Although the Alpha architecture may have been brought to the end of the line by HP, developers across the world have worked together and released an updated version of AlphaCore, an unofficial version of Fedora Core for the Alpha architecture.
AlphaCore 1.0 Released based on FC3
About The Author
Eugenia Loli
Ex-programmer, ex-editor in chief at OSNews.com, now a visual artist/filmmaker.
Follow me on Twitter @EugeniaLoli
Alphaserver 4100 might be usefull again.
I thought that it was superior and pure 64 bit, unlike other processors
money talks! ..
There’s a lot of perfectly functional legacy alpha hardware out there. One of Linux’s many functions is to give life to obsolete hardware abandoned by propriatary OS vendors. This is a perfect example of this.
developers must look in the future and stopp working on obsolete alpha architecure.
the world is going amd64, the rest will die soon
Don’t count your chickens. Now that HP has shown Carly the door and is re-evaluating their strategic direction, it’s entirely possible Alpha could be resurrected.
It ain’t over til it’s over.
No way I think we should still look at developing on legacy hardware too, think bout it, I mean come on, so many organizations use alpha systems and its sufficient enough for them, you dont need to be all fast unless needed, so Im glad Linux devs are supporting legacy hardware too, its just the way it should be, just because you people dont use legacy hardware, doesnt mean that other people dont, dont think of your selves all the time…
developers must look in the future and stopp working on obsolete alpha architecure.
Obsolete? It was, for one, designed from scratch by a company who knew to do CPUs. It was designed “to become 1,000 times faster over the coming 25 years”, with things like SMP in mind. Alpha could very well be kicking other cpu’s asses during the next decade if HP wouldn’t have been so blind (they even had a nt version!)
From http://research.compaq.com/wrl/DECarchives/DTJ/DTJ801/DTJ801SC.TXT:
4 Architectural Goals
When we started the detailed design of the Alpha AXP architecture, we had a short list of goals:
1. High performance
2. Longevity
3. Capability to run both VMS and UNIX operating systems
4. Easy migration from VAX and MIPS architectures
These goals directly influenced our key decisions in designing the architecture.
In considering performance and longevity, we set a 15- to 25-year design horizon and tried to avoid any design elements that we thought could become limitations during this time. In current architectures, a primary limitation is the 32-bit memory address. Thus we adopted a full 64-bit architecture, with a minimal number of 32-bit operations for backward compatibility.
We also considered how implementation performance should scale over 25 years. During the past 25 years, computers have become about 1,000 times faster. Therefore we focused our design decisions on allowing Alpha AXP system implementations to become 1,000 times faster over the coming 25 years. In our projections of future performance, we reasoned that raw clock rates would improve by a factor of 10 over that time, and that other design dimensions would have to provide two more factors of 10.
If the clock cannot be made faster, then more work must be done per clock tick. We therefore designed the Alpha AXP architecture to encourage multiple instruction issue* implementations that will eventually sustain about ten new instructions starting every clock cycle. This aggressive technique of starting multiple instructions distinguishes the Alpha AXP architecture from many other RISC architectures.
The remaining factor of 10 will come from multiple processors. A single system will contain perhaps ten processors and share memory. We therefore designed a multiprocessor memory model and matching instructions from the beginning. This early accommodation for multiple processors also distinguishes the Alpha AXP architecture from many other RISC architectures, which try to add the proper primitives later.
I needed this 6 months ago…
I’m glad atleast some people are still working on what is still a perfectly useable architecture. In fact, if HP (and compaq before them) hadn’t been such idiots the Alpha series would still be alive and kicking, destroying other architectures in performance. Sadly, times change. As does all things.
Anyways, I know Debian doesn’t upkeep much on its alpha port anymore so its good to see someone else trying. I know my Alpha 2100/4 machine still works perfectly even though its close to 10yrs old now and still handles file serving for about 25-30 people. Did I mention the only thing thats failed has been a hd?
These machines weren’t made to be buy and toss PCs. They were made to be incredibly long lasting, powerful workstations or servers that could scale almost infinitly.
Chris wrote:
> I know Debian doesn’t upkeep much on its alpha port
What do you mean?
http://buildd.debian.org/stats/graph2-week-big.png
As of today, Debian alpha is >98.5% up-to-date. Okay, this number is high because Debian is near the next release, but it rarely fell under 90%. Full stat here:
http://buildd.debian.org/stats/
We have an old XP1000 station that was used for crunching numbers 24/24, it was one of our power computers until P4 performance surpassed it. It remained turned off for two years until we needed a computer for hosting some intranet apps.
and guess what?? thanks to someone that decided to port Linux to Alpha that good first-class hardware had a second life (RedHat based on the 2.4.X kernel). The only problem was the video driver, but, since the computer was going to be used as a small server, that wasn’t a problem. We installed apache, php, mysql, our app and that was all.
It’s important to considerer that people spent a lot of money with these machines, so there is a particular interest of keeping them alive.
I manage a couple of alphas (ES40/XP1000) and I must say they can still be very useful machines.
But I rather use Debian. It’s normally more up to date and is noticeably faster than AlphaCore.
debian on alpha is very nice and viable. beside it’s the pet arch of the current release manager steve langasek.
it’s sometimes troublesome to run latest -rc kernels from kernel.org as the alpha port sometimes misses latest arch fixes, but beside that it is an easy arch to support.
Alpha is by far one of the best CPU’s ever designed and i too lament the way it was handled after Digital was purchased. The problem is that the stated upgrade path for these old boxes is Itanium2 based servers. Hopefully HP sill get their heads out of there rear ends and realize what they have.
Alpha and Digital Unix, the true unix power !
The the reviewer said that XP needed more than 256 megs of ram
and a faster than 400 mhz cpu to run a GUI, give me a break!
Not true, love linux but don’t make up facts
sorry i ment for my commit to go to fedora core review.