End In Sight For Alpha

← Back to Stories (view on slashdot.org)

Posted by ryuzaki0 on Thursday December 5, 2002 @08:17PM from the out-with-a-bang dept.

minektur writes "news.com has an article stating that DEC ... I mean Compaq .... Uh, I mean HP has decided to EOL the once mighty Alpha architecture. Let's all take a moment of silence." I was lucky enough to have access to a 533 MHz Alpha back when the fastest Pentiums were only around 200 MHz, and the Alpha architecture earned a special place in my heart. It will be missed.

9 of 422 comments (clear)

Min score:

Reason:

Sort:

Still lives within the EV6 AMD Athlon... by SirDaShadow · 2002-12-05 20:22 · Score: 5, Informative

AMD sure had it right with its decision of making the Athlon Architecture based on the Alpha...to the point that it outlived the Alpha itself...
1. Re:Still lives within the EV6 AMD Athlon... by kc8apf · 2002-12-05 20:52 · Score: 5, Informative
  
  The speed increases on the p4 is due to the use of a 22 stage pipeline. The Athlon and Alpha do not have nearly that long a pipeline and as such do not scale in Mhz as easily, but they get more work done per clock, hence why a slower Athlon is on par with a p4.
  
  --
  kc8apf
2. Re:Still lives within the EV6 AMD Athlon... by Anonymous Coward · 2002-12-05 21:16 · Score: 5, Informative
  
  AMD sure had it right with its decision of making the Athlon Architecture based on the Alpha...to the point that it outlived the Alpha itself...
  
  They only licensed the bus architecture. Nothing else...
3. Re:Still lives within the EV6 AMD Athlon... by Chasing+Amy · 2002-12-05 21:30 · Score: 5, Informative
  
  This is true, but hyperthreading seems to have great potential for fixing the weaknesses inherent in having such a long pipeline. Few apps have specifically been optimized for it yet, but even so it provides a small to large increase in productivity depending on how many threads you have going at once and how much each app is optimized for hyperthreading or dual processors. The benchmarks posted at places like Anandtech and Tom's Hardware demonstrate this, even at this early stage.
  
  Add to that the fact that Intel is pushing for developers to compile using optimizations for hyperthreading and dual processors, and to make apps more multithreaded, and you get an even greater likelihood of performance increases in the future. The cost of that long pipeline is clearly being lowered, and P4 with hyperthreading can get more done per clock cycle than the P4 without.
  
  I was one of the people who laughed at Intel when the P4 was released in its original incarnation, believing the Athlon's Alpha-like brute force would continue to trounce the comparatively puny NetBurst architecture at every turn. But in the end, the larger cache, faster FSB, and now Hyperthreading ability of the newer P4, seem to be adding up to be just as valuable as the P4's GHz scalability.
  
  All I can say is, brute force doesn't seem to cut it any more. Intel is finally improving the little things, and not just clockspeed. The fact that next year Intel is planning to move to an 800MHz effective FSB with matching dual-channel 400MHz DDR memory just goes to show that. Who ever would have thought? :-)
  
  --
  
  Chasing Amy
  (We all chase Amy...)
  "The more corrupt the state, the more numerous the laws"-Tacitus
Re:Alphas by kc8apf · 2002-12-05 20:54 · Score: 5, Informative

Which is now known as Tru64. Of course, depending on what manual page you look at it, the name varies from OSF/1 to Digital UNIX to Tru64.

--
kc8apf
Re:The day of a single very powerful CPU is over.. by anonymous+cupboard · 2002-12-05 21:27 · Score: 5, Informative

Um, the Alpha was ideal for that. Dick Sites, the main architect used to work for Cray and he used a lot of ideas to make Alphas work well together. You want 16 processors, it will do it and do it well.
Re:you know -- the current generation still rule by pesc · 2002-12-05 22:15 · Score: 5, Informative

Loosey operating systems. ULTRIX was immature and buggy

AFAIK, Alphas never ran Ultrix. They ran OSF/1 (later renamed Tru64). The first true 64-bit OS released 10 years ago which still beat newer attempts in good, clean 64-bit design (including, for example, HP-UX).

VMS was VMS (some people love it, not sure why)
They run it because of the reliability and clustering capabilities. Which VMS had 15 years ago and no UNIX yet has emulated...

It was a memory hog. With a "int" set to 64 bits as standard
No, an int was 32 bits. A long (and void*) were 64 bits, just as it SHOULD be.

See LP64

and each machine instruction taking up a lot of room (256 bits I think)
Have you ever used an Alpha? Each instruction is 32 bits long.

--

)9TSS
Re:A true shame... by evilviper · 2002-12-06 01:24 · Score: 5, Informative

Alpha gets added to the list of failed, technicaly better products.

No kidding. I really can't imagine why it is being dropped. I'd think HP would keep it around just so IBM doesn't take over the top spots for supercomputers.

Right now, the Alpha is firmly holding spots 2, 3, 6, 7, 18, 47, 57, 58, 59, 63, 79, 109, 110, 117, 118, 144, 179, 217, 245, 246, 337, 340, and 355 on the list of the 500 fastest supercomputers.

Sure, they can replace those slower systems with their other systems, but what about the 4 Alphas in the top 10 spots? What does HP have that can rival them in performance, while still keeping the prices down? I'd say if they kept the Alpha, rather than their own processors, they'd have a chance at finally gaining ground on the hi-end Unix server market where IBM and Sun dominate.

But, there's always hope for Alpha fans. Intel bought the technology, so if their new 64-bit processor (which shatters compatibility anyhow) doesn't perform well enough, they could just start making Alphas and call them their own.

AFAIK, there's nothing stopping Samsung (or anyone else involved) from continuing to build Alpha processors... Maybe API will try to keep the Alpha alive. It's been a good product for them for some time.

Or perhaps some other party might pick up the torch. Sun would be a good candidate, since they're in a tight competition with IBM, and the Alpha seems to be the only thing to top IBM's Power3 (and is doing so with half the number of processors!!!).

Come on HP. The Alpha has just as loyal a following as Apple... It's a big mistake not to start improving it and seeing what it can really do for you.

--
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
Re:This might just be a good thing by uncleFester · 2002-12-06 01:37 · Score: 5, Informative

No, this is a case of money and influence over technology.

No, I think this is a case of poor marketing. It's a superior product, so much so the competetion even bought into it.. but the product was saddled with two companies who couldn't market the product. Digital was notoriously poor in marketing, and when Compaq bought them it was merely a product-rounding move. Compaq, after all, made their money in Intel-based crap and Capellas never really pushed the Alpha as the strong superior product it was.

The Alpha was a decent hardware/OS setup: I ran a number of them at my last job, supporting boxen using Oracle. The boxes were solid computers (even for older 4100-series machines!), Tru64 was fairly solid (only a tricky NFS glitch on one machine spotted a perfect record with them) and the 1 1/2 years I spent with Dec/Compaq/Tru64 was suprisingly excellent. It's a shame the companies involved pretty much killed them due to stupidity.

--
-'fester