alpha (~30% of the Unix volume, both in volume and revenue; Alpha was stuck around 5-6%). And PA was already on the way out when HP acquired Compaq. Not only that, but most Alpha folks had already left Compaq by then (mostly to Intel as a group, and individual to other companies). So Alpha was never an option for HP. So please stop spreading this myth that HP killed Alpha. DEC/Compaq killed Alpha before the merger.
Regarding run by a complete loser of a woman with the sole intent of systematically destroying the company, I had the pleasure of working with some former engineers from "the old DEC". Some of them are excellent people. Overall, however, I saw a lot of bad attitudes that could sink a tech company. NIH, no concern for deadlines, shipping a real product or customer experience. Some of those folks are so wrapped in the memory of the golden years when DEC R&D was perceived as the best in the industry (while the real top talent has already moved on or retired), they don't realize what makes a company tick (pleasing customers).
I am sorry to say that, while DEC/Compaq (and now HP) management might not have helped, I believe that the Alpha/Tru64 R&D folks played a good part in the killing of their products, by being a bit too much convinced of their own greatness and failing to see that this technical greatness did not help their customers. Their toys did not win in the marketplace, outsold by less sexy widgets built by less arrogant folks (including the PA-RISC and HP-UX teams). I do not like Carly much but she and her team are probably saving HP and what remains of DEC by keeping such bad attitudes in check (by cutting the teams that do not deliver). Being 'sexy' doesn't help much in the marketplace, and it doesn't seem to help much in HP anymore. Good, too much money was wasted on sexy things.
People are rooting for the underdog, cheering AMD and boohing Itanium, longing for the good old time of technically pure Alpha. Yet Itanium is a very clean design compared to x86 / x86-64, and people forget some of the crap associated with Alpha (lack of byte loads on first generation processors, WTF !?). Such selective blindness is ok for teenagers in their basements, unfortunately they seem to be held by more senior folks who should know better.
Our industry is in a pretty sad state. Perception, mindshare, hype and FUD matter a lot more than they should.
Of course they did, because the only people who gave a crap about Alpha at this point were lockedin VMS customers.
Courtesy of Google.
os-390 911 emergency dispatch about 34 hits
hp-ux 911 emergency dispatch about 93 hits
netware 911 emergency dispatch about 620 hits
solaris 911 emergency dispatch about 1,050 hits
linux 911 emergency dispatch about 3,620 hits
openvms 911 emergency dispatch about 5,660 hits
look at specfp it is like 2000 vs 2800, that is a big performance difference and spec is not the end all be all. IBM power5 also offers virtualization features that Intel cannot dream of.
In addition to this look at some other benchmarks, something came across my desk, it was some benchmarks and on one of them I saw a 16 proc. Power5 system close to a 64 proc. itanium and on the rest it was beating a 32 proc. system in every test.
Itanium is not a good bet, if I were a CIO I would not put my money into a platform that is DOA. What we know right know is that compilers are not mature, there is no native software and realistically a high end opteron is almost as fast and cheaper. There is no reason to buy Itanium. On the low end Opteron and Xeon are crawling up its but and on the high end Power5 kills it.
Intel messed up plain and simple, anyone who knows anything about processor design can tell you VLIW does not work well to changing design.
Repeat after me:
...
The Itanium is the "Edsel" of processors...
The Itanium is the "Edsel" of processors...
The Itanium is the "Edsel" of processors...
Nobody ever wanted it except the folks who designed and built it.
Nowhere it says that development of the Itanium will stop completely. It only says that HP will no longer co-develop with Intel; Intel will continue development alone.
I received a presentation last week on 64-bit systems from HP where they actually promoted the Itanium for its higher scalability in multiway systems. As HP also offers Xeon and AMD Opteron SMP systems, maybe they aren't too heavily biased. The guy was actually rather upbeat about Itanium's prospects.
At least one other manufacturer has placed a bet on Itanium for replacing a proprietary 48-bit (!) processor. Itanium won't die so soon.
Flourescent (adj): smelling like ground wheat.
Once with the PA-RISC (from which the Itanium was actually derived...) and the Alpha when they picked up Compaq (which had picked it up from Digital...).
In the case of the PA-RISC/Itanium, they screwed up on compatibility, cost, and overall performance. The Itanium and the Itanium 2 were far, far more expensive proportionate to the performance of the Athlon64 and Power series (Power 5 and G5) CPUs- and worse yet, they had a mediocre support for legacy apps. In this one, AMD got it dead to rights. The Athon64's a better performer on 32-bit code than any other x86 architechture machine and if you recompile your code for 64-bits, you get an average 25-40% speed boost and all the benefits of 64-bit architechture on top of it. The same could NOT be said for Itanium, and if you're going to have to recompile for a new architechture, you're better off with a PPC machine if you're not using AMD's 64-bit architechture- much bigger bang for your buck.
As for Alpha, I'm still not sure what in the hell happened there- it's in the performance class of the Power 4/5 architechture and if they'd gone for the mass production on it like everyone does with PPC and x86 chips, it'd have been as cheap or cheaper. I just guess those that had it in their hands just simply had absolutely no clue whatsoever what they had.
I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
That Sun article seems really insightful now (even if it was seemingly FUD at the time) - this subheading pretty much sums it up:
Without a Volume Market, Intel Could End Up Dropping Itanium, Leaving Customers Hanging
"There is more worth loving than we have strength to love." - Brian Jay Stanley
I appreciate the commentary from someone who really knows when they are talking about. I have to admit a certain fondness in my heart for old HP products, I used to work on an MPE-3000 that I grew to greatly respect, even if not to love...
"There is more worth loving than we have strength to love." - Brian Jay Stanley
In reality:
AMD is not a no talent company, they simply have a good design team. They are proving to intel that x86 can be almost as good as anything else. I think x86 is absolute garbage but ISA's are not important because of microOPs. Sure we have to worry about an ugly decode stage but it becomes less and less of a problem have you seen AMD's monster decode stage.
Itanium is a fundamentally flawed architecture, everyone else knew that general purpose VLIW system processors are not advisable. The biggest issue is being limited on what you can do with your design, backwards compatibility is of utmost importance Intel really should have known this.
I would hope Itanium had some performance, give the amount of die space it has.
If intel was smart they would have used Alpha designs. If they could have developed a dual decoding system that would have run both x86 and alpha code unmodified. This would be very difficult because x86 is a real pita. If intel could have made this work then they would have won. Hell forget about all this, they are intel, just decree that Alpha is the now intel and build the shit out of it. Make models all across the board low end to high end, desktop and server. Given a nice ISA like alpha intel could build very fast machines.
They're an ink company now, selling 'high performance' ink for fools to pay-and-spray on expensive paper.
David Packard was right, BTW. Fuck Carly (not literally, though *shudder*)
"What's the frequency Kenneth?"
For a chip to utterly devistate out 4 of it's 5 64-bit competitors is a glowing success.
I only feel a bit sorry for HP who was the biggest casulty of Intel's brilliant game.
Add to the fact that SGI also gave up on high-end MIPS during that time, things couldn't have worked out better for Intel.
Before writing Itanium off as a failure for Intel, when it utterly destroyed our over half the competition.
You just have to wonder how HP fell for the whole scam - they pay for the knife with which Intel stabbed them, and gain nothing in return.
If you look at just the CPU core architecture being superpipelined, maybe P4 was closer to Alpha than AMD. If you look at the whole thing, including I/O through the EV6 bus and HyperTransport, then Dirk Meyer's K7/K8 was a much closer evolutionary descendent of the Alpha.
Laissez lire, et laissez danser; ces deux amusements ne feront jamais de mal au monde. - Voltaire
Is it just me feels sorry for SGI? Silicon Graphics was once the symbol of excellence in performance and graphics workstations. They made the nicest boxes, the fastest graphics cards, and the most advanced high performance compilers. I remember many years ago, I saw a Silicon Graphics demo, that completely blew away all competion. Will they have a chance to recover from this Itanium disaster?
Will their customer base believe in them when they switch to a new architecture again? What arch should they switch to? POWER?
What will their selling point be without Itanium?
Try the reverse?
Strangely it looks like Elbrus finally succeded maybe not that way they intended. but ... ;-)
Help fight continental drift.
One thing that I can't believe no one posted yet is that Intel just killed Tukwila, the great white hope for Itanium.7 0s is not nearly as cheery as it sounds.
http://www.theinquirer.net/?article=202
http://www.theinquirer.net/?article=20286
Thi
-Charlie
We're going to have to go there eventually. I guess we're just going to have to evolve there slowly. First multicore, then many-multicore, then we'll realize there's too much overlap and the'll be a "head" core that manages the others, until eventualy we're right back to an itanium/epic-like design.
That is unless ILP is a white whale and TLP is all that matters. Guess we shall see.
The fancy new architecture we need is here already.
It's called Power 5.
Read up on it, from assembly programmer's standpoint it's a dream come true compared to x86 anything, including AMD64.
Basically, it's a far superior architecture to anything in x86 land.
I was really disappointed when it didn't come out. Whether or not it would always have been as slow as the first release, it sure would have been an interesting computer to program. I found a book many years ago on it, hard bound. I doubt this hardback is the official manuals. They'd be fun to get. I wonder if Intel still sells them :-)
Infuriate left and right
The only snag is that AMD showed up with 64-bit x86 before Intel was ready for that phase.
Finally! A year of moderation! Ready for 2019?
Look at the money spent on Itanium-and how little came out of it versus Chuck Moore's Forth chips-and far Chuck got with that with virtually no funding.
I'll take issue with #4.
No, the CPU is not starved for data. Almost never.
That's the "bandwidth myth".
Back in the day there used to be a "megahertz myth" but what no one seems to realize is the tables have turned for alot of CPUs (except maybe the P4 which is designed to be starved).
The real problem is that CPUs just are not fast enough to deal with the bandwidth they have, and that is why everyone is quickly jumping to multiple cores on the CPU. 2 CPUs can easily share the bandwidth of an Opteron and it's easier for them to do than doubling the frequency. (shame for those of us with single-threaded apps that can't paralellize)
The benchmarks bear it out as well. Check out anandtech's recent server review, where using 400 MHz RAM and 333 MHz RAM made no difference.
Older benchmarks show doubling the L2 cache size makes at most a couple percent difference, but increasing MHz 10% on Opteron gives almost a linear speedup.
Itanic destroyed the competition, but it did it for IBM, not Intel.
That's funny, considering how it was originally IBM whose somewhat misadvised choice made them pick Intel's CPU for their PC.
IBM was simply clueless with the PC. They had all their talent in-house, but didn't trust themselves. Perhaps with the Power architecture, they finally will. At least the current proliferation of Power based chips and partnerships looks very very promising.
My question is this: Are all of these "Pent"iums still of the "586" generation? If not, which of these were in the same generation? What is the "X86" generation equivilent of the most-recent Pentium IV that we are currently in? Anyone know?
Come on now, fanatism isn't good on any side, but saying that AMD is producing cheap knock offs and not putting money in R&D?
Cheap knock off? EMT64
R&D? Just look at the Opteron/A64, man. x86-64, on die memory controller, Cool'N'Quiet and low wattage (hello, Prescott? Yeah, Intel's designs are SO good). AMD's partnership with IBM. etc. Itanium might be really cool on paper or if you don't have to pay for it, but in real life, it just totally failed.
And all that for less money per performance/unit than Intel chips.
Treehugger? Treehugger... Treehugger!
windows 911 emergency dispatch about 56,700
Okay, let's add Microsoft to the list:
The sum total of Microsoft's market share looks to be even less than that of NetWare.Because she's turning HP into a company that peddles nothing but commodities.
What made HP great were technologies that were unique and high margin - healthcare, scientific, and engineering fields paid a king's ransom for these products.
Carly has turned her back on these industries. She wants to sell 64-bit systems running linux? Great, so does SUN, Dell (pretty soon), and every white box vendor on the planet. What makes HP so compelling?
HP is losing their edge in printing. To whom? Dell. Sure, their (laser) printers aren't as robust or durable, but they are 1/3rd the cost of most HPs these days.
Now Carly wants to make HP a "services" company. Guess what Carly? - IBM already has you beat.
HP was a company that produced technology no one else had - that was called innovation. Now Carly wants to be a "me too" company, but it seems that Dell and IBM have already beaten HP.
-ted
What you really need to look at here is that there's now strong evidence IBM is turning away from their personal desktop market, and targeting business environments. POWER5 has proved itself in the server/workstation enviornment ... and IBM has realized that they need to stay with what they do best: Business
/. goggles for a second and realize that in all honesty Linux on the desktop for "most" users is still a pipe dream that's at least 5 years away, then reconsider this data we have IBM developing a very strong chip that rocks under unix architecture ...
... I wonder what company, that's now partnered with IBM, stands to gain them most from this. Maybe a company with a very strong end user support base, a rock solid Unix operating system with a beautiful GUI ... that also happens to be making it's strongest inroads to the personal computing market with new trendy stores opening across the country.
... only stronger than ever ...
If we all put down our
Hm
Here's my prediction:
Apple + IBM
IBM: Business
Apple: Desktop
Fricking beautifully played.
**AA: a bunch of mindless jerks who'll be the first against the wall when the revolution comes
" backwards compatibility. This reason can't be stressed enough. I just can't believe Intel couldn't put a x86 core on the Itanium chip."
They did. The Itanium had an x86 instuction translator. On the later-generation Itaniums, it was about as fast as the host CPU, clock for clock.
Exactly. AMD is doing more USEFUL development on the x86 processors than Intel has done in years. The stuff AMD is adding to that platform is the kind of stuff Intel *used* to provide its hundreds of millions of users until they decided to sink billions into the money pit that was the Itanium.
You may want to take a closer look at the Power architecture. The key RISC problem was serialisation of input (i.e. a bottleneck), and IBM has found a rather neat way round it, hence the stunning latest benchmarks.
You may be right long term, but it has always struck me as a rather risky strategy to throw out the old before you have the new stuff well and truly debugged. Even Sun was betting on this chip - they abandoned RISC years ago, probably because of the above problem that IBM solved.
All of this has left IBM a nice, wide open barn door to the market. And they supply good kit, so I personally think the long term damage done by Intel to all that depend on them is not exactly small..
Insert
In other words: the only CPUs that are still competing against the PPC have become what they are after using elements and whole sections from the alpha design. If we add to that that alpha was supposed to be the first CPU with SMT the picture becomes perfectly clear.
Baker's Law: Misery no longer loves company. Nowadays it insists on it
http://www.sigsegv.cx/
The Itanium effort has not hampered Intels x86 line as much as you think. They have invested more money on x86 than IA64.
Yes, they delayed their introduction of 64-bit in their x86 line, but that is about it. Also, much of the money which has been put on Itanium is of benefit even for the x86 line.
The "problem" Intel have is that they can't compete in memory latency with AMD currently.
"Cheap knock off? EMT64" If you have some kind of knowledge on this, you would know that Intel has spent a lot of research on extending x86 to 64-bit during many years. Research has been done, but a release has not been made for other reasons. Now, they had to change their implementation a bit to match AMD.
"hence the stunning latest benchmarks." IBM's recent stunning benchmark have very little to do with the core. It is the memory architecture that is outstanding.
I do not like Carly much but she and her team are probably saving HP and what remains of DEC by keeping such bad attitudes in check (by cutting the teams that do not deliver). Being 'sexy' doesn't help much in the marketplace, and it doesn't seem to help much in HP anymore. Good, too much money was wasted on sexy things.
Raise your hand if you think that Ms. Fiorina would have been allowed to run both Lucent & HP into the ground had she remained a brunette...
Just say the fockin chip sucks! (as do most things from with "intel inside" these days)
Where's my free iPod!? Until then, I'll settle for a kiss...
In college I used an Apple IIe, which I added a memory card to double the memory from 64 kilobyte to 128 kbs. It had an 8-bit processor that might have run 1 Mhz. It did word processing and speadsheets just fine. Car engines don't follow Moore's law, desktops do. I wish I was hilarious, but its just that you're young and dumb.
Symbolics ported their Lisp Machine Operating System, Genera, to Alphas running DEC Unix before discontinuing their Lisp Machine hardware. Some of my favorite software is now defunct twice over! :-(