Slashdot Mirror
New Mega Alphas
GoNINzo writes: "Compaq has just announced the new Alpha servers. The have between 8 and 32 CPUs, run with a 64-bit 731 MHz Alpha chip, and current are distributed with Digital Unix or VMS. How soon before these machines are shipping with Linux preinstalled?"
Better?
There, see, you're answering your own question -- that is the price tag. :-)
--
...other silliness
No Laughing Allowed!
More to mention is that Andrea Archangeli from SuSE was the first to get the machine booting, of course with the help of Compaq Alpha Linux experts. :-D makes thing even harder. If you buy one, ask Andrea for the patches ;-)
This machine is a new platform and you can't run alpha linux on it out of the box. The tsunami platform is the closest though. But the QBBs and the 100+ PCI busses
Care about Bogomips?
SMP: Total of 11 processors activated (14067.70 BogoMIPS).
Unfortunately with only 11 procs, but that was one of the first runs.
Actually, Compaq already has linux running on these beasts. There are a lot of modifications needed due to the unusual hardware, but it won't be long before it's released. They have people working on it.
--
http://gammatron.weblogger.com
Let's see most fabs run VMS clusters for their production lines (including Intel). Hmm, last I knew the fabs were still running. I wouldn't call that dead.
This article quotes a figure of $100,000 for the GS80, $500,000 for the GS160, and over a million for the GS320.
Damn.
-skip
...................
...................
...................
The natural result of that is that hacking on SMP stuff is not of top priority to the average person using Linux let alone those that are actively "kernel hacking."
That's a mouthful that effectively says "few people truly care about SMP."
Of those that do have SMP hardware, how many have more than 2 CPUs? My SMP motherboard has only slots for 2. The Slashdot What's a good motherboard for SMP Linux? discussion mostly found 2-way and 4-way SMP hardware.
Recent pricing at PriceWatch indicates that quad Xeon mobos start around $2500, and that ignores CPUs.
Certainly consistent with these being very expensive puppies that there is, resultantly, relatively little experience with.
Soup it up to 8-way SMP, and the pricing obviously heads into the stratosphere, thus further discouraging the wide deployment that allows the "open source" principle that
If it costs $20K for the motherboard, and $100K for the system, that rather diminishes the number of "eyeballs."
I think I have to agree that Linux is unlikely to be as ready to take advantage of high end SMP hardware as VMS, "whatever they want to call Ultrix today," Irix, or Solaris.
It only will get much better when there's a goodly population of kernel hackers with 16-way Alpha boxes :-). (Drool...)
Alternatively, it would be rather cool if there was some platform where we could get "massively SMP" motherboards where the CPUs didn't have to be "massively expensive." I dunno what, exactly. StrongARM would be interesting, but I gather that it is not terribly supportive of SMP. MIPS looks like the architecture for which there exist both cheap CPUs and massively parallel systems ( e.g. - the SGI/Origin "Cray" boxes).
If you're not part of the solution, you're part of the precipitate.
This is not meant to be a sales pitch or anything but I buy a significant amount of Alphaserver hardware each year and am *very* happy with the reseller that I use. I've recommended them to others who have also been pleased. Your milage may very but if you are interested in a reseller with good engineers who can get quotes out the door quickly I'd recommend Pioneer Standard (http://www.pios.com). I've been using them for years. My rep has been trying to sell me the DS10L systems for a while so I know that they are familiar with them.
It's Ace's Hardware, and here's the article.
Guess what, companies that spend hundreds thousands of dollars on such boxes frankly don't give a fuck about Linux. Why would you want to run Linux on those anyways? Linux on non-x86 platforms lacks commercial application support. Want Oracle? Need JDK? Need this supernifty application server? Forget about it on Linux/Alpha. And as previous posters have mentioned, running Linux on SMP boxes with +4 CPUs is a waste of time and money. FreeBSD and Linux are good to run on your PCs but this is it. They don't come to compete with the midle range or high end RISC unix servers.
I know, but can't that be solved with a slocket type thing? I know that there is some work with this concept, but since the athlon uses the EV6 is used by the athlons in theory with a new bios and the "slockets" it can be done. It would be better if the bios was open source. That way we wouldn't have to worry about support suddenly ending.
At the very least I am suprised that alpha chipsets aren't being used as a basis for athlon multiprocessors.
Let me repeat myself: check the real performance numbers. Even though nothing from the GS line is even in there yet, Alpha is still way out in front.
I checked the numbers, did you? Clock for clock, the PA-Risc outdoes the alpha at integer ops.
For database systems, this is generally more relevant than floating point speed.
--Shoeboy
(former microserf)
My zsh-powered linux seems to be more self-critical - it wants to set itself in fire, but being unable to do so, that asks for help:
zsh> So, Linux, how about that SMP support?
zsh: no matches found: support?
-- v --
Better?
A little (-:
You're missing the point. In the past, Microsoft has imposed certain regulations on their retailers, showing, to me at least, that MS has a lot of power over their resellers.
Compaq, as a corporate entity, is a MS reseller. It doesn't matter, what product line we're refering to, we're talking about corporate politics here.
The _original_ poster was being speculative. And as I said in my post, I doubt that this is the case this time, because of Compaq's recent support of Linux.
Just trying to clarify things.
When Compaq absorbed DEC, they spent over a year with a thumb up their ass where the Alpha is concerned. In theory, they should start pushing those high speeds through soon.
--GnrcMan--
I wouldn't want one of those Alphas running a measly 700MHz, but you could probably get them to work OK. I certainly don't want one of those "lousy" 450MHz UltraSparc-II's, even if might be able to run basic applications like ls and mkdir...
--
--
fat lenny's gonna lick your brain today.
How soon before these machines are shipping with Linux preinstalled? /.? :-), but the world is not Linux-centric.
Is it really necessary to mention Linux to get a story posted on
We could ask "how long before Sun E4500s are shipping with Linux preinstalled", "how long before my toaster ships with Linux preinstalled"...
We all know it should be
I see many posts that Linux can't efficiently handle 32 CPUs. They're missing the point when it comes to the GS320. This box has real partitioning such that Linux can run on 4 CPUs, and Tru64 can run on the rest. Carve it up even further - hell you could have a 8-node Beowulf cluster inside a single box.
And the hardware supports hot-swap RAM and CPU. Tru64 will support that in 5.1. Can't wait for that!!!
Is it any more eerie than guys pretty much in love with Linux?
Don't get me wrong, Linux is cool, but nothing beats VMS.
FWIW, in my past life, I was a system admin in the VMS Development group at DEC. Now I push Linux. I miss VMS.
What's my Karma Mr. Burns? "Excellent"
uh. linux doesn't need to be on everything.
SMP is working fine on sparc32 and sparc64. Haven't a clue about PPC, I think it's there but I don't recall.
The only archetecture that I know for sure doesn't SMP under linux is Mips. Mostly because Mips processors don't handle cache coherency the way other archetectures do, so a lot more motherboard logic is required to make it work. There are plenty of SMP Mips systems in existance (for instance the discontinued NEC NetPower series) but documentation for the SMP hardware implementations is scarse.
This is just like television, only you can see much further.
well it's not 66 * 6.5 it's 66.6666666 and extend the 6's out a couple hundred places, you'll notice it gets dang close to 433
It means you don't need people in the room with it. You could get up and leave and turn out the lights and not worry about it.
I assume it must have remote system admin stuff, so you could administer a cluster of these without needing to go to each machine individually, or have direct physical access to the machine.
I sat in on the announcement in the Compaq cafeteria here... it was pretty neat. Unfortunately sounds like although they may be the 'best'... they are only the 'best' at what they are designed to do. Somebody must have been taking advertising advice from Microsoft....
This space for sale
We've got 3 quad xeon 550 boxes running RH6.1 here at work being used as very small compute servers. When all 4 processors are at full utilization, the overall efficiency for the sparse-memory (ie the 2MB processor cache doesn't help much) computations (verilog simulations) that are being done is terrible.. something on the order of 63%. Benchmarks we got were something like... 1 job = 100%, 2 jobs = 83%, 3 jobs = 75%, 4 jobs = 63%. (i.e. for 4 jobs, each processor is running at 63% of what the single processor ran the same job at)
Now, of course these are shared-bus (100 MHz) i440GX chipset motherboards with 2GB ram. I really couldn't tell you what impact the kernel has on these numbers, but because the caches are constantly missing, the memory bandwidth is pretty much pegged past 2 processors.
I don't have numbers for our SMP processor Alpha Linux box, but it's only 2 processors. Memory bandwidth (I don't believe) is getting swamped with just 2 processors on that box.
It's frustrating because our 32 processor Origin2k (Crossbar processor/memory interface, not shared-bus) can handle more jobs without the falloff of the linux boxes, but if you're just running 1-2 simulations, the intel processors absolutely smoke the Solaris/Irix boxes. Intel's Shared bus just doesn't scale past a couple of processors.
Well, as an example; say you've set up this wonderful web site that does lots of database and CGI work, on beefy intel hardware running linux, with horse killing amounts of bandwidth available... You show it to the world, they love it; your server begins to melt. For some reason you didn't take that possibility into account when designing your system, and so you can't break the functionality out into different machines very easily.
Either you let the existing system boil while you do a (more correct) reimplementation that can be spread across machines, or you replace your single server with a more powerful single server...
... just a possible "why".
VMS: Rumors of my death have been greatly exaggerated.
VMS isn't dead, despite Gartner and the rest proselytizing that fate for the last 10 years. They've done the same thing to unix, until very recently.
VMS still has a large user base, but Compaq has seen fit to cut off their noses, keep prices through the stratosphere, and aim for the high end only, all the while selling off bits and pieces of technology to M$ as part of the 'Affinity' program. This was of course to woo NT development over to Alpha, but M$ as usual has found a way to make this useless to their 'partner' (delaying 64-bit NT on Alpha until Merced ships with 64-bit NT, denying any Alpha leadtime). Fortunately, Compaq has seen some of the light and pulled the plug, pulled their Digits off NT filesystem/clustering development, etc.
There are a number of organizations that will support VMS, though I bet you're more after commercial application support. There are still quite a few Apps available (even WordPerfect 7) but the market has declined into a lot of vertical applications (science, education, research, telecommunications, banking, utilities). Some of this is due to development cannibalization to port to NT, most of it is due to DEC and now Compaq treating VMS like it is a dirty word for the past 5 or 6 years.
Compaq is still a PC box pusher. They don't understand that they have an OS with incredible reliability (uptimes in the range of 13-15 years have been reported) and clustering that nothing else can touch (shared everything, over multiple transports, with automatic load balancing, cluster aliases, the ability to cluster machines 100's of miles apart, etc...)
There is still a community, despite the Q's attempts to munge DECUS into a new marketing vehicle for their desktop PC's (I get offers as a member of DECUS for steep discounts on PC's with NT installed...while what I want are steep discounts on Alpha boxes with VMS or Linux). Check out the VMSNET newsgroups or COMP.OS.VMS. Very active. DECUS has managed to get Compaq to issue a 'hobbyist' VMS license and a selection of layered products. Some commercial VMS vendors are participating to offer their products under the same license. Check out Montagar Software which distributes hobbyist licenses. You have to join DECUS (free).
The 'Open' in OpenVMS was a marketroid move when VMS fully supported POSIX (6.0?). IIRC VMS had full POSIX support before any commercial Unix did. It had nothing at all to do with the move to Alpha. It was just buzzword compliance when everything deployed had to be an 'open system'. There is no difference between VMS and OpenVMS, save for the POSIX layer. That has been removed in recent versions, as the standard VMS runtime libraries now support the POSIX API's as well.
Too bad it was before your time. When I was in college, VMS was *it*. VMS is younger than Unix, mind you, but they gave steep hardware and software discounts to colleges and phenomenal support. Now, so many useful things have been dropped from the CSLG (Campus Software License Agreement) that we plan on dropping the CSLG here next year. It is no longer worth it. Compaq's high-end blinders have lead them to sell off the layered products that made managing VMS clusters so sweet (PolyCenter Scheduler, Console Manager, Performance Analyzer, etc.) Most of these were sold to Computer Associates and now run on (and require) NT. Compaq's direction is loudly ranted about on COMP.OS.VMS.
Regardless, you could learn a few things from VMS. Linux could learn a lot, structurely. VMS was _designed_ (when Olson, the engineer, was CEO) and does so many things right... Even though Compaq has butchered the site, try the OpenVMS Website to learn more. The Documentation and FAQ links are there.
--Rubinstien
You have been trolled. Have a nice day.
---
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
Does anyone know the current State of Alpha linux in regards to SMP. or SparcLinux or LinuxPPC for that matter. I mean I read whats in the kernel devel but I havent been able to get ahold of any real benchmarks or heard from many people running SMP systems other than on intel.
Free Unix? Free Windows. http://www.reactos.com
There was at one time an Alpha version you could actually buy,
Look again. There's an \alpha subdirectory on every Windows NT 4.0/3.51 CD-ROM that I have seen. So there's nothing 'extra' to buy. You buy a regular copy of NT 4.0 and you choose at that point wether to install it on an x86 or an Alpha system.
Obviously, there aren't Alpha binaries on the W2K CD release, as MS has abandoned Alpha.
What the hell does Windows 98 have to do with an 8-32 processor server? Did your knee-jerk Microsoft hatred get the best of you on this one?
Linus et al have been working on this. I think it does 8 or 16 pretty well, but they aren't recommending it for above 16 yet.
Pin the spig.
I saw a few of these in a Compaq SAN interoperability lab a few weeks ago. I assume they are ready now with Tru64 Unix...not sure about getting them preinstalled with linux though.
The Compaq product info page is here. The 64bit OS plus the high internal bandwith means it should be a very great clustering unit, especially as you can now fit 40 of them into a single rack.
Here are the specs:
Then again, maybe I'm just pissed off that no matter what the story is, Microsoft bashers and Linux zealots all need to chime in.
This is what I get for feeding a damned troll, I guess.
... Formerly known as Ultrix
This is a boring sig
What's cool about these is they've got a crossbar switched architecture, so they scale better than a bus or omega switched network. [snip] ... these are sweet boxen and should deliver truly obscene tpc-c and tpc-h results.
I agree completely. These servers should provide some healthy competition for SUN and SGI (and others) in the high-end server market. From all the specs I saw under NDA, these are very competitive designs with all the right things in place.
Now drop a bunch of these into a SC-class framework (Compaq's high speed, low latency clustering solution) and you have a killer supercomputer.
[bash]$So, Linux, how about that SMP support?
bash: So,: command not found
What?! They still haven't intergrated the self-awareness patch into the kernel?
--GnrcMan--
Strange: (Open)VMS is generally perceived as older than UNIX, while in fact it only dates back to 1978, while UNIX was conceived in 1970 (or even before).
The transition VMS to OpenVMS was done several years ago by Digital, in an attempt to boost the image of the OS. (All to no avail, as they were bought by Compaq a few years later.) The "Open" in the name simply meant "adhering to industry standards". Nothing to do with Open Source (the phrase wasn't coined back then), or even platform support (VMS only ran on VAXen, and later Alphas. The name change had nothing to do with the introduction of the Alpha processor AFAIK.)
There still is a relatively large user base, and an active users group (DECUS gives away free hobbyist licences for the base OpenVMS system).
Officially, Compaq still supports OpenVMS, although they seem to have the policy: "we'll support your installation until the NT box next to it is able to replace it".
I believe OpenVMS will survive for quite a while, especially since Microsoft has dropped Alpha support of Windows 2000.
WWTTD?
Nope. Above 4 CPUs, you get diminishing returns for Linux as it stands at the moment, but it's not a hard limit (and 2.4 should do better with more CPUs, too). Take a look at http://www.dare.demon.nl/linux/sparc 64/yow.txt for an example of Linux running on a 14 CPU UltraSparc system. It's worth remembering that Linux is not just Intel. I don't think that current Intel chipsets can handle more than 8 CPUs. Machines that can take more (e.g., the Data General AV25000 can take up to 64 CPUs) tend to use multiple quad-CPU boards. These are also NUMA configurations, rather than traditional SMP.
"The invisible and the non-existent look very much alike." -- Delos B. McKown
"configured at boot time" == kernel relinked at boot time == just like IRIX, Tru64[1], Solaris, UnixWare...
Get over it.. just about every Unix has to recompile the kernel for hardware/kernel config changes, just like linux.
I use Friend/Foe + mod-point modifiers as a karma/reputation system.
You don't know what you're talking about.
SMP machines such as Compaq 2xxx, 4xxx, 8xxxWildfire, SGI Origin, IBM Winterhawk, and Sun E10K maintain coherent caches so that all processors have the same view of memory. Because of the way the caches are organized, it is quite possible for different threads (running on different processors) to "fight" over memory locations that are referenced through more than one cache. According to SGI's Parallel Performance Tuning Tutorial, in the worst cases this can cause a code running in parallel on 8 processors to execute at just 1% of the speed of the code running on one processor! The same effects happen on other systems, too -- trust me; I do parallel performance engineering for environmental modeling as my "day job".
Some AC's don't have any idea what they're talking about, and insist on trying to spread their ignorance!
"My opinions are my own, and I've got *lots* of them!"
I wanna know where i can get this "Linux-Live Free Or Die" license plate.
Ham on rye, hold the mayo please.
thelocust[dot]org
BTW, did you notice that SGI is open-sourcing their Linux IA-64 compiler suite under the GPL? See URL http://oss.sgi.com/projects/Pro64/
"My opinions are my own, and I've got *lots* of them!"
Yeah, and I checked the other numbers too. All the evidence I see suggests that the top reported Alpha numbers are higher than the top reported HP numbers. In fact, Alpha seems to be ahead of HP in spite of the fact that the most recent offical TPC numbers for Alpha are almost two years old. (I'm really looking forward to seeing transaction numbers for the GS series.)
I fail to see how "work per clock cycle" is a more relevant measure of performance that "work per unit wall clock time" (aka "throughput").
CVS is teh suck. Use Vesta instead.
Samsung is the primary supplier of Alpha chips to Compaq. Intel also fabs Alphas at the Hudson, Ma. fab. That fab used to be owned by DEC. StrongARM was also fabbed there.
API, a.k.a. Alpha Processor Inc., is a Samsung company. API/Samsung have an architectural license to Alpha. Intel does not.
mike (I work at API)
What's my Karma Mr. Burns? "Excellent"
A few months back I snagged a copy of "Bullshit Bingo" from our printer where somebody had left it. It contains a nice grid that you could use during meetings whenever you heard to stupid buzzwords. Your posting would win it several times!
But according to the Official Compaq Spec the 21264b can toot along at 940 MHz if you can cool the heat sink enough to keep the Operating Temperature at Heat Sink Center down to 83.8C.
So just a little push and you should have GHz 64-bit processors, scads of them!
... an idea, the fugitive fermentation of an individual brain ... -- T. Jefferson
EV7 systems aren't out yet. Maybe you meant EV67?
(EV6=.35 EV67=.25 EV68=.18micron)
mike
What's my Karma Mr. Burns? "Excellent"
Steve Lionel
I heard that these systems are capable of running multiple OS's simultaneously through software partitions (Galaxy or something?). Furthermore, I heard that each OS instance could share memory with each other, communicate with each other and allow for dynamic reconfiguration of the CPU's. Can anyone Elaborate on this?
-Throttle
I though there was a limit of either 4 or 8 processors on a board (no where near 32)... Could someone please tell me if this is wrong and what vers made me wrong :)?
- Sig
Well the AlphaServer GS320 which is 4 clusters of 8 processors, was already shown in Geneva at the Telecom 99 show. At that time they where ironing out the multi-cluster possibilities of the system. I think this machine might have had some true potential for the Windows 2000 Datacenter, but I guess Tru64 and OpenVMS will fill that role extremely well to.
;-)
I wonder if I can cluster the 32 processor GS320 with an old 2000-300 alpha workstation ? And use a MicroVAX II as the quorum disk with VMS 5.5-H2
You're right about that. Alpha/PI/II/III is way too complicated, 10GHz i386 based upon 0.18 micron process technology would be smaller, faster, cheaper and cooler. :-)
Hey! My old 6502 would be even better
Hint: moderators: "blah blah fud blah", along with the post in general, implies sarcasm, or an attempt at humor, not flamebait. If you think the post's overrated, mark it "overrated", but READ a post through before you moderate it.
This forum does not need half-assed moderators, and frankly, I'd trust Sig11 to moderate my comments much more fairly than whatever thoughtless, faceless cretin marked him down as "flamebait".
Stay up hacking each weekend. Sleep is for the week.
While I'm an advocate of sticking Linux everywhere it can work well (and a few other places, for fun), there's no way I'd pick Linux over Digital Unix on one of those systems, unless there was some monumental task that worked under Linux that just couldn't be ported to Digital Unix. Digital Unix performs amazingly well in things like Apache benchmarks, partially due to their amazingly optimized tcp/ip code. :)
The OS is written completely for the Alpha, and the optimizations shows. It's a work of beauty, don't kick it out just because you like Linux.
(I'm not saying Digital Unix is not without faults, I'm just saying it has some great strengths on the Alpha.)
Not that you really need to read another, 'me too', but its really the algorithm that chooses what keyword to use that is at fault here. This message at the time of my reading is labeled 'Flamebait', but it actually has 3 funny votes and only 1 flamebait.
Go figure...
It depends upon what sort of applications you want to run on the system.
Some applications (those with no parallelism) won't take advantage of more than 1 CPU, regardless of if you have 4 or 8 or 32 in your machine.
Network servers can take advantage of multiple CPUs, -IF- the workload is primarily CPU-bound, not IO-bound.
Parallel computational programs (like those run on Beowulf clusters) will take the best advantage of all CPUs, as long as there is little cache contention.
Uh, correct me if I am wrong, but didn't VMS die a long time ago? I remember going to it's funeral, the only thing I can conclude from this, is that Compaq == Jesus Christ if they can raise the dead like him...
Seriously, is VMS still alive and kicking? Does it have any user base, commerical support (besides compaq) or community behind it?
Differance between OpenVMS and VMS? Is OpenVMS *really* Open, or Open for marketing reasons?
Sorry, when it comes to VMS I am an idiot, it was before my time
"`Ford, you're turning into a penguin. Stop it.'" -THHGTTG
Why has there been no story about this?
No replies made to AC posts. Please log in.
I have seen and touched a Slate at a customer site in San Diego two months ago. Running Linux, no less. Persumably these people now have a rack full of them. Officially, Slates have been on the market for a month or so. I am not surprised to see that people are still waiting for them, though. I suspect that high-profile customers got first dibs.
How many people who hack linux in their spare time have exclusive access to a 16 or 32 way $500k server? Thats why you are better off running commercial unix, after all it was designed specifically for that hardware.
I think having to compile a kernel for a hardware change is archaic, when was the last time you had to recompile SunOS or IRIX when adding a second cpu or network card? Just load the module and you're ready to go.
Only the State obtains its revenue by coercion. - Murray Rothbard
Compaq can provide better info than this, but a rollout is probably the wrong time for this. A short while ago we had one of their high performance computing / enterprise computing managers out here, and we got a lot of meat. I am not sure to what extent I am still bound by the NDA, but let me assure you that the new GS boxes are very competitive with Sun's E6500 and E10000, as well as SGI Origin2000. A lot of good design decisions went into these servers, and they should shine in both, the commercial database market as well as in the technical computing arena.
Actually, it was pretty good. They had it at the Fox Theater, which is a pretty cool place for just about any occasion.
75 posts and no "imagine a beowulf of these" yet ;-) Well here it is.
Spyky
Was NT supose to be Microsoft's cross-platform portable OS? I have seen stuff rolling around in old comp.sgi.* posts with people having problems getting NT on their MIPS proc... I know it isn't alpha, but the point being, wasn't one of NT goals to run on every proc know to man?
Maybe it was either a dream or an lsd trip... Mmmm roasted white rabbit never tasted so good.
"`Ford, you're turning into a penguin. Stop it.'" -THHGTTG
This is copyrighted information, and the DMCA clearly states that "useful information cannot be posted on SlashDot". Please remove this post immediately.
the alpha is far superior to the current intel offerings, but intel at least goes through the motions of improving and releasing new cpus. even if the improvements aren't all that great (kni anyone?) they at least let their customer base know that they aren't being left up a creek.
so- has there been anything really new and exciting in the alpha world, or is compaq letting it languish?
--
Obviously, there aren't Alpha binaries on the W2K CD release, as MS has abandoned Alpha
Actually, you've got it backwards, Compaq abandoned MS.
--GnrcMan--
COMPAQ?!?!?!?!?! Listen Up!!!
Actually it will have ZERO potential for Win2k Datacenter. Microsoft is not developing Win2K for Alpha, and neither is Compaq.
Q.
"yeah, but can i run linux on it?" i don't get it. if you get a GS and run Linux on it, i'm not sure what condition you suffer from but i'm sure it's unpronounceable. the linux lunatic fringe really irritates me. there's a huge difference between VMS and UNIX, and yet another gap between UNIX and Linux. -m.
digital\l\a\t\i\g\i\dDEC\C\E\D(etc...) has a history of playing the name game. All the way back to the 'Programmable Data Processor', their first complete computer.
Heh. See the comp.os.vms FAQ about how to port from VMS to OpenVMS.
If you want more confusion, look up MicroVMS, or VAX/VMS, or VAX-11/VMS. DEC, masters of the name change game.
How recently? I remember using an Alpha with a early beta of W2K a while back.
IIRC the last Alpha release was NT 5.0, Beta 2 (don't recall the build number exactly, but I think it was in the 1700's).
Information wants to be free -- but informants want to be paid.
Hmm, you don't seem to be compliant with the latest HML (human markup language) tags. Didn't you know that and are the most important additions to this recent release?
The Alphas used to have NT on them as an option. You could run both Softimage and 3DS MAX at phenominal speeds, which I understand is what they used for a lot of the (mediocre) computer effects on Titanic.
The translator card they used supposedly rewrote certain parts of the MS code for optimization, and at the time (for like a week) was far and away the fastest NT-running hardware around, if I remember right.
When Linux started getting bigger, the Alpha-with-NT market dried up (not that it was huge in the first place), and right around the Digital-Compaq merger, it was suggested that they wouldn't run MS on their newer chips. Digital had already been in a pissing match with Intel over MMX and now they were competing in the 64-bit race, MS made the obvious choice to stick with Intel and that was that.
MS predatory pricing stuff may have kept Compaq relatively quiet in the past, but after the court stuff comes down you'll probably see Compaq throw their weight behind Linux to the degree where they reassign some of the Alpha development folks to supporting Linux directly with official drivers (like with Lucent's special Linux driver for their Thinkpad-deployed Winmodems) and possibly even ports of their supposedly excellent (I'm no judge) Digital-UNIX filesystem and development toolsets.
Like I said above, I'm not an expert at any of this stuff, it's just that I'm interested in 3D animation and I was looking at Alphas with 3DS Max as a lower-cost alternative to SPARCs with Renderman (in like '95-'96), and the weird politics of the Digital/MS/Intel relationship sort of drew me in.
-jpowers
-jpowers
please don't feed the trolls...getting angry responses is what they live for (sad huh?)
Yeah well, they do exist, but as with the system integration parts in the ES line, there are yield problems. The transition to the fabless model since the sale of Digital Semi hasn't been as perfect as it could have been, and scaling down the feature size has turned up more bugs than expected in the 21264. Not like it matters though, because Alpha is still #1 in performance. If you care about MHz over actual performance, then you need to go back to college and learn a thing or two about computer architecture.
Of course there's also Alpha's 64-bit advantage, which does make a big difference in important applications (gene sequencing/discovery, data warehousing, etc.).
Let me repeat myself: check the real performance numbers. Even though nothing from the GS line is even in there yet, Alpha is still way out in front.
And as for "doing more in a clock cycle," no, they really don't. We have an acronym for what they actually do: VLIW. It's not more parallelism (that comes from how many instructions you issue in a cycle), it's just more explicit information about operation independence (which it turns out doesn't work so well). It didn't work in the '80s (Multiflow RIP), it sucks today in HP machines, and it's going to suck tomorrow in IA-64. (Not that it matters though. Intel could sell a rock with wires coming out of it and people would still buy it.)
"With IA-64, Intel makes a 20 year leap forward in technology: from 1960 to 1980."
CVS is teh suck. Use Vesta instead.
Speaking of Metallica...
Today on the way to work one of their songs came on the raido. I like metallica but after the mp3 thing I just got this sick feeling. I like the music but ever since the Napster thing I just cannot listen to them any more.
If at first you don't succeed, skydiving is not for you.
i was under the impressions that linux didnt make effective use of having more than 2 cpus (at least on i386 machines). Has this changed?
If so whats the max number of cpu's linux can make effective use of on alpha/intel?
john
-- john
The word "open" has been used for many things. In some circles, "open systems" refers to Unix systems (as opposed to mainframe systems). These systems use relatively open standards like SCSI.
So OpenVMS runs on hardware designed for Unix systems. Old VMS ran on a Vax.
The Open Source movement is a relative newcomer to the "open" name.
So this should also explain why The Open Software Foundation, now known as The Open Group, is not an open source organization.
I'm not entirely certain about the specifics but I do know that DEC/Compaq doesn't produce the chips. I also know that Intel is producing some of them, due to some deal worked out a while ago. I seem to remember it involving some patent or trade secret deal they worked out. But I'm hazy on that. Samsung makes Alpha chips as well, I think.
--GnrcMan--
My impression is that it is a marketing term aimed at a bunch of the ease-of-install and ease-of-management stuff that they have added to the systems. This includes the ability to power down parts of the system without bringing the whole machine down as well as a bunch of features aimed at the "limited access" crowd (think co-located servers in secure racks/rooms) -- the systems can be installed and configured/run remotely and have all sorts of sensors and environment monitors that can report sensor status to remote management tools.
Analysts estimate the GS80 will cost around $100,000, the GS160 around $500,000 and the GS320 more than $1 million. The high-end servers initially will come with OpenVMS or Tru64 Unix; Linux will be available later.
:P
--- snip ---
the '80 is the 8 processor, '160 is 16, i'll leave it as an excersize for the reader to figure out the '320.
--
blue
i browse at -1 because they're funnier than you are.
Perhaps the question of when would be more relevant if Linux had better SMP support. We might see Linux on those boxes after the 2.4 kernel is released.
Uhhh...Microsoft doesn't even support the Alpha...at all. Geez, leave it to you guys to turn an announcement for a MS-free platform into an excuse to bitch about Microsoft.
(Yes, NT used to be supported on Alpha, but it isn't any more. And 9x NEVER was.)
--GnrcMan--
Try AIX. All modular and configured at boot time, if not on the fly.
Correct me if I'm wrong, but didn't Linux use to have some problems with running on lots of cpus? Like in one, two or four cpus was ok, but more didn't really gain anything. Is this fixed now?
Phobos - Greek word for fear or flight
"The have between 8 and 32 CPUs..."
Hmm...
Emil
"Why are computer nerds always so short?"
You see, the great thing about Compaq buying |d|i|g|i|t|a|l| is that now it's a marketing driven company, whereas |d|i|g|i|t|a|l| was engineering driven . We all know how much engineers suck, so what will a bunch of salesdroids be able to do with these incredible products ?? Give them really cool names!
oh, rapture!!
Compaq says they expect $1 billion in revenue from these boxes over the next four years. They haven't named a price range, but given the market they intend to compete in, I'm guessing these are a very pricey solution for dot com web service machines... better to just get the bandwidth and a bunch of low end boxes in a cluster, I'll bet.
-- Still waiting for the Nike endorsement
FWIW, True64 on the Alpha rocks!
---
--
If I actually could spell I'd have spelled it right in the first place.
I wish i had oine of these running my webserver. My school had an alpha running the grading system. I'm not sure if they still have it but it was old so i doubt it.
Shine on, you crazy diamond.
BUT, you need OS support to do this kind of stuff(duh). And the first OS to support this?? VMS .
Followed by Tru64, of course.
Now who said VMS was dead??
goddammit... it's *Tru*64...
I use Friend/Foe + mod-point modifiers as a karma/reputation system.
It was supposed to, yes. There was at one time an Alpha version you could actually buy, and a planned MIPS version (not sure if this one made it to production). They were dropped some time ago.
Smoke a joint or something, dude. Sheesh.......
Does anybody know if these can be used to make multiprocessor athlons? I know they use the same bus. Of course, it may be EV7 or 8 now, but there has to be EV6 boards out there. Maybe even running at 400Mhz???
VMS is also used heavily by Intel to run their fabs.... all the intel fabs have Compaq/DEC technicians to look after the computers.
I use Friend/Foe + mod-point modifiers as a karma/reputation system.
the last time i recompiled my irix kernel, must have been a couple of weeks when i re-installed a patch set from SGI.
When i rebooted it automatically relinked the kernel...
Digital Unix does the same.
Unixware does the same.
OpenServer does the same.
Hell, i can't think of any Unix where you *don't* have to recompile the kernel.
I use Friend/Foe + mod-point modifiers as a karma/reputation system.
Never was Ultrix. Ultrix was another beast completely.
Lottery: a tax on those bad at math.
it was never ever known as Ultrix.
Also the marketing name has changed a couple of times (OSF/1 -> Digital Unix -> Tru64) But it's *real* name (ie uname) is and always has been OSF/1.
I use Friend/Foe + mod-point modifiers as a karma/reputation system.
sorry that should be titled I want an alpha.
Shine on, you crazy diamond.
It was, unfortunately, a fairly typical corporate presentation, unencumbered by any real hard data.
They simulcast the CEO's announcement from NY, and we heard from another high-level manager, some dude from Oracle and a pre-recorded "howdy" from Larry Ellison. This was followed by a lunch break, some local presentations, a brief panel discussion and the requisite giveaways. Linux *did* get a mention in a couple of slides.
A great deal of time was spent talking about how great the Compaq/Oracle partnership is. I asked about Informix benchmarking, but didn't get a whole lot of response beyond "we expect the results to be good."
Whatever. There wasn't much in the way of new information. Lots of processors, Tru64 Unix scalable, manageable, really fast, etc, etc.
A brief list of buzzwords:
functionality
knowledge management
megatrend
the "edge of the web"
clickstream
"go to market"
Zero-latency-enterprise
And there you have it.
Now that I have saved up enough for a new Box and I have to drool over this one. I guess I will have to unleash my unholy army to raise even more money. If its not one thing its another I mean if my henchmen are not calling in sick my Cluster wont run my death ray. I would just like a break and this just might do it.
Claiming that your operating system is the best in the world because more people use it is like saying McDonalds makes
Seriously though, this is a cool system. I just wish I could afford one.
kwsNI
What the hell does Windows 98 have to do with an 8-32 processor server? Did your knee-jerk Microsoft hatred get the best of you on this one?
What the original poster was refering to is Compaq's consumer-level machines like the Presario.
These machines come with Windows98. The example was that Compaq can get Win98 for $20. If they piss Microsoft off, then maybe Compaq's cost on Win98 will rise. Even if it rose to $21, and Compaq pushed 1 million units, they would lose $1Million in profits.
Corporate interests need to be careful about every political move they make.
Having said that, Compaq already seems to be supporting Linux, so they might not be so concerned about Microsoft's agenda.
Anybody know when they go on the market?
Damn, I swear that had me laughing for about 10 minutes.
And meanwhile the other post is at 5. Come on moderators, this post deserves some recognition too!
--GnrcMan--
As for Beowulf, in fact the current Linux port sort of does a "beowulf-in-a-box". We support SMP up to four processors. Above that and you run multiple instances of the OS in different "partitions" of CPU-sets. Again, if a business need arose to require supporting a single instance of Linux on a 32-processor system, we could probably make that happen ("Given enough money, all problems are shallow?" 8-) )
I helped install 2 sites with GS160's in the past 6 months. There isn't a lot exciting about them. These machines are fast, because they have the new EV7 Alpha chips, but they really aren't anything groundbreaking. The same basic hardware has had 3 different names in the last 5 years TurboLaser 7000 a.k.a. Alpha 8400 a.k.a. GS160. It is a shared bus architecture that can support mulitple PCI backplanes. The thing to be on the lookout for from Compaq is called "WildFire." That will be a true distributed hardware architecture. This means Compaq will finally catch up with Sun... The operating system has a similar history (OSF1 a.k.a. Digital Unix a.k.a. Tru64 Unix.) Whenever Intel releases Merced, they have promised that the OS will support it. Keep an eye on this verison of Unix. They just added clustered filesystems, which, if it works, will make this unix ideal for distributed high-availability applications.
HOW THE FUCK ARE YOU SUPPOSED TO GET SOFTWARE TO THESE THINGS?!
Tar the required files into one big file, Base64 encode it so it is a nice long text string, copy it into your clipboard, then in telnet, type:
cat > filename.tar.base64
paste the file from the clipboard into your telnet window, unencode it and untar it. Voila, you have your napster client on the testdrive server.
--
--
My sometimes helpful blog
It's worth noting that the tpc scores you are comparing are of an 8 node, 96 proc alpha cluster vs. a single, 32 proc hp box. Compaq's top single box score is half that of hp's best single box score, but that's not a fair comparison either.
It's also worth noting that Compaq has been selling GS series boxes since the intro of the 21264, but these new ones are the first of the GS line to feature the switched crossbar architecture.
They should stomp the HP V-Class, but IBM's S80 and Sun's E1000 aren't going to be far behind.
--Shoeboy
(former microserf)
The big announcement (what this article about) is the GS series, which is separate and totally different from the DS series (of which the DS10L is a member).
Don't get me wrong, the DS machines are great, they just don't have the new system architecture that makes the GS series so awesome (which is what all the hubub is about).
CVS is teh suck. Use Vesta instead.
Take this as a note: build karma, get moderator points, then b1tch s14p him every chance you get.
Sig11 is living proof that moderation only works so well, and is quite aware of it. I am sure he would agree with the late Trollmastah, who said: "Take all good things in moderation, including moderation."...
--
--
fat lenny's gonna lick your brain today.
Call it "The operating system formerly known as the operating system formerly knows as OSF/1"
Okay, these were supposed to ship early last year, but compaq was getting lousy yields on the custom asics used in the box.
What's cool about these is they've got a crossbar switched architecture, so they scale better than a bus or omega switched network. What sucks is that the alpha architecture hasn't kept up in the clock speed race. Ghz alphas were supposed to be out by now too. Historically, the alpha has had the highest clock speed of any chip on the market. No longer. This is a bummer since they don't do as much per clock as, say, a PA-Risc system.
Still, these are sweet boxen and should deliver truly obscene tpc-c and tpc-h results. Drop a couple of storageworks coffins into the server room and all your data warehousing needs are met.
--shoeboy
(former microserf)
Right now Linux has shown only mediocre or below performance _relative_ to other, SMP optimized OS's when there are more than 4 CPU's. So you may get Linux only if you pound on the table when you ask for it, and the tech's will probably be scratching their heads in wonder that you'd spend the money for a system that Linux can't take advantage of nearly as well as DEC Unix or VMS.
Do we need to re-examine the entire approach to the kernel to really take advantage of 8+ CPU's? Why does a Linux kernel which works well with many CPU's have to be the same kernel for systems with only 1 or 2 CPU's?