End Of The Line For Alpha 514
Scareduck writes "Infoworld reports HP has released the last iteration of the Alpha chip. I used these babies in the late 90's, and for a time, they were da bomb. Sadly, the economics weren't there, DEC management really didn't have much of a clue, and Alpha has, at long last, bit the dust. Alpha-based servers will continue to be sold through 2006, and supported through 2011. Farewell, Alpha; the world's line of chips seems to have declined to Intel and a handful of niche guys." Slashdot ran for the first 7 or 8 months off an Alpha box.
At last... (Score:1, Insightful)
Niche guys.... (Score:3, Insightful)
AMD (Score:4, Insightful)
only intel? (Score:5, Insightful)
Will anyone actually be *using* this? (Score:5, Insightful)
Of course, that's just my opinion, and business decisions rarely make much sense
Re:Sad (Score:5, Insightful)
And who knows what the future will bring? AMD may diverge so far from Intel that they may eventually be considered their own architecture.
I think the chip market is about as dead as *BSD (*according to Netcraft.)
Don't forget PowerPC (Score:5, Insightful)
Re:amd is niche?? (Score:3, Insightful)
I guess the poster's point was that there aren't any widely-used architectures out there besides the x86 stuff, which was originally developed by Intel, was a solely Intel offering for a very long time (close to 15 years, I think), and which is still synonymous with Intel. Despite the fact that AMD, VIA, and a couple of other outfits make x86 CPUs.
What's Changed? (Score:5, Insightful)
We still have Itanium, two Sparc variants, a number of Power variants, Transmeta, Opteron, and whole bunch of other niche processors, most of which probably have more market share than alpha.
Re:Heh (Score:1, Insightful)
Long live NetCraft jokes!
Reminds me of CISC vs. RISC debate (Score:3, Insightful)
In the early 90s, there was this hot debate about RISC vs. CISC, and the merits of each, ...etc.
This has all died out now, with CISC (read: Intel) coming out as a winner.
Regarding the number of chips out there, AMD is not really different from Intel, at least it is instruction set compatible. Maybe this will change a bit in the 64-bit versions, but not right now. PowerPC is a good architecture, but not so wide spread. Outside of some IBM servers, and the 3% that is Apple's share, they are not used much.
What's so bad about x86? (Score:3, Insightful)
Think about how many Intel Xeons you could get, on 9xx chipset mobos, for $30,000. If you built them yourself, probably 15-20. Is one (or four) 1.5 GHz Alphas are more useful than a cluster of 20 Xeons? Hell no!
See, ever since Intel lost their de facto monopoly on powerful x86 chips (thank you, AMD!), their prices have dropped far enough that it's hard to beat x86 solutions on a price vs. performance basis. Even if you have to stack up more boxes in a rack to do it. Hell, Quad-CPU Xeons can still go for less than $6,000, if you build them from parts, so rackspace isn't really an issue.
The whole idea is crazy (Score:2, Insightful)
I don't get it.
Oh, where is ObviousGuy [slashdot.org] when we need him?
Re:Niche guys.... (Score:5, Insightful)
The fact that AMD seems to be getting the upperhand in driving x86 technology doesn't change the fact that there is one technology which dominates the market, and everybody else either controls a nice slice with another technology, or competes with the major x86 player in a more specialized niche.
Alpha is dead, UltraSPARC is in doubt, and Via seems intent on shoving ARM out of the market. m68k is an abberation. There are two battles left. The battle of the archetecture (x86-64 vs POWER5/PowerPC), and the battle of x86 innovation (AMD vs Intel). That's sad.
Re:Sad (Score:5, Insightful)
As far as AMD goes, they did a damn fine thing with AMD64. Hopefully they keep it up and keep diverging from intel, while still offering a cheaper and (in some cases) technologically superior competating product. I would hate to see the day when Intel really does own the processor market.
Re:Cost of the servers (Score:4, Insightful)
(Though to be fair, Itanium 2 was a lot better
Microprocessor Report (Score:5, Insightful)
Alpha was a Risc chip's risc chip. The IBM Power architecture has dozens of operations and permutations; the Alpha has a handful. This contributed not only to the Alpha's speed, but also to its insatiable demands for memory. DEC introduced a code-translator that allowed the Alpha to run x86-32 binaries at native speeds, but warned that memory requirements would grow substantially. The software never became cost effective.
But, towards the turn of the millennium, something strange happened: the Pentium Pro architecture (happily renamed PII and PIII) inched towards the lead in integer operations. The P4 actually surpassed the Alpha chips. Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies. How could Intel catch up to the Alpha when Intel was burdened with an architecture as convoluted as x86?
Strangely, the x86 architecture can also be a benefit to chip design. Because x86 compresses commonly used instructions into tiny, awkward byte codes, the P4 generation of chips requires less memory and fewer cache misses - and the convoluted opcodes can be decoded quickly by the processor prior to dispatch. In the long run, Alpha's simplified instruction set proved to be less useful than machine-code x86 compatibility; and x86 chips are now little more than Alpha chips sitting behind an x86 instruction decoder. The Alpha design lives on in every CPU you buy, whether it be AMD or Intel.
For further reading, check out CPU performance numbers on http://www.spec.org [spec.org] and read the commentary on Microprocessor Report [chipanalyst.com].
Re:Will anyone actually be *using* this? (Score:3, Insightful)
Re:Reminds me of CISC vs. RISC debate (Score:4, Insightful)
Much of the lower level workings of "IA-32" chips are a lot more RISCy than they started out being. More complex instructions are implemented in microcode. On the flip side, architectures like PowerPC (and even SPARC
Neither side won absolutely. This is probably as it should be.
Re:only intel? (Score:5, Insightful)
Intel ships 1 million Prescotts a week(http://www.xbitlabs.com/news/cpu/display/200
That's probably more volume in a single week than the entire IBM + Sun + Alpha volume for an entire year.
Why is this the case? It is RIDICULOUSLY expensive to manufacture CPUs in this day and age. If you DON'T ship on the order of 1 million a week, you will never recover the costs necessary to build the all of the fabs.
This is why Sun will eventually abandon SPARC. This is why IBM loses money in their microelectronics division, but will probably maintain POWER and eat the costs for strategic reasons. This is why HP/SGI and others have gone with Itanium.
This is not to discount the technical acheivments of the these CPUs. I design processors for a living and have great respect for the Alpha design team. But at the end of the day, the only reason someone is going to fund the design a computer is to make money. Only the profitable survive.
Re:Sad (Score:5, Insightful)
Just started our last lease VMS on Alpha's (Score:4, Insightful)
Have run alpha's for a long time, and they are still screamers. Problem is, you'll scream, then have a heart attack at the HP prices. Our current environment mentioned about was around $1.5M.
Re:Will anyone actually be *using* this? (Score:3, Insightful)
Only that (1) Alpha still has more than good enough performance, (2) you stick to what you already have working, (3) competitors don't have yet a compelling story on the viability of their RISC offerings, (4) going Intel feels like downgrading, (5) HP's migration proposals are still ridiculous, because (a) there is no good substitute for Digital Unix yet, HP-UX being much inferior, (b) no one believes in Itanium.
Re:Sad (Score:5, Insightful)
It's truly scary how the Intel is becoming the only mainstream chip architecture left alive.
That dominant 386 instruction set has grown larger than life, threatening even Intel, who was responsible for its initial creation.
Intel's Itanium line has been a business flop, while AMD stuck to x86 compatibility in its K8 x86-64 development and is thereby is making inroads into Intel's market.
The realities of a market demanding
it wasn't management that failed, it was marketing (Score:5, Insightful)
And that was on a good day.
Yes, there were certainly some engineering and management blunders (mostly management) but Marketing was completely inept.
During the 70s the PDPs practically sold themselves, and during the 80s VAX literally sold itself; it was the hottest thing you could hope to get. So when the big Unix wave came, with its cheap-ass Sun hardware, and so-called software compatibility, the Marketing droids could not cope, and the former #2 computer manufacturer is now just a zit on HPs ass.
Do I sound bitter? nooooooo.......
Re:Will anyone actually be *using* this? (Score:4, Insightful)
True, it's a dead-end choice, but one that might limp along for another 6-8 years. Not everyone has the option of migrating NOW. That works if you're talking about tru64/apache to linux/apache, but not if your talking about tru64/Legecy-app-from-company-no-longer-in-busine
My call is that makes lots of sense.
"Niche guys"? (Score:5, Insightful)
Didn't know that AMD is out of the game now. Guess they don't sell 64bit CPU's anymore...but we got those 64bit Intel chips in everything now don't we? Whoa...look-at-em go!
I also didn't hear that the PowerPC architecture was all gone too...guess they're just selling what little inventory they have to the "niche" Apple market...but everyone know's that Apple's dying....any...day...now....
Pfft...the submitter should remove head from rectum...
Re:Barely Knew Ya... (Score:2, Insightful)
VAXes (surprise, surprise) had VAX CPUs, not Alphas.
They had to rename the operating system from VAX/VMS to Open VMS/VAX and OpenVMS/Alpha.
Kids today... I'm surprised no-one's made a comment about Pentium-powered PowerMacs or something equally non-sensical.
Re:"Niche guys"? (Score:5, Insightful)
Of course the power of the various embedded processors (Dragonball,StrongARM) and single-chip computers are rising to the point that they could be meet most user's computing needs. We've reached the point where average users don't need any more power; they need the same power with less heat & noise and more reliability & stability.
Marketing (or the lack of) killed it. (Score:2, Insightful)
I really wanted some of these babys.
I suppose my problem was that I wasn't a huge OEM. Let that be a lesson to those marketing folks: kill the hacker market, and your technology isn't going to prosper as much as it should.
Re:Sad (Score:3, Insightful)
Competating is kind of a neat sounding word, though.
Re:Sad (Score:3, Insightful)
Half right. (Score:4, Insightful)
Compaq dragged their heels on following Digital's development plan, and then pronounced its doom suspiciously close to the HP acquisition. Compaq *could* market, and if Compaq had understood what they'd got from DEC and really worked on expanding the Alpha business instead of going toe to toe against Dell's lower margins they and the Alpha would probably still be in business.
Mentec, who *did* understand what *they* got from DEC, is still selling PDP-11s.
Instruction sets have been marchitechted out. (Score:5, Insightful)
Sure it does. The further the instruction set is from what the processor's doing internally, the more time it takes for the front end to feed reordered instructions or recompiled instructions to the real ALU. The more time it takes, even if it all happens in parallel, the more latency there is between instruction fetch and useful work. When you combine that with a small register file that requires extra copies in and out of cache, even if that's simulated by a top-of-stack cache, you end up with huge pipelines and lots of instructions (real instructions hitting the internal ALU) that are just doing busywork.
The longer pipelines you need to implement these inappropriate instruction sets means that cache misses and branch mispredictions are more expensive, because they cause huge bubbles in the pipeline and lots of wasted instruction cycles.
Which means that your processors are running faster and hotter than RISC processors that do the same work
And that's why *despite* having a fraction of the resources directed to it than Intel or AMD have spent on their monster chips, and despite real neglect even before its doom was pronounced, the Alpha was still the fastest kid on the block right up until the day when, shortly before HP bought them, Compaq announced they were shutting down the EV8 development and terminating the Alpha line.
No, a superior instruction set helps a lot. Not enough to satisfy Compaq, clearly, but more than enough that if Compaq had understood what they'd got from DEC and stuck to their original plans... instead of trying to outslug Dell on its own turf... EV8 would be the fastest chip on the market today.
Re:"Niche guys"? (Score:3, Insightful)
So fundamentally flawed, in fact, that x86 CPUs are the highest-performing, most compatible CPUs in the world.
Seriously, who cares what the hell your code compiles to anymore? What's wrong with x86?
Re:only intel? (Score:3, Insightful)
"In the first quarter of 2004, IBM Microelectronics lost about $150 million" -- Source http://www.infoworld.com/article/04/04/21/HNibm_1
IBM makes several billions in profit per year. A 150 million per quarter loss isn't going to bury them.
Re:"Niche guys"? (Score:5, Insightful)
In Three words: Variable Length Instructions
The RISC guys had it right. So right in fact that even current x86 chips are RISC on the inside, and then waste close to half their transistor count on circutry that does nothing besides transform the x86 instruction set into something that isn't brainfucked. That Athlon-64 would cost half as much, draw half as much power, and generate half the heat if you ripped out the x86 emulation layer.
Re:"Niche guys"? (Score:3, Insightful)
Re:Sad (Score:3, Insightful)
emt-64 is an amd-64 compatible extenstion to the P4. How is it fake 64 bitness unless Opteron and the A64 line are also fake 64 bit nonsense?
Or are you refering to Itanium? Last check, it was a fully 64 bit capible sysetm, no signs of 'fake 64-bit nonsense' there either.
Geez, if you're going to troll, atleast do a good job at it.
R.I.P. (Score:3, Insightful)
Re:Reminds me of CISC vs. RISC debate (Score:3, Insightful)
Oh, and supers had pretty aggresive modified OO and Tomasulo's like units way before the P6, and they did it FAST too.
So what was your point?
Re:"Niche guys"? (Score:4, Insightful)
Re:Reminds me of CISC vs. RISC debate (Score:3, Insightful)
To bring this back on topic (if only slightly), it's a damn shame about Alpha, but not so much, really. All of the RISC architectures looked pretty similar (unlike the CISC ecology before them). If the surviving RISCs are not quite as elegant as Alpha, at least they illustrate the same basic simplicity and orthogonality. The survival of x86 proves that you don't need a perfect architectural design to achieve high performance (at least not on integer code, and not if you have more money than God), so POWER/PowerPC, MIPS, Sparc and ARM should have few difficulties in the years ahead, despite minor architectural flaws. (actually, I'm not too sure about Sparc's continued survival, but I wouldn't shed a tear at it's demise: register windows are an abomination) IBM has already had to employ PPro-like tricks in the recent POWER5/PPC9xx designs in order to get high performance.