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."

Comments

AMD did it

[emptybody]

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.

Re:AMD did it

[Glonoinha]

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. That was a killer platform and some collaboration between Intel and whatever company held all the people that did the Alpha would have resulted in computer nirvana - unless the company that held all that Alpha history was run by a complete loser of a woman with the sole intent of systematically destroying the company and bringing a few other companies with it.

Oh wait - that is exactly what happened.

Re:AMD did it

[PygmySurfer]

Actually, they had it twice... Alpha AND PA-RISC.

*sigh*

Re:AMD did it

[Lisandro]

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. Never mind the and great performance and bang-for-the-buck value. I expect AMD to become bigger than Intel in the next 10 years, when 64-bits become mainstream. They already have the edge there.

Anyway, the Itanium was too expensive, too incompatible and too slow compared to the rest. The only surprise here is that HP took so long to realize it was a money drain.

Re:AMD did it

[museumpeace]

who modded you "interesting?", you're trolling! [or did Carly lay you off?]
HP did/does have great high performance platforms. I worked at DEC when the Alpha first came out and DEC had already been nervous about PA-RISC for a while at that point.
The problem is, HP, like every other computer company, can't run a charity for good engineering by offering several 64 bit architectures and several OS's. They should have spun off something like "Legacy Computer Corp." a while back and let all the fans of the various high quality/low volume systems pay the real costs for continuing support. HP has been fighting to streamline their high performance catalog for over a year and surprise surprise: they have not pleased everyone.

Re:AMD did it

[mrm677]

I expect AMD to become bigger than Intel in the next 10 years

That is quite naive. AMD has close to 15,000 employees and is a $9 billion company. Intel has 85,000 employees and is a $140 billion company. This doesn't change overnight, and yes, 10 years is overnight when you consider companies of this size. Intel will have to make several more mistakes like Itanium. Plus AMD has a long ways to go to match the manufacturing capabilities of Intel.

Re:AMD did it

[Chris Burke]

Alpha wasn't a proven market failure. DEC was a proven failure at marketing Alpha.

HP deliberately carried on the tradition of poorly marketing the Alpha, because they were tied to Itanium. Yet still their Alpha solutions outperformed their Itanium solutions. If HP had been as dedicated to Alpha as they were to Itanium, then Alpha may have been a success. If Intel, who grabbed all the Alpha engineers, had joined with HP to promote Alpha as the 64-bit platform of the future, along with a commitment by Microsoft to support it (part of what hurt Alpha) then it would have had a much better chance of success.

Alpha solutions with the marketing muscle of Itanium and the performance of, well, Alpha. Don't tell me that doesn't sound like a recipe for success.

Itanium's main problem was that it was a CPU designed by compiler people. That it took several years for the compilers -- the thing that actually gets you the performance on Itanium -- to become decent was a big sign. The biggest sign to me, the one that told me Itanium was doomed, was the ISCA(?) paper by Intel that concluded that predicated execution for branch resolution -- one of the touted great ideas of the architecture -- wasn't worth much except in carefully hand-tuned code. Since the upside turned out not to be there, the downsides of in-order-execution (e.g. not being able to service more than one cache miss at a time) dominated. Since then, Itanium has been holding out by having big caches. That's not a long-term solution, though, since you can put big caches on any CPU as long as you can afford it -- see recent Xeon MPs.

The funny thing is that Intel will simply double-think their way out of any embarassent, claiming that Itanium was always meant to only go in an ever-shrinking market segment until nobody remembers how they were promised the world and got a small pail of dirt instead. Besides, they still have mounds of cash and their IA-32 with NotAMD64 extensions. No, the real ones who are going to suffer are HP who killed off two good CPU lines and as a result are getting beaten up by IBM with the occasional sucker punch by Sun.

And yes, that is entirely Carly's fault. If I was an HP employee, I'd be screaming for her head (for other reasons too, beyond the scope of this article).

Re:AMD did it

[Lisandro]

It's not a matter of mistakes; right now, Intel is playing catch up with AMD in the 64-bit segment. AMD also has better 32-bit hardware, running cooler, faster and cheaper; Intel's brand name recognition, IMHO, is the only thing that stopped AMD from doing even better than it did lately.

I'm not a fanboy, and i'm not suggesting that Intel will dissapear, but AMD is in an enviable position right now, which i think they will exploit to the fullest.

Re:AMD did it

[museumpeace]

I was being a bit lazy in pointing to my own comment [though it did contain the most current development ] on HP reducing its diverse hi performance options. Slashdot has covered this topic every step of the long, sad way:
HP pruning the OS proliferation, HP repeats: alpha is really going away! and alpha chip to be discontinued
oh, what a small world...just noticed HP's dropping TRU64 was a gain for Veritas which was the subject of a recent /. mention

Re:AMD did it

[museumpeace]

...poor management...
yes, definitely poor management...I was one of the engineers, not one of the managers. The question is: whose poor management? Dec was NOT making it with any of its vax-on-a-chip designs...Intel was eating our lunch on $/FLOPS basis and that is what was selling systems at the time.

That Compaq bought DEC for its customer list and Intel bought DEC microprocessor design/fab capacity to avoid a profit-hemoraging patent battle was vaguely sensible at the time. Is the management misstep you refer to the question of why did HP pick up a bunch of niche-market product lines [and my retirement plan :-( ] when they already had a competative product? Or is the mismanagment you refer to the steps they have taken since the acquisitions? We engineers assumed that Palmer, haveing run DEC semiconductor operations, would not have sold what we saw as the crown jewels. But DEC had something called share holders and it was in bad financial condition.

Who was making the management mistake? the buyers or the seller?

Re:AMD did it

[Chris Burke]

Well that cache miss comment is about the most false statement I've seen in a long time.

Woops! Right, that's a big gaff. I should have said that the problem is finding the misses, in part due to the stall-on-dependency (of course, it's in-order) and also loads bypassing stores with uncomputed addresses. I.e. you'd like to move your load as far forward in the execution stream as possible so you find the miss sooner, but you can't move it in front of a store because it might conflict. I have no excuse; I just recently talked with someone researching ways around this problem (and I may still be misrepresenting it). Oddly their funding (from HP) was canceled. :)

Unless of course you hit in the 1-cycle L0d cache

Of course because that's not a miss. :)

In-order execution certainly puts more burden on compilers, but it frees up a ton of area for registers, functional units, and cache.

Eh, in theory. First, area clearly isn't a big issue with Intel and Itanium. ;) Registers aren't really that big a deal, either. Most compilers don't use all of the 32 most RISC cpus have, which is only the logical registers not the physical (of which there are many more, on par with the EPIC machines). Sure, the 8-ish of IA-32 is woefully inadequate, but that doesn't mean you needs gobs of them.

And functional units aren't a big deal at all, because neither the compilers nor OoO schedulers are able to find enough ILP to use them. They're mostly idle anyway and adding more is just wasting area. The exception is highly parallelizable FP code, but the solution there is to add vector units (which gives you more bang per unit of fetch bandwidth than non-vector in-order scheduling).

As to cache, look at any server part. On Itanium, Xeon MP, and even to a lesser extent Opteron with only 1MB of L2, the die size is dominated by the cache. Getting rid of schedulers and reorder buffers isn't going to allow them to add a significant amount of L2/L3 cache. The size of the L1 cache is a tradeoff between miss rate and access time, not miss rate and area.

Fundamentally, when you're willing to make chips that are 600mm^2, the area benefits of in-order don't really buy you much. :)

The real benefit, as I understand, of in-order was supposed to be complexity. Remembering Merced, I'm not sure that ever panned out either.

Regardless, this is all a case of reality trumping theory. The original plan for Willamette (P4) had a 32K L1 cache running on the same (double pumped) clock as the ALUs, but strangely it couldn't work at that speed. If K8 had come out when it was originally planned at the speeds planned, we'd already be singing the eulogies for Itanium and Xeon. Also, if I'd have just been bitten by that radioactive lemur I'd be out fighting crime from the treetops instead of working a day job and posting on /.

God damn reality.

Maybe it's just me, but...

[CrazyDuke]

"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.

Re:Maybe it's just me, but...

[Anonymous Coward]

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.

Mark my words, consumers will never have a need for a 64-bit processor. Itanium was toast from the start. 32-bit processing is good enough for anybody.

Re:Maybe it's just me, but...

[CrazyDuke]

That's not my point. My point was the performance increase 64-bit processing gives was not enough to justify the increased cost of that chip. As another poster in this thread points out, if you have to use 64 bit processing for whatever reason, Sun's Sparq chips where even better. Then AMD released their 64bit CPU lines...

Re:Maybe it's just me, but...

[Anonymous Coward]

Eventually people will need 64 bits just for the extra direct memory addressing. Software keeps getting bigger, and as displays get larger and graphics get more intensive, it's going to take more and more memory to hold all those bitmaps and textures and to render those fonts at higher and higher resolutions. When the standard monitor is running at 300dpi, it's just going to take an awful lot of memory, and not just video memory.

Itanic sinks, great loss of money feared

[IO ERROR]

The Itanic sank today on its maiden voyage. Most of us saw this coming. When Microsoft won't even get on board, you know your processor is in trouble.

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.

Re:Itanic sinks, great loss of money feared

[ultrabot]

it's about time that HP and Intel realized they were pouring money down a drain and pulled the plug on the project.

It's a great loss of face to call quits on a project of this magnitude. I bet many corporate directors would rather go further with it, even knowing in their hearts that it isnt't going to fly. It allows them to keep their lucrative jobs at least, instead of having to compete with other departments that are doing well.

I'd love to see Itanic turning to an "open" architecture, instead of dying altogether. That probably isn't going to happen, so we can expect to see the pain going on for a long while, with Intel downplaying the long term importance of the chip to the company. It's going to go the way of SPARC - a dead chip walking, with only the manufacturer being interested in it anymore. Better than PA-RISC I guess, with which even the manufacturer doesn't care anymore.

Re:Itanic sinks, great loss of money feared

[hackstraw]

I'd love to see Itanic turning to an "open" architecture, instead of dying altogether. That probably isn't going to happen, so we can expect to see the pain going on for a long while, with Intel downplaying the long term importance of the chip to the company. It's going to go the way of SPARC - a dead chip walking, with only the manufacturer being interested in it anymore.

First, the Itanium processor line is going nowhere. Just the HP and Intel partnership which means that other vendors will have as good of pricing as HP, so it will be more "open".

Maybe I'm just ignorant and biased, but the Itanium based HP servers that I have worked with are the fastest and best built 64bit servers that I have worked with to include Alpha, Sparc, and IBMs power chips. The Itanium chips appear 10 times in the top 100 supercomputers including numbers 2 and 5 on the list.

Intel recently released their low voltage offerings of the Itanium processor with speeds up to 1.4GHz.

There have been issues since the Itanium's release. The first chips, Itanium1's, did not perform well. The current Itanium2's are power hungry and require tons of cooling. Now they are excellent performing and have lower power and cooling requirements.

And people are interested in the architecture. For number crunching or a fast database, there are few better offerings. The Opteron or current IBM chips appear to be the closest contenders. If Intel were to lower the price of the Itaniums and continue improving their performance and reducing their power needs, I think these things are going to be around for a while.

Re:Itanium is dead

[Anonymous Coward]

"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."

Cool. A perfect match for *BSD.

1st thought - shoot Cappellas, 2nd - shoot Carly

[arivanov]

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.

Also...

[StevenHenderson]

but the chip has been a flop due to delays, cost overruns and lackluster demand.

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.

Wow...

[copponex]

Slashdotters said something was going to die, and it actually did...

I think I'm selling my iBook.

Re:Wow...

[Xpilot]

Slashdotters said something was going to die, and it actually did...

I think I'm selling my iBook.

Because it's from Apple or because the OS runs something that's BSD-ish?

Itanium failure as a chip, but...

[Anonymous Coward]

an enormous success as a space-heater.

Sad to think that...

[Anonymous Coward]

...Digital's Alpha died for this miserable farrago.

an ex-Deccie.

Re:Bring back the alpha!

[Anonymous Coward]

No. It basically means that HP will be gettng out of the high-end market and instead will sell outsourced designs from Intel or AMD. In other words, HP's tranformation to a shitty version of Dell will be complete in 3 years.

HP will be selling Itanium for a long time because there's customers marooned on the IA64 platform now.

History lesson - man behind Itanium deal

[Anonymous Coward]

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!

Not the End

[Jah-Wren Ryel]

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.

Re:Not the End

[Anonymous Coward]

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.

The history of the industry is littered with powerful processors that never sold enough to justify their investment -- Alpha immediately springs to mind, but there have been many others.

In the end, no matter how wonderful it is, if it doesn't sell it you have to move it over to the "total flop" category.

Flip your justification around: POWER5 SPECfp is neck and neck with Itanium -- AND is compatible with a large existing customer base, AND has a developer following, AND has an ecosystem around it that includes low-end derivatives such as PowerPC, AND is run by a company that has more of a clue. I think POWER5 also may be less expensive, more flexible, have better thermals, do better SPECint and be easier to design compilers for. Given all that, where does Itanium get to play?

Face it: the sole unique value proposition for Itanium is and always has been "We're Intel and we say you should use this." The one thing they could have and should have been able to offer -- performant compatibility with existing Intel processors -- they didn't do and they're paying for their arrogance big time.

Ramifications

[killmenow]

I first saw this on technocrat.net but didn't comment on it. However, I immediately wondered about the ramifications of this when you also consider all of this:

1. IBM selling its PC business
2. Cell workstations
3. POWER5 amazing benchmark records
4. IBM incents Linux on Power app development
5. Launches a Power architecture coalition
6. IBM and Red Hat begin certifying apps for Linux
7. 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...

TitanicBSD?

[copponex]

You mean OS X?

Itanic

[canuck57]

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?

Re:Famous last words?

[lseltzer]

The supposed quote was about 640K, not 64K, and it's a myth

End of a proprietary dead end

[Animats]

The Itanium's real design goal was to be uncloneable. It was Intel's answer to the AMD threat. That was achieved; there's lots of patentable technology in there, because it really is different inside. Not better, just different. Intel threw tons of money into Very Long Instruction Word machines, a dead-end previously abandoned by others. VILW machines are notoriously hard to generate code for, because the compiler has to do so much scheduling. I've been to talks where the Itanium compiler guys from HP admitted they didn't really have a solution to that problem. Intel just ended up with a new, different, innovative, hard to program machine.

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.

Re:End of a proprietary dead end

[obender]

It's surprising that Intel didn't sell Itaniums at lower prices to try to build market share.

I think the Itanium decidedly needed a Celeron version. At some point in time I wanted to buy one and assemble a small web server. I abandoned my plan the moment I saw the price.

Keeping it out of the reach of programmers ment less software for it. And a processor without software is quite useless.

HP, Intel Call it Quits on Itanium Partnership

[MARSCALLINGEARTH]

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.

This is not at all what they promised

[Anonymous Coward]

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.

What about HPUX? What about VMS?

[mosel-saar-ruwer]

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.

Itanium is not JUST a 64 bit processor...

[rpsoucy]

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).

Carly did it.

[Anonymous Coward]

Or rather, her board probably made her do it. HP was once admired as a company that cared about developing the coolest and best technologies.

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.

DEC did it Re:AMD did it

[Anonymous Coward]

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.

Re:What remains in 64-bit land?

[mikefoley]

ARGH...

Read my lips. Alpha is DEAD. Expired. Pining for the fjords.

Samsung has ZERO interest in investing in it any further. They'll keep making them only as long as HP buys them, not one day longer.

Jesus, it's over people. Almost all the Alpha developers are working in either Hudson, MA for Intel or Boxboro, MA for AMD.

How do I know? I worked at DEC for 18 years. Then at API Networks .nee. Alpha Processor Inc. The company that Samsung "ran".

If Intel had just gotten over the Not Invented Here syndrome and ponied up enough money, Alpha would still be going. But they didn't.

Repeat after me, Alpha is Dead.

Sheesh.

Re:Hypocynical.

[Jeremi]

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.

This is true to a point, but for most of us software developers it doesn't really matter -- the dog's breakfast that is the x86 architecture is mostly hidden from us by our trusty compiler. As long as our software runs, and runs fast, we don't complain too loudly.

Contrast that with the Windows API, which many software developers have to interact with directly on a daily basis to get their work done. Things like Java and Qt aside, there often isn't any protective layer that can shield us from the complexities and ugliness of that!

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'd be happy with that... but then I'm also generally happy with what we have now. It doesn't matter too much to me whether my CPU is an elegant work of art or an ugly jalopy... as long as it is fast and reliable, and my vanilla C++ code will run on it.

Re:viva la AMD

[bob beta]

It's a refocus. The H-P team members are being transferred to Intel. The Itanium development is not ceasing.

I'm not trying to be a 'fanboy' for any particular company or venture. But the way this news is being spun by anti-Intel enthusiasts is erroneous.

Re:What remains in 64-bit land?

[bob beta]

You forgot to include Itanium.

It isn't going away. HP will cease to co-develop it with Intel. They will continue to design them into their servers.

Itanium succeeded

[amorsen]

Itanium has killed off PA-RISC, Alpha, MIPS (high-end)... At one point it looked like SPARC would be a casualty too. POWER is the only RISC architecture which is doing well now. Intel even got HP to foot much of the bill. In a while they can transition their Itanium customers to 64-bit Xeon, and only HP will be seriously angry about it. The other Itanium system vendor, SGI, will be able to switch fairly easily to Xeon since they run Linux anyway. Ok, perhaps "fairly easily" is overstating the case, but Intel can afford to help SGI financially with the transition.

The only snag is that AMD showed up with 64-bit x86 before Intel was ready for that phase.

Re:Poor SGI

[bani]

1) The MIPS architecture dead-ended. It couldnt scale far enough to keep up with x86.
2) PC 3d hardware eventually surpassed anything SGI was capable of designing.
3) SGI had an opportunity to migrate to x86, but didn't take it seriously enoguh and blew it. Now they're paying the price.
4) For a while there, they couldn't decide if they wanted to be a server company, a workstation company, or a desktop x86 PC company.
5) They laid off most of the engineers of their proprietary hardware. A lot of it was undocumented, so nobody was left who knew how to make anything of SGI's work.

All of these spelled doom for SGI's traditional market. They've since been shoehorned into a tiny niche of supercomputers. They "still sell" workstations and servers, but nobody buys them for anything new anymore. It's simply legacy support for existing IRIX customers.

Carly must like commodities....

[zerofoo]

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