Alpha Up For Grabs?

A number of people have been writing about Compaq selling off the Alpha processor, with some coverage from different media sources. The Inquirer cites Intel as the likely buyer, which seems odd to me considering their aversion to antitrust lawsuits. Maybe AMD? Who knows - it's too bad that the Alpha technology has never realized the same commercial success as it has technologically.

Comments

Sony

[Anonymous Coward]

Sony would be a good fit. Unfortunately they recently tied the knot with IBM for design help on their next generation processor for the PSX3. Think about it - Alpha is excellent at floating point. It would make those game consoles sizzle. Sony would be the best fit of all because everyone else is short of cash or tied up with their own next generation processor. It's realistically doable -- go for it, Sony !

Re:Sony

[Anonymous Coward]

I'm not sure I want a 150 watt processor in my PS. Sizzle is right.

Re:Sony

[Libertarian001]

Alphas are power hungry only because of the tech level used to fab them, .25um. If they fabbed it in .13um (not even using copper or anything else special) a 500MHz Alpha would consume 21W. It would also cost significantly less to fab than the EE does.

StrongARM (or XScale, it's successor) would be a much worse choice than Alpha. All it has going for it is power consumpiton efficiency. Alpha crushes it in interger perfomance, and StrongARM doesn't even have an FPU.

Re:Sony

[Libertarian001]

It's amusing that you mention Alpha for a NG console. DEC was actually working on an Alpha based console/arcade box (think of it as being similar to the DC/NAOMI relationship). Things were going well and even had titles lined up. See the game Dronez by Zetha Games? Originally designed for this Alpha platform. Then Compaq bought out DEC. Yet another chance for Alpha to be in the home destroyed.

For Sale

[Anonymous Coward]

Alpha. Buyer to pay all antitrust lawsuits.

Bid history:

$91M Sun
$92.5M HP
$95M Intel
$98M AMD
$99M Sun
$101M AMD

Reserve not yet met.

Compaq sell Alpha:: No loger Rumor

[Anonymous Coward]

http://www.compaq.com/newsroom/pr/2001/pr200106250 1.html

Compaq, shame on you.

[emil]

I had hoped that Compaq would aggressively market Alpha with the DEC acquisition, and would offer us a choice in the IA32-IA64 migration.

I had hoped for fast and reasonably-priced Alpha systems. These never materialized. You never even gave the architecture a chance - the marketing was nonexistent.

I've had a reasonable level of respect for Compaq equipment, but now I hear that Compaq wants to reposition itself as a services company.

Shame on you, Compaq. You are the second largest computer company in the world, but it looks to the public that you are lackeys, easily threatened and controlled by Intel and Microsoft. You could have made the market a better place, but all that you've done is make everything worse.

I guess that it's all in Sun's hands now.

Sad

[heroine]

In other words a lot of gifted EE's in Massachussets are getting creamated. Must say
the Alpha had the fastest memory bandwidth, even faster than AMD 760 DDR. Now I'll have to get a real VCR for recording movies like everyone else.

Re:Why Intel or AMD?

[warmcat]

Access to patents. That's why Alpha has any worth at all.

Alpha has been a dead duck for years. Amazing how long things can go on after they start to emit the stench of death.

If Commodore had sold sushi...

[amorsen]

They would have marketed it as "cold, dead fish". s/Commodore/DEC/ to make it on-topic, but I heard it about Commodore first.

Great Linux folks

[RC Pavlicek]

I have no idea what is (or isn't) going down at Compaq, but I know that many of the Alpha Engineers are among the most vocal Linux supporters in Compaq. I just wish them well with whatever comes down.

Keep up the great work, guys and gals, wherever you end up.

-- Russ

Tru64 Binary Format?

[Macka]

Hmm .. if Intel get all of the Alpha design team, then they also get all the compiler designers. That leaves Compaq with none for the Tru64 port to IA-64. So what are they likely to pick?

As Intel have already put a lot of effort into working with the GCC developers on IA-64, one would assume that any new talent they get is going to be focused in the same direction.

The logical move would seem to be for Compaq to use GCC for the Tru64 IA-64 port, which would result in binary compatability (though not library compatability) with Linux IA-64. The library issue could be addressed easy enough, and would make Tru64 a good platform for running Linux apps, while further helping to entrench Linux as the development platform of choice!

It will be interesting to see how this unfolds.

Macka

Re:Intel: Alpha vs IA-64

[deadline]

Simple economics. With no Microsoft OS the Alpha is a niche CPU. (i.e. less than a 500K are probably sold a year, more like 100K). When IA64 hits the street, Compaq will dump Alpha because they will save a tremdous amount of money with one 64 bit CPU (IA64)which will cost them less to buy than to make an Alpha. Why do you think HP teamed with Intel? (same reason, PA RISC is in the same boat as Alpha).

Yes it is fast and great, but the cost of designing and fabing a CPU is in the billions so you have to charge say $2000+ for a cpu to recover your costs (or sell a lot of CPUs).

So who is left X86, SPARC, Power, who will go next?

Re:Why Intel or AMD?

[Waldmeister]

DEC was renowned for nothing so much as their inability to market good products.

Uh, I thought that company was IBM? ;-)

However, another question also arises. The Alpha has been around for, what, a decade or so now? Possibly the architecture is nearing the end of its life cycle, and if so no one is going to want to spend much to acquire it.

If you take a look at the market, Alpha is one of the "youngest" chips around. x86 is succesfull for more than twenty years now. And SPARC ('87) and POWER ('89?) reach their 15 yrs anniversary.

I also remember a paper from DEC with a planned lifetime for the Alpha architecture with 20 or 25 years.

I think that time has proven that you don't need a completely new archicture to keep pace with the technical advance. (It's about evolution or revolution.) AFAIR Tomshardware has a great article about (changing) chip architecture and (pretty static) instruction sets.

Re:Motorola?

[DGolden]

Actually, the PPC is bi-endian - you can run it in either big or little endian mode. Thing is, all the MoBos I've seen, and the CHRP/PReP specs, run it it in big-endian mode, (since the MacOS started out on a big-endian system)

It's a pity, since I prefer little-endian on the whole... (however I'd still prefer a big-endian PPC to a little-endian x86, since the x86 instruction set non-design and lack of registers is soooo crap)

Re:It's a pity

[Bio]

I have taken some photographs of our early Alpha Prototype board. Have fun!

It's a pity

[Bio]

We did two hardware board designs with the DEC Alpha 21064 and 21066 back in 1992. The architecture and the processor were far ahead of it's competitors then (64-bit architecture, 150 MHz).

It's a pity that the Alpha had not more success!

From within the company

[saihung]

I've heard from friends inside of the Alpha team that the problems started in December, when the head of the series 7 design team told the president of Compaq a month before the chip was supposed to be finished that he'd need six more months. Thanks to that delay Compaq had to reneg on several contracts, and that may have made Alpha the most obvious candidate for the axe when Compaq's recent financial problems manifested themselves. For those who don't know, the Alpha team always has two separate design projects going at once; one for the next generation chip, and one for the chip after that. The next scheduled release was (if I remember correctly) series seven, but that team has bungled things so badly that series eight is nearly finished and seven still isn't close to release. Its a shame, really. From what I've heard the eight is a real jem.

Oh, and there's also a rumor that Samsung, one of the Alpha's main fabs other than IBM, is no longer interested in producing it...more problems.

Re:From within the company

[Libertarian001]

Really, what did you expect? The series 7 ('364) is designed by people that have no clue WTF they're doing. It's a '264 core with a Rambus controller on it, not much more. The '264 came out in '96, so 5 years later and they still can't release a new product? I smell incompetence.

Ahh, the series 8 ('464). Now *that's* a pretty chip. 8 instructions/cycle issued, something like 256 in flight at once, multi-threaded core. Tick for tick it has twice the performance of the '264, and it runs at twice the clock. Too bad they won't fab it in state of the art processes.

Re:Why Intel or AMD?

[Black Parrot]

> I would think it would be a lot of money to buy a product that would not be that useful to either company except to maybe get some ideas on improving there own chips.

Actually, most of the ideas are readily accessible in published papers. There may be some patents locked up in the Alpha, but I doubt that there are any secrets.

> I dont think there would be a large market for the Alpha being that Compaq and DEC could do nothing with the chip.

DEC was renowned for nothing so much as their inability to market good products. Dunno about Compaq, but without an NT for it I can't imagine that they would know what to do with it (which probably explains this article).

Your VIA suggestion sounds good. However, I think it would be a shrewd move for AMD too, if they're in a position to market it at a more competitive price than it traditionally has been.

Also, parts of AMD's architecture has been converging with parts of the Alpha's (even on Athlons), so AMD might be able to integrate it into the high end of a "family" of processors.

However, another question also arises. The Alpha has been around for, what, a decade or so now? Possibly the architecture is nearing the end of its life cycle, and if so no one is going to want to spend much to acquire it.

Anyone know how many more years they can squeeze hot stuff out of the Alpha? And is there any margin for cutting the price a bit?

--

TACO, NEED A (-1, Ignorant) MODERATION K THX BYE

[marxmarv]

True, they've got the PowerPC, but it wouldn't hurt them to have another product, particularly one that is used in the server market, where the PowerPC is virtually non-existant.

AS/400, you ignorant fool.

-jhp

When Alpha was sold to Compaq

[Oink]

Hmm, my original understanding was that as part of the deal with Dec Compaq was required to release much of the Alpha technology as public domain. Intel never seemed to take advantage of this, but where do you think AMD took a lot of their architecture design from? I could be wrong, but I recall this being the case.

Intel: Alpha vs IA-64

[NovaX]

My question is, why? I didn't believe this when I read it earlier, and still not now. The Alpha is a viable architecture, proven and powerful. Intel could gain patents and technology, but I thought these issues were, for the most part, resolved years ago in a secret settlement. Intel bought DEC's fabs, DEC dropped lawsuits against Intel over the P5 and other 'things.'

So Ace's says that the newest compilation of SPEC outperforms the Itanium (Merced). I think the Merced has a lot of potential, in the fact that it isn't the cleanest design (more of a proof of concept and a 1st attempt to learn from), and that I doubt the Intel compiler is very up to par. Yet it still gives an impressive performance, if you believe SPEC.

IA-64 and Alpha are both viable at scientific applications, and from the latest Compaq compiler, they are relatively equal in their current forms. The Alpha wouldn't die because of the 3rd party consortium (forget name: APR?). And I've read claims that many of the best engineers left when Compaq bought DEC and moved to AMD amongst others. So, what is the major gain Intel would get from this?


-----------------------------------------

Re:Intel: Alpha vs IA-64

[posm22]

>> My question is, why?

I don't know if this Intel buying Alpha rumor has any truth to it, but it does make some sense.

Alpha is the only viable competitive 64-bit microprocessor architecture to IA-64 (maybe the last possible mass-produced alternative to Intel-based architectures of any width). It has been working for a long time and it will be a very long time before IA-64 can catch up with it, at least if Alpha remains reasonably well funded.

Intel would substantially consolidate the market and remove the largest visible threat to its dominance by taking over Alpha, whatever it did with it afterwards.

There's a nontrivial chance that the Justice Dept would quash the deal on anti-trust grounds, though. That's still not a bad outcome for Intel; just by going through the buyout motions it will weaken Alpha whether Alpha stays with Compaq or goes elsewhere.

Re:Intel: Alpha vs IA-64

[jnew]

Interestingly, I was at a Compaq update last week, and there were pretty solid plans for the future of Alpha past 2010.

The VMS business is worth $4billion, and Tru64 is currently about $3.5billion...why would they want to go and port to a whole new architecture?

The presenter scoffed when asked about IA64, saying what an inferior architecture it was, and that the compliers would need years of work before they were useful.

So it will be interesting to see who is telling the truth.

Re:Intel: Alpha vs IA-64

[denshi]

HP teamed with Intel b/c the CEO-for-hire they had at the time tried to get the company to drop PA-RISC and HP-UX and move everything to Intel and WinNT (because that's the future!). I wonder in which class in biz school do they tell you to just drop 2 decades of engineering focus and end-of-life all your products at once. The predictable occured: all their server customers went to Sun, who was busy sucking up every internet customer around. Their 'high-end NT workstations' were massively undercut by, well, every PC clone maker in the world. Moral: value your uniqueness. The board managed to fire him in time to reverse some of the damage, but HP was been burned during the fastest growth period for Unix servers in years (possibly ever). They didn't need to before, but now they really need to honor those contracts with Intel.

As an aside, this same CEO-for-hire did the same manuver at SGI (end-of-life MIPS & IRIX, sell WinTel), with the same consequences. He's now working at Microsoft. It's a facinating biz study -- every commercial Unix vendor who partnered with MS & Intel was badly damaged (DEC was destroyed). Sun, who fought MS tooth and nail, thrived. Perhaps it's naive to follow behind WinTel...

Your link leads to a Beowulf integrator. If you work there, you understand the current limits of parallel processing, and the premium companies will pay for really high end equipment. Besides, the hardware is usually the cheapest thing in an organization. And what the hell are you talking about dumping Alpha when IA64 hits the street? Compaq's Alpha business is an 8 billion per year market. Most of those are big corporate customers who won't change platforms for 5 years minimum. Assuming they'll change over this fall presupposes the existence of your magical pet monkey.

Re:Intel: Alpha vs IA-64

[denshi]

Alpha is the only viable competitive 64-bit microprocessor architecture to IA-64 (maybe the last possible mass-produced alternative to Intel-based architectures of any width).

Umm.... Sun's UltraSPARC? SGI's MIPS? HP's PA-RISC? IBM's Power line? A swath of Japanese chips, notably Hitachi? With the exception of SGI, all of these seem to be doing fine. Even ARM is working on 64-bit. To my eye, the 64-bit conversion more or less where the field was before, with the exception of PA-RISC (which will be phased out after McKinley). The literature has been covering 64-bit issues for years now; It's not like one company is holding all the trade secrets. All the niches will remain where they are; the operating systems will carry over (presumably Windows will be 64-bit clean in 3 years). What makes you think IA64 is the end of the world in chip design?

Intel would substantially consolidate the market and remove the largest visible threat to its dominance by taking over Alpha, whatever it did with it afterwards.

Intel's largest visible threat to its dominance is AMD. I can't understand how you're missing that. They have chewed up more of Intel's market share than any competitor ever. And perhaps you aren't aware of this: a bunch of the original Alpha designers work at AMD now. So I'm not scoffing at the promises of their own 64-bit proc.

I just don't see any need for doom-and-gloom here.

Re:Intel: Alpha vs IA-64

[denshi]

It's very funny. Solely as a business decision, these manuvers were supremely moronic. Michael Porter (Harvard B-school professor) defines "strategy" as "doing what is necessary to become unique in your market." Belluzio (& similar folk) took the exact opposite approach, and paid for it. There's the obvious problem of MBAs failing to understand technical specialization, which is a rant that has no end, so I won't touch it. But yesterday a friend and I were talking on similar lines and I gained a new insight: biz school folk are taught 3 or 4 models, they drill those into them, and make sure they know them; but they are never taught tax -- the details of which can wipeout entire industries -- witness the yacht industry in the late 80's. The country is run primarily by biz types and lawyers who don't understand how their models actually apply in the real world.

So I can see that these types 'know' business real well. At least the small subset that they believe is the entirety of biz, and all hell is lose when the map doesn't match the terrain. If there's a moral here, maybe it's "never hire CEOs from outside".

BTW - UT Austin victim right here! Physics department, 99. What's your damage?

Re:Intel: Alpha vs IA-64

[mandarax85]

Knowing the Compaq (DEC) Alpha's ability to support PALcode in firmware to translate instructions from one processor to another, (this is how VMS was successfully ported to the Alpha from VAX) I don't beleive that the Alpha would be sold.

Rather than support a whole family of different architectures, I think that Compaq could successfully run all 4 from its family of operating systems (VMS, Tru64 UNIX, Windows, and the ex-Tandem NonStop OS) all running on Alpha based machines.

I know Compaq is seeking out a simpler solution, but I don't think selling Alpha, and thereby probably killing it, is a viable option.

Monoculture is a dangerous thing

[isdnip]

If Alpha passes to Intel, it is likely to be phased out -- Intel will milk it of its best technology, or at least of the part that they find compatible with their own rigid ideas, and scratch future Alphas. They want the team, but mainly to improve on IA chips.

This is dangerous, for the same reason that other monocultures are dangerous. Plant too much of the same "improved" seed variety and diseases/pests particularly suited to that variety will erupt/spread. Spread one architecture too far and good ideas from others will get lost, and progress will slow down.

Already we've lost lots of good ideas from the early days of computing. Some of the Burroughs CPUs of the 1960s had advanced features that modern CPUs would benefit from. Multics and TENEX/TOPS-20 had features that "modern" OSs, like the many variants on 1969's Unix, lack and could benefit from. The economic benefits of spreading one design (h/w or s/w) across many units usually outweighs the benefits of a better design. At least in the short term, but then we lose the long term benefits.

That's where Alpha got clobbered. DEC had no marketing skill. Alpha was DEC's fourth in-house RISC design (after SAFE, Titan and Omega, and those are only the ones I can remember offhand) and its designers learned a lot from the weaknesses observed in SPARC, MIPS (which DEC used for a while) and other earlier designs. Alpha has unique features. It morphs into a VAX, NT or Unix machine via a code layer that other CPUs don't have; Transmeta is not quite the same idea but at least has some parallels. Its floating point processor still blows the doors off of Intel's or even the superior AMD. It's a clean architecture, unburdened with IA-32's 8080 compatibility (itself a kind of PDP-8 heritage).

But none of that mattered; Alpha never got volume, so it was always a niche machine. VMS still has strong markets (read Terry Shannon's SKC stuff, for instance) and it depends on Alpha, but that's apparently not enough these days to sustain PC-centric Compaq. How sad.

Re:Monoculture is a dangerous thing

[Libertarian001]

Yes, Alpha still knocks the pants off of Itanic. The embarassing part about it for Intel is that the Alpha is doing it at "just" 833MHz. How "fast" was the Itanic going again?

Re:could be a backup strategy

[Tackhead]

> Alpha could be a good backup strategy for Intel: it's a more traditional architecture with lots of existing compiler backends.

OK, then, so why not have AMD buy Alpha, if for no other reason than to deny Intel access to it?

Both companies have about the same amount of cash. AMD may even have the stronger balance sheet than INTC. What's the Alpha division really worth? (And can it be bought for less, perhaps CPQ is open to selling it at fire-sale prices in order to clear the decks for their new "We can't beat DELL when it comes to moving hardware, so we'll sell support/services" strategy?)

Why Intel or AMD?

[cansecofan22]

I can treally see why either Intel or AMD would want to spend the $$ on Alpha. They both have there own 64 bit CPU's finished (or nearly finished). I would think it would be a lot of money to buy a product that would not be that useful to either company except to maybe get some ideas on improving there own chips. I dont think there would be a large market for the Alpha being that Compaq and DEC could do nothing with the chip. IThe only company I can think that might want it would be VIA so they could make an alternative to the Intel and AMD chips like they did with the Cyrix chips.

Re:Why Intel or AMD?

[kevinank]

DEC was renowned for nothing so much as their inability to market good products. Dunno about Compaq, but without an NT for it I can't imagine that they would know what to do with it (which probably explains this article).

Um... NT does run on Alpha in 32 bit mode. Not that it helps much since practically nothing else besides the OS runs on Alpha. Even Microsoft didn't bother to port their own apps to Alpha.

Re:Why Intel or AMD?

[jbridge21]

The original design life was 20-25 years. And those smart DEC people made sure that it was that way.

You can still get another good 10-20 years out of the Alpha....... I don't know what's gonna happen now, though.
-----

Re:Why Intel or AMD?

[Lord Kestrel]

But you're not in charge. AMD already lost out on it, so the next time you hear of Alpha will be when Intel releases the Itanium. Then all it will be is a blurb saying that Intel purchased the Alpha product from Compaq, and hence there won't be any competion for Intel.
---GEEK CODE---
Ver: 3.12
GCS/S d- s++: a-- C++++ UBCL+++ P+ L++
W+++ PS+ Y+ R+ b+++ h+(++) r++ y+

Re:Why Intel or AMD?

[VAXman]

Way back, in the early-to-mid 90's, Alpha was marketed as a commodity processor and a competitor to Intel. The project was started with this specific goal, and that's why FAB6 was built. It made sense, right? Alpha had 2x-3x the performance of the Pentium, was smaller (thus, cheaper to manufacture), and could run Windows NT. In the EV4 era, DEC marketed PC's with Alpha's running Windows NT (the DECpc, the Mutlia, and othered). For a long period, Linux on Alpha was considered to be a very serious threat to the Microsoft/Intel duo. Samsung, Compaq, and Microsoft (!) formed Alpha Processor, Inc. with the intention to manufacture Alpha in volume. Of course, EV5 and especially EV6 took Alpha completely out of the PC game.

But now Alpha is essentially dead, and any kind of commodity potential for it died long ago. The only customers which really depend on it are VMS customers, since it is the only architecture which that OS runs on (ironically, VMS is also one of the least performance sensitive markets in the world, with a majority of the customers still running VAX). (Tru64 has been ported to IA-64, right? Did Tandem ever switch to Alpha?)

Since Intel's and AMD's core competency is manufacturing high volume processors, I don't see why either would be interested in Alpha. Frankly, I don't see why anyone would be interested in Alpha. Its performance is reasonable, but it still outshined on most SPEC benchmarks by the Pentium 4, for 1/10 the cost. Furthermore, it has absurd power requirements. It has a long way to go before it can compete with IA-32 (or IA-64).

Re:Why Intel or AMD?

[Stephen Samuel]

> > DEC was renowned for nothing so much as their inability to market good products.
> Uh, I thought that company was IBM? ;-)

Actually IBM used to be able to market even bad products. Like Microsoft, they relied on their market dominance. Unfortunately for them, their dominance is only in the mainframe world. That's also the reason why the IBM PC became all the rage, as one friend of mine said at the time:

IT's got 3 things going for it ... 'I', 'B' and 'M'.

In truth, the IBM PC had little to go for it other than IBM's marketing muscle in the computer world. the 8086/8088 was essentially a 8085/Z80 with extra registers and hardware bank-switching. It was chosen (I think) because the architecture was so crippled that it was unlikely to become a threat to IBM's System/370 line of Mainframe boxes.

Yet it managed to become 'the industry standard'. Such is life.
--

Re:Why Intel or AMD?

[beefness]

AMD licenses the EV6 Front Side Bus on it's Athlon and Duron chips from Compaq, the bus was originally developed for the Alpha chip and even though AMD currently only uses it at 233Mhz, it can scale to 400Mhz which would suggest that it is a big part of AMD's roadmap.

If Intel had the patent, AMD would be Intels licensee, in the same way that AMD currently is with the x86 architecture. This means that they could increase the cost of the license and force the price of AMD chips to be more expensive. Intel could achieve more profit per chip by raising it's prices, and also make money on each chip AMD sells, this is any companies ideal position, make money on everything you sell, make money on everything your competitor sells.

I expect AMD to be the guys who purchase Compaq's Alpha division, if they dont, then they will be in an incredibly bad position, unless they can quickly move to a different Bus architecture (HyperTransport?), but I think this is unlikely.

Re:Why Intel or AMD?

[vsync64]

And OpenVMS.

--

Re:Why Intel or AMD?

[RedWizzard]

Also, parts of AMD's architecture has been converging with parts of the Alpha's (even on Athlons), so AMD might be able to integrate it into the high end of a "family" of processors.

Athlon and Alpha share the same front-side bus architecture. Chipsets for the two processors are potentially compatible (I've heard that people managed to get Athlon SMP systems working using Alpha motherboards). So AMD might be interested in the chipset technology that Compaq owns. OTOH they've repeatedly claimed to be uninterested in chipsets so maybe not. Might be a good move for VIA, as you say.

As far as processors go I don't think Alpha has much that AMD would want, technology-wise. However they are looking to get into the server market so they might be interested in Alpha's existing marketshare. It'd give them a good headstart.

Re:Why Intel or AMD?

[sunryder]

Perhaps Intel/AMD are simply tring to eliminate the possibility of a competitor. Or at least to eliminate someone else buying Alpha and turning it into a competitor.

Re:Why Intel or AMD?

[Billly Gates]

"I can treally see why either Intel or AMD would want to spend the $$ on Alpha."

The answer is simple. To eliminate the competition so the IA64 will seem faster. It is rumored that the IA64 workstations in use internally by Intel are already second generation. Even the second generation batch is too slow to bring out into the market. Especially with the alpha and the new sparcIII. If IA64 flops it will hurt intel for many years. To make sure it survives it needs to be the fastest available.Also wiht less supply their is higher demand so intel can rasie the priuces. Sparc systems are quite expensive.

The power users will oohh and ahh over it and buy it if they only see x86 vs ia64 benchmarks.

Intel could also boss around AMD because they use the alpha bus technology in their motherboards. So intel could stop innovating and save money by selling slower more expensive processors. Intel would have nothing to lose. I hate to seem like the pessimist here but corporations are greedy and doing bussiness deals with rambus and Microsoft may have looking at more hardball tactics. Intel may seem alot more gentle then these 2 companies stated above but they aren't excatly innocent in hardcore tactics.

I would hope apple would buy alpha. They can't compete when intel processors have 2.5 times the magahertz speed. Sure its comparing apples to oranges but Joe consumer and even ignorant IT managers don't know that. Yes, there are even some in IT who think magahertz is king. If apple can put some multimedia instructions into the chip like they did with the motorola G4, then they can have the fastest adobe photoshop workstation on the market. Motorola does not want to speed the chips up because they are greedy and do not want to upgrade their chip plants.

Re:Why Intel or AMD?

[driftingwalrus]

x86 has been around for a good 20 years, and alas, shows no sign of dieing soon....

Re:Why Intel or AMD?

[Veteran]

When Apple went with the Power PC the decision almost put them out of business. Why? Because there was no software for their new chip. They had to do with kludges like emulating the 68K in order to have anything running.

When you change chip architectures you have to run in place for years just to get back to where you were before.

As Intel is discovering with the Itanium writing state of the art compilers to support a new architecture is a very difficult job.

If processor manufacturers switched architecture every few years like you seem to be suggesting then software adds would look like this:

Gamesoft announces PONG for the Snazoid 2010

WooHoo.

Doing things like arbitrarily switching processor architecture just because you can is adolescent "I have no clue how the universe actually works - so I am randomly trying things until I find out what is going on" behavior.

Re:Why Intel or AMD?

[mazor]

Um... NT does run on Alpha in 32 bit mode. Not that it helps much since practically nothing else besides the OS runs on Alpha. Even Microsoft didn't bother to port their own apps to Alpha.

NT runs on Alpha in 64 bit mode. The Alpha chip doesn't have a 32 bit mode. The NT kernel only recognizes the low 32 bits of pointer values for the normal kernel-managed page-swapped virtual address space, but native compiled Alpha apps can access more than the 2GB of data by calling special allocator functions in a support library shipped with the Alpha version of NT. Memory above the 32 bit address space is not page swapped, it must reside in physical RAM.

Other than the memory addres space being squished to 32 bit for normal apps, native compiled code running under NT on the Alpha chip is fully 64 bit code.

Yes, application availability was a major stumbling block for the Alpha back in the days when DEC was grooming it to be a major contender. However, I seem to recall that MS SQL Server was available as a native executable on the Alpha, and of course all the server chunks that shipped with the OS were native, such as COM, DCOM, and IIS. Solitare and the Space Cadet pinball game also ran native. I'm pretty sure there was an Alpha version of MS Word as well.

The only reason NT 4.0 for Alpha didn't make it out of beta was that Compaq laid off the DEC staff in residence at Microsoft that did the actual work of porting and supporting NT on Alpha. NT has run on several hardware platforms over the years, but the only one done by Microsoft was the Intel version of NT. MIPS, Alpha, and PowerPC versions of NT were all funded by the hardware vendor in one way or another.

--mazor

Re:Why Intel or AMD?

[Libertarian001]

"Anyone know how many more years they can squeeze hot stuff out of the Alpha? And is there any margin for cutting the price a bit?"

The current roadmap shows an additional 25 years, taking the chip up to EV12 (currently EV6). As far as pricing goes, it's simple: They cost a lot now because Compaqs goal is not market proliferation, but exacting the highest possible profit per chip that they can (IIRC, in Economics there's a couple equations you use to set a products price. One of them maximizes sales, the maximizes profits).

Also, look at how the chips are currently being fabbed, in .25um 6-layer CMOS. This isn't particularly asonishing, and the chips are currently 225mm2. If I were in charge, I'd have IBM (who is already fabbing them) fab in there CMOS-9S process. This is a .13um, Silicon-on-Insulator, Copper interconnects, low-k dialectric process that can be used in up to 9 layers. The chip would now be ~ 78mm2. That's a smaller than anything else in the desktop arena and would dramatically shave prices. It would also ramp the clock up to well over 1GHz, probably around 1.6GHz, and would consume under 90W (probably around 70W).

Considering that tick for tick the EV6 is twice as fast as a Thunderbird, anyone want to comment on how fast a 1.6GHz Alpha would be?

Then you could be like Samsung and make a 760-based MB for it, or go a step better and make an nForce-based MB for it. Of course, if you changed the packaging from 587-pin to 462-pin (and all these extras are power & ground, which can be trimmed if done right) then you wouldn't have to make any special MBs for it, just make a special BIOS to use it in any current/forthcoming TBird MBs.

And run AlphaLinux.

That's just what I would do if I was in charge.

..

[vbrtrmn]

I guess that Compaq hopes to make a lot of money in the consumer market selling their ghetto-ass PC workstations. I'd personally rather buy a Packard Bell or an Acer than a Compaq! Doesn't look like Packard Bell is doing business in the states any more, I guess it is up to Acer.

--
microsoft, it's what's for dinner

bq--3b7y4vyll6xi5x2rnrj7q.com

Re:Motorola?

[rjkimble]

Maybe, but then wouldn't Motorola have to go against their endiadness philosphy? I think religious wars have been fought over less substantial differences of philosophy.

All Your Base Are Belong To Us!!!

And in my email appears...

[yatalung]

Dear Compaq HPS customer,

Please see the attached note from Compaq's Area Director for North Atlantic. I will follow-up during the week to see if you have further questions.

URL for customers for Monday's webcast.

The following URL has been provided to us by Corporate for you to communicate to selected customers who would like to participate. The time of the webcast is Monday, June 25 at 9:00am Eastern time.

URL http://webevents.broadcast.com/compaq/PressAnnounc ement

Re:Desktop market?

[supersnail]

All recent IBM AIX|AS/400, all recent sparcs from sun, plus all Nintendos and Sony PS/2 are running 64 bit chips.

Its the Wintel dinosaurs which have fallen behibd.

Incidently (I know it was mentioned in passing be another poster) Intel bought the alpha FAB from DEC, all current aplha chips are manufactured by Intel, the latest Alphas were largley designed by Intel engineers, it makes sense for Intel to own the archirecture outright.

What compaq owns is the VMS and Tru64 operating systems and associated software.

The answer is obvious...

[vague]

It's just gotta be Amiga Inc (or whatever they're called) :) The beginning of a new end far away from the mass market for two arcitechtures that should have been but never were.

A match made in heaven if I ever saw it =^)

-

Expect an Announcement on Friday

[Constellation]

I'm working on a super computing project up here in Canada, known as SHARC-Net. It is a group of Beowolf clusters (using Alpha's, with all the hardware supplied and serviced by Compaq) located at 3 different universities (as a side note 2 of the clusters run Linux and the other Tru-64). The project directors had a conference call with Compaq on Friday, for which they had to sign NDA's. When the Director for the University of Guelph came out of the conference call she was very unhappy with Compaq. She told us this:

1. Compaq will be announcing to the world what they discussed on Friday.
2. It won't effect us until 2004 (which agrees with the article).
3. Had they known about this earlier it could have effected their choice of supplier for the clusters.

This is very little to work with but it does agree with the article. Needless to say, may of Compaq's customers are very unhappy with them right now (including us as we are just now bringing these clusters online).

Re:Compaq's World Domination Strategy

[n9fzx]

You forgot:

• Give the world's best search engine to someone who only knows how to sell consumer PCs, and who brags that he "doesn't know anything about the Internet".
• Give said CEO a billion in cash to waste on bad acquisitions and an unneeded advertising campaign in order to boost the stock valuation.
• Stand by as $3 billion in value is destroyed by lack of capital investment in the core business.
• Dance around the fire at night chanting "Smart is Beautiful!"

Alpha was the great architecture that blew everything else away, but thanks to the guys in Houston, we're left with the One True Architecture. Bah!

"The 80xxx series of microprocessors is clear evidence that INTEL isn't doing in-house drug testing." (Usenet, 1988)

AMD?

[Perdo]

Wasn't the entire alpha design team head hunted over to AMD? I think that is why the athlon uses the EV6 bus. The original alpha chip, designed by the guys that are now at AMD, is still the fastest processor on the planet. Seen their Seti
results? 59 minutes to do what takes my 1.4Ghz athlon 1 hour 50 minutes to do (old client, ars's benchmark unit).

Re:Desktop market?

[cant_get_a_good_nick]

Maybe Gnutella would be scalable if we all were packing them.

Gnutella's scaling issues were bandwidth, not processor based.

Worst Tux ever!

[RatFink100]

OK this is offtopic but I was checking COmpaq's site for news of this and came across this monstrosity!

http://www.compaq.com/alphaserver/news/linux_aff in ity_0601.html

It's the worst Tux logo I've ever seen!

Re:What about Apple?

[Quila]

It won't happen for the same reasons that Apple didn't go to the IBM POWER architecture -- they need a chip they can run in their desktops and their notebooks. The PPC has a very good power/performance ratio, but can you imaging a notebook with an Alpha or a POWER 4?

convergence to IA64

[red_crayon]

There is a strong industry-wide convergence to the IA64 platform...
it's too expensive to roll your own processor platform anymore.

The Compaq decision is not surprising. Look at the other current makers
of 64-bit hardware:

SGI: uses MIPS, but also converting to IA64. And, based on
the current business environment, will we soon read "Silicon
Graphics R.I.P. 1982-2001"?

H-P: PA-RISC, but also involved w/Intel in IA-64 development.

Sun: OK, well, these guys are still holding out w/SPARC.

IBM: POWER, but interested in IA64, particularly wrt Linux.

They really did it!

[yaba]

Compaq did it. It's no longer a rumor. Read the press release on Intel's web site: http://www.intel.com/pressroom/archive/releases/20 010625corp.htm

Re:They really did it!

[tb3]

Wow! There's so much spin in that press release I feel dizzy. They really want you to believe it's a "Good Thing" (TM).

"What are we going to do tonight, Bill?"

Motorola?

[sacremon]

Let's not forget Motorola. True, they've got the PowerPC, but it wouldn't hurt them to have another product, particularly one that is used in the server market, where the PowerPC is virtually non-existant.

Motorola is primarily an embedded processor maker, and perhaps the Alpha can see some life there as well.

Re:Motorola?

[Libertarian001]

Hunh?! PowerPC is derived from Power, not the other way around. One of the reasons IBM didn't want to jump on the AltiVec bandwagon is because Power already has a phenomenally powerful FPU. They sell Power in the high end (as you said, AS/400s and RS/6000s) and PowerPC in the low end, where they don't need FPU strength as much. Adding AV was counter-productive as far as they were concerned.

What about Apple?

[Maskirovka]

Given the problems they've been having the the PPC, the alpha might be a viable alturnative. I'm not talking about switching over to it instantly, but over a couple of years phasing out the G3 and G4s. There won't be a 64-bit PPC processor for at LEAST a couple of years. If they were to buy it within the next couple of months and start selling alpha systems about year for now, the mac community will be used to the bugs and changes from OS X that it won't make a difference. Too bad it won't ever happen...or maybe not?

Maskirovka

--
Smith & Wesson: The original point and click interface.

Desktop market?

[ImaLamer]

Is there or will there be a desktop market for this chips? I've been reading about 64-bit chips [here and there - never got into them] for years now, but yet I see no 64-bit machines.

I never have even seen an 'enterprise' computer so I have couldn't even say this machines exist, but are they ever going to be desktop machines?

They do run linux right? I've seen that directory in /arch/ before. What is the chance of us getting them into the mainstream? Wouldn't they rock at 3d games and what not?

Maybe Gnutella would be scalable if we all were packing them.

I guess I'm really a lamer since all my experience is with x86 crap.

Re:Desktop market?

[Libertarian001]

"Incidently (I know it was mentioned in passing be another poster) Intel bought the alpha FAB from DEC, all current aplha chips are manufactured by Intel, the latest Alphas were largley designed by Intel engineers, it makes sense for Intel to own the archirecture outright."

Uhh, no. Alpha chips are currently fabbed by Intel, IBM and Samsung. Intel stole design secrets in the current (EV6) Alpha, not developed them.

Re: "Only 833MHz"?... Itanium runs at 800MHz...

[Glasswire]

Not sure what you mean when you say it's impressive that Alpha is beating Itanium on floating point (not conceded by me BTW) at only 833MHz, when the first Itanium rev is running at 800MHz.

I was impressed by some of your comments on fab technology, so this lapse is perplexing...

Itanium will run faster and if future verisions at or beyond Madison/Deerfield have input from Alpha designers, it's likely some Itanium will be the fastest FP.

Don't forget

[blair1q]

Intel only owned the parts of Alpha that it already owned because Intel was already using Alpha technology in its chips.

Remember that Intel and DEC settled DEC's infringement suit when Intel bought the Alpha lines.

That same agreement multi-sourced Alpha at Samsung, AMD, and IBM. So there was and is no danger of Intel's monopolizing Alpha.

Compaq then bought all of DEC, and ended up owning whatever Intel didn't buy. Naturally, that sounds like an inefficiency. Compaq can't handle inefficiency. Intel is organized to mediate inefficiency and even find ways to profit from it (they build a fab for one chip partly on the premise that once that chip is done in the market they can use the fab line for less-mainstream products; they've done this for 30 years; some lines are designed knowing that their primary product--this year's desktop chip, for example--will never be enough to pay the mortgage; it's a gutsy and thoroughly pro move).

--Blair

Wild guess

[Ayende Rahien]

Microsoft will buy it, turn into a hardware company, and release all their software as GPL.

--
Two witches watch two watches.

Alpha will stay around for ten years or so.....

[anonymous cupboard]

One of my clients is the systems division of an financial securities exchange. The host and intermediate layers run on OpenVMS/AXP clusters. This thing needs uptime and message passing (not byte streams). Porting would be a major headache, whether to Windows or to Unix. Incidentally the code base on the VMS side is Cobol, C, Fortran, Pascal.

Another major client is the US military, they also have a bag load of applications that just won't port easily.

The implication is that if Compaq pass the technology on, the customer (Intel) will have to continue to produce so that Compaq can fulfill its high-end systems contracts.

What attracted Compaq to Digital was not Alpha, it was the Digital service infrastructure and the client list for high end systems, who they hoped to be able to sell PCs to.

Compaq PCs had a number of problems that didn't endear themselves to corporate customers, so this never really worked. Even though these issues seem to have been largely addressed (however, my little Ipaq illustrates the bad QA that Compaq has suffered from).A good little beast but let down by a losy sound jack that is being echoed by many other users.

Don't worry about AMD...

[Glock27]

I listened to the entire webcast, and it was made clear that this was a non-exclusive technology license for Intel. That means EV6, HyperTransport and other Compaq technologies currently being used by AMD will be unnaffected.

The one thing that AMD probably isn't too happy about is that this announcement made it clear that Compaq doesn't expect to be doing Sledgehammer (Athlon64) servers...and no doubt Intel will make "an offer they can't refuse" to keep it that way.

186,262 mi/s...not just a good idea, its the law!

Re: "Only 833MHz"?... Itanium runs at 800MHz...

[Libertarian001]

I couldn't remember what speed Itanium was running at. I assumed (thus making an ass of myself) that it was in the 1.5GHz range.

Also remember, we're talking about a 5 year old chip here vs something "brand new."

Try this on for size. Take the EV6 core, remove the 128KB conventional L1 cache (9 mil trans), now we're down to 6 mil trans. Have MoSys add 128KB 1T-SRAM (1.1 mil trans) L1 and 1MB (8.8 mil trans) L2. Now we're back up to 15.8 mil (.6 mil higher than we started with) and have gobs of super hi speed, low latency cache. Now we fab it in IBMs CMOS-9S in a 9-layer process at .13um. We've got an 82mm2 chip now, probably running at ~1.6GHz.

The EV6 Bus scales to 400MHz. It's sitting at 133 right now. So make the jump to 400MHz. Alpha is used to having 128bit or 256bit memory subsystems, right? So you make a new memory standard and screw JEDEC. Samsung just released 300MHz DDR SDRAM, they'll hit 400MHz in the next 1-2 years. This stuff is normally used for video cards, right? Ah, but it's intended for 128- or 256bit systems and has a hi-speed serial connect, perfect for our needs. All you need to do is design a new memory controller (which a friend of mine is doing) for this.

That'd make for a pretty bloomin' fast h/w setup. But it's not h/w alone that make a computer tic, you still need s/w. So pick an OS, like AtheOS (which would need to be ported, but it's a pretty small OS still) that has all the features you want and go to town.

But as someone else was kind enough to point out, I'm not in charge.

Compaq's World Domination Strategy

[zero2k]

:-) Compaq has a strange way of trying to grab the market. I believe they want to only rid the world of DEC. Let's see:

• Buy a high-tech company that produces products far superior to anything available (DEC).
• Attempt to stop supporting an OS that presumably no one uses except for large organisations that'll pay heaps to continue the product(VMS).
• Change the name of an OS that kicks ass to Tru64 which no one cares less what the Tru means. It's freagin UNIX for goodness sakes.
• Start kicking off people with the know how who have been researching vigorously to create new products (original DEC employees).
• Hire a whole bunch of loooozers who know nothing except marketing ploys and new starters who have never worked with real tech before (a whole buncha WinDoze Luzers)
• Kill off Alpha, because it's no longer a fad when it's really a killer platform.

I hate Compaq! Die! Die! Die! Compaq

could be a backup strategy

[m08593]

I think Intel's IA-64 architecture is in more trouble than people think. It puts a huge burden on the compiler. While you can probably get good performance out of it for benchmarks in Fortran and C, things get iffier once you are talking about real applications and other languages. Who is going to write all those high-powered backends?

Alpha could be a good backup strategy for Intel: it's a more traditional architecture with lots of existing compiler backends.

What about

[Gazelem]

Transmeta perhaps?

Re:What about

[pumkinut]

Probably not since Transmeta is in dubious financial state right now. I've actually heard rumors that AMD might be interested in them.