SGI NUMAflex Linux System On Display @ SC2002

jarrod.smith writes " According to SGI will unveil its Intel® Itanium® 2 NUMAflex shared-memory supercomputer architecture (which runs Linux as its OS) at Supercomputing 2002 which runs this week in Baltimore, MD. The link at SGI says the system will be on display at the show. The exhibit floor opens this evening. Unfortunately I did not go this year. Can those lucky enough to be at the meeting scope it out and post comments?"

Comments

Nothing special

[Anonymous Coward]

It was your run of the mill cheapy supercomputer. You couldn't run nuclear explosion simulations on it in any reasonable time or anything.

LINUX OS

[r0xah]

Don't get me wrong Linux is a great OS for a server and even a home computer, but is it really the best OS of choice for a new supercomputer? Will it be able to fully utilize all of the abilities. I assume in time that it would, but you would have to wait for the open source developers to catch up to the curve.

Re:LINUX OS

[boaworm]

Well... the new IBM machine BlueGene (II) or whatever its named is supposed to run linux.. and the new cluster used for nuclear simulations is also to run linux.. so it actually seems like a fairly common choice. And if they choose linux this early in the project, they can

1: Fine-tune Linux to fit the platform

2: Design the platform to utilize linux

So it sounds fair to me.. Consider installing some propriatory OS instead.. where they cannot play around, change kernel design, drivers, VM or whatever they fancy. Would not that be a greater drawback ?

Re:LINUX OS

[Anonymous Coward]

Is this a joke? or a troll? IBM has stated several times, here as well, linux is the os of choice for their super comps. And SGI is at the top of the heap for knowing what to do with hardware.

Re:LINUX OS

[Jungle guy]

It might not be the "best" choice, but certainly is a choice.

The Los Alamos National Laboratory is building a supercomputer based on a Beowulf Cluster with 1024 nodes (2 processor in each node). You can read the story here or in this Slashdot thread.

Re:LINUX OS

[Anonymous Coward]

Well we could always run windows in bochs.

Re:LINUX OS

[binaryDigit]

Well it seems like a good choice for SGI. It allows them to come out with a supercomputer using "more" commodity parts (e.g. Intel processors) running an OS that is the hot topic and, one would assume, cheaper for them to sell. After all, what would their options be if they had not chose Linux? Irix only runs on MIPS afaik. Maybe BeOS ;)

This is more SGI schizo behaviour. They can't really decide what they want to do or be, what hardware platform they want to push or what OS they want to use. Another sad day in a long line of sad days for a once cool company.

Re:LINUX OS

[sql*kitten]

Consider installing some propriatory OS instead.. where they cannot play around, change kernel design, drivers, VM or whatever they fancy. Would not that be a greater drawback ?

But IBM already have the source to AIX... they wrote it.

Re:LINUX OS

[Anonymous Coward]

You're right. Linux is primarily targetted at the x86 personal computer architecture, since that's what most developers use. Nothing wrong with it, it's just a fact of life. A lot more time is spent getting optimizing gcc to produce x86 code than PPC or mips, too.

Meanwhile, commercial unix variants (or other OS like VMS) have been heavily optimized for big iron, supercomputers, SMP, etc. As a general purpose OS, they might suck, they might not handle limited resources as well, but they'll certainly outperform linux (or bsd) on the high end equipment.

Re:LINUX OS

[Anonymous Coward]

SGI has been working on this machine for a while now, and you can be sure the linux it runs has been tweaked for performance.

This machine is Intel based. SGI had to choose to port IRIX or make Linux run well. IRIX isn't going on their IA64 computers, period.

SGI has always focused on high speed internal communication in its machines, and SGI has tended to lag behind the curve in the MIPS processor's raw MHZ. The IA64 chips are much faster than any MIPS processor out there. This machine has some amazing performance--I think everyone will be surprised at what SGI has done. If you need a high end single image shared memory Linux or Intel solution, SGI has filled that role.

To be fair, if you don't need this machine.. don't buy it or think about it. SGI is a dying company and in the long term you'll get better support elsewhere. Sun and HP will have competing machines out, but they won't perform as well. I trust HP and Sun to be around longer than SGI though, and they won't fuck you over like SGI will.

What else can I say? Oh, the one I saw was painted in penguin colors.

Re:LINUX OS

[stevejsmith]

With all of the time and money they're putting into this, wouldn't it make sense to code their own operating system? I don't know much about coding OSes, but it seems that it would be the best way.

Regarding Linux: I don't know a whole lot about the kenel structure and what-not, but it seems that the good things about Linux are things that a supercomputer wouldn't care about (portability, a good GUI platform, etc.). Why not use IRIX?

You know, if they wanted a stable OS, they'd use Windows 98 and just pay the money for the second edition and then patch IE. That's pretty stable, right?

Re:LINUX OS

[Iguanaphobic]

Just think how fast Windows 98SE would fly on this baby!!

Re:LINUX OS

[Anonymous Coward]

That is a regular cluster, not a NUMA machine. There is a difference.

Re:LINUX OS

[jericho4.0]

Yes. Linux is a great choice for supercomputers. It's support for shared memory, threading, and SMP is equal to the best designs out there, mostly because it's those designs incorporated into linux.

Unfortunatly, I havn't found the time to test it on my Cray, so I might be talking out of my ass.

Re:LINUX OS

[jedidiah]

A "supercomputer" just has a lot of computational horsepower. It seems that the whole idea of this thing is to expose lots of cpus and physical memory to a single OS image. That's relatively simple when compared to virtualized machines like z90's or E12K's.

Just think of it as your grandson's palmpilot.

There may be OS scalability issues. However, SGI should be well equipped to address them.

I'd be curious to see how a single Oracle instance might scale on such a beast.

Re:LINUX OS

[creature]

Linux is a great choice for supercomputers. It's support for shared memory, threading, and SMP is equal to the best designs out there

One of the weakest areas in Linux, compared to commercial Unix, is its threads support. The "light-weight" processes is a hack, at best. Each of the Pthreads libraries are limited in some respect. signal delivery is all messed up. If you use one of those user level thread libs, then there is little advantage to SMP.

Personally, (Please note, I understand that a lot of people disagree with this, but this is what I think) Linux is great for desktops and small servers (=4 CPUs), but when it comes to "Big Iron" and Large SMPs, the thread limitations alone make it a bad choice. I guess in a cluster a small servers, like a beowulf-like cluster, it is fine......

Re:LINUX OS

[jedidiah]

True. The more relevant question would be: is AIX worth the bother of maintaining and porting? What value does IBM derive from that R&D expenditure. Does any of that serve to distinguish IBM from it's rivals in the marketplace?

Re:LINUX OS

[jedidiah]

I dunno. As much as processes bop from system board to system board on the bigger Sun machines, I am no longer certain that Linux would not be able to eat Sun's lunch in the +32 CPU box arena. Add IBM and SGI into the mix and you've more than enough engineering to bridge the gap.

Re:LINUX OS

[jedidiah]

This isn't VMS or NT we're talking about here. The lack of good threading won't necessarily hamper a serious Unix application. Some of them don't even support threading very well. So, this particular Linux disadvantage may end up being a moot point.

You don't need threads to scale Unix apps.

Re:LINUX OS

[khuber]

It seems more likely to me that AIX would distingusish IBM from its rivals. Everyone runs Linux.

It's possible that AIX is encumbered by technology that IBM licensed, but I don't know. I'd have to think IBM has ported AIX to x86. Likewise, I wonder why SGI hasn't chosen to port IRIX which has mature support for large scale multiprocessing.

-Kevin

Re:LINUX OS

[John Whitley]

Why not use IRIX?

Three reasons:

1. Good business sense. Instead of maintaining the whole OS, SGI (and other companies) can meet their requirements in the Linux kernel environment, focusing only on the value they need to add to the system. Who wants to reinvent all the old-hat stuff like driver or filesystem interfaces, anyways?

2. Good business sense. Very few companies except Microsoft make money from an Operating System. Rewriting an OS from scratch is a huge business risk and cash investment unless you're into very specialized hard-core OS R&D work. See Plan 9 and EROS for examples of, IMO, well-founded OS projects that started from scratch.

   Recall that SGI is a platform vendor. You buy a package of hardware and software from them. If their software costs are lower, that translates directly into higher margins. Apple made a similar "don't reinvent the wheel" decision in the choices that led to MacOS X, which left them time to focus on their true focus of applications and system usability.

3. Good business sense.With large development projects, it's useful to spread the development cost across a large population of developer-users. I.e. this is a driving motivation behind collaborative open source development. Only now it's happening at the corporate level instead of the level of the individual developer.

Re:LINUX OS

[Meister]

To be fair, if you don't need this machine.. don't buy it or think about it

I disagree... if you need a decent server, especially a scalable one, this machine is for you. You can start out small and add stuff as you need it.

Wanna run a database? This machine is perfect. You can add to more CPUs to the system if you need them. You can also add more I/O to the system independently, w/o changing your CPU count unless you need to. For those reasons, this machine would also be great as a general purpose server for running apps of any sort that need server class I/O and CPU power.

Wanna run some crash simulation codes? Again, this machine is perfect. You can run a threaded version or an MPI version and get tremendous performance because of the massive memory bandwidths and low latencies that this system provides.

OTOH, if you wanna run Quake or UT you should probably get a Clawhammer or one of those hyperthreaded P4s.

SGI is a dying company

This machine is the most general purpose machine that SGI has put out in a long time, due to the fact that it runs Linux on Intel. This should mean bigger markets will be available to SGI, hopefully preventing its demise.

Re:LINUX OS

[stevejsmith]

He proved me completely and totally wrong. :-D Mod him up, please.

Re:LINUX OS

[guile*fr]

I rather agree with u about SGI fscking customers...
but I don't think it will die because there will always be admins who want their data center look like the Entrepise deck...

Re:LINUX OS

[ninewands]

Well, considering that SGI had a perfectly free choice between using Linux (which already runs on Itanium), porting Irix to the Itanium and trying to make Windows64 (or whatever they (MS) are going to call their Itanium version) work on a NUMA architecture machine, I'd say they probably made a wise choice.

SGI has been a BIG booster of Open Source software in general and Linux in particular for about the last 5 years. I was reading the changelogs for the 2.5 kernel tree a couple of nights ago and noticed that their code for running the kernel on NUMA-based machines has already been contributed to the tree and merged.

The major beef about Linux as a big-iron OS has always been "It doesn't scale well above 4 processors" ... now, thanks to SGI's and IBM's big-iron work, it does ... the Origin 3900 is a 128 processor monster, and it's my understanding that preformance under the NUMA-ized Linux scales linearly up to 64 processors. I haven't seen any reports on the bigger boxes, but Let's see Win2K server do that ...

Re:LINUX OS

[ninewands]

Quoth the poster:

To be fair, if you don't need this machine.. don't buy it or think about it. SGI is a dying company and in the long term you'll get better support elsewhere.

Oh ... like Cray, Inc. is a dead company?

SGI, like Cray, wandered away from doing what made the company special (godawful high performance computing) and both of them suffered the consequences. Cray has moved back to it's roots (cost-be-damned-make-it-FAST one-off boxes for government-sponsored research projects) and has returned to the land of the living. SGI is turning that corner now ... I think I'll give them a few years before I write them off completely.

The poster continues:

I trust HP and Sun to be around longer than SGI though, and they won't fuck you over like SGI will.

HP probably ... if they don't get too Compaqted ... Sun's a little iffier ... with the demise of the PA-Risc and Alpha, and with SGI looking more and more toward the Itanium, Sun, Apple and IBM will probably be the last producers of non-Intel-processor machines that one could call "personal computers" ... Apple's volume and IBM's economies of scale are keeping the PPC afloat for now ... but Sun stands alone behind the SPARC. Don't get me wrong ... I love my Ultra10, but I also have my doubts ... . Also, I've never had any experience with HP support, but I have NO complaints about either Sun OR SGI's willingness and ability to help a customer in any way they can.

and ... oh yeah? Penguin colors??? Every Origin 3000 series machine I've EVER seen was black and purple ... and I've NEVER seen a penguin in THAT color scheme ...

Re:LINUX OS

[Twirlip of the Mists]

You seem to be completely out of your mind.

There are basically three ways to parallelize an application: processes, threads, and sprocs or other lightweight shared-memory process implementations.

Processes for multiprocessing suck. The reasons for this are well known and won't be re-stated here, but cross-reference "shared memory."

Threads are standardized, light-weight, and efficient.

Sprocs are an IRIX-specific thing, but there are similar dohickeys on other OS platforms. A sproc is basically another instance of a process that shares its address space. Sprocs are similar to threads in a lot of ways, but they're not as elegant for many applications and they're highly platform-specific. Programming with this is tough, and porting virtually impossible.

Threads-- and, almost as important, thread performance-- are critically important for application scalability under any operating system, UNIX or otherwise.

Re:LINUX OS

[creature]

Obviously you have never written a "serious" Unix application....

so - If I don't threads in my application, how am I gonna use multiple processors concurrently? Am I going to have seperate processes and perform some type of IPC between them? That would require a lot more memory and a large amount of overhead for synchronization.

Most of the workload on super-computers is threaded (>90%). Most supercomputers are Unix (>95%)..... If "serious" applications don't gain anything from threading, then why do the developers spend that much time doing threading their applications? Have you ever written a larger parallel applications? I have, and let me tell you, If I didn't have to deal with threads, I would not. When you have a problem, dubugging is VERY difficult. This goes for message passing libraries, like MPI, too.

Re:LINUX OS

[creature]

sprocs are basically like Linux threads? what other Unix OS's have this type of "light weight" process? That are they called?

I have never programmed a large SGI machine. Personnally, I would like to better educate myself. Porting threaded applications to run on Linux well is kind of a pain. I wonder if the correct way to write a cross platform (Linux and commercial Unix) applications would be start with a linux-thread or sproc type structure from design, instead of Pthreads..... maybe this would prove to be more work.... Interesting idea to ponder.

Re:LINUX OS

[Twirlip of the Mists]

No idea. You can learn more about sprocs by starting with the man page, here.

Re:LINUX OS

[Anonymous Coward]

1. Raw MHz means nothing. SGI's MIPS-based machines perform excellently, at the top of the Spec2000 benchmarks, and extensively blow away both x86 and Itanium I. There isn't enough data yet to draw any conclusions about Itanium II. I would take an Irix-based Origin system any day over the completely unproven IA64.

2. Having developed for NUMA architectures, I am confused as to why this machine is designed the way it is. Unless they've done extensive modifications to the kernel, and especially the brain-damaged Linux thread libraries, you're going to end up with what are supposed to be threads of the same process running with different memory access properties.

3. Even more confusing, what little press there is on this machine claims constant data access to anywhere in the combined memory space. NUMA by definition is non-uniform memory access. What's with that?

Re:LINUX OS

[Meister]

1. Raw MHz means nothing. SGI's MIPS-based machines perform excellently, at the top of the Spec2000 benchmarks, and extensively blow away both x86 and Itanium I. There isn't enough data yet to draw any conclusions about Itanium II. I would take an Irix-based Origin system any day over the completely unproven IA64.

Huh? There's data out there, let's look at some of the SPEC results:
CPU specint specfp
600MHz R14k 483 495
800MHz Itanium 314 645
1GHz Itanium II 807 1356

So the MIPS CPU does pretty well considering its low clockspeed, but Itanium II has a much higher peak perf. When you combine that with the monstrous bandwidth of an O3K machine, you get something pretty powerful.

2. Having developed for NUMA architectures, I am confused as to why this machine is designed the way it is. Unless they've done extensive modifications to the kernel, and especially the brain-damaged Linux thread libraries, you're going to end up with what are supposed to be threads of the same process running with different memory access properties.

Linux 2.4 with the O(1) scheduler is pretty good at SMP thread scheduling, but since the latencies accross NUMAflex are so low, process and thread placement aren't as important as they would be on, say, an IBM NUMA box, which is much more 'non-uniform' wrt memory latency. The 2.5 kernel should be even more scalable, as it'll probably include a NUMA-aware scheduler.

3. Even more confusing, what little press there is on this machine claims constant data access to anywhere in the combined memory space. NUMA by definition is non-uniform memory access. What's with that?

I imagine they're referring to the fact that you don't have to use a message passing API to do your app development, i.e. all the memory of the machine is in one big address space. Of course accessing different nodes will result in varying access times, but that's obvious.

Re:LINUX OS

[fgodfrey]

There are a large number of reasons going back to stupid internal politics (the offenders have either quit or been fired by now - see Rocket Rick as an example), but it basically came down to two basic reasons: 1) A conscious descision was made at some point (early '90's maybe?) that Irix wouldn't be ported to a radically different (*cough* little endian) architecture and so a port would be really hard (though not impossible) and probably more important 2) Linux for this thing can run any application that is written for IA64/Linux (which presumably will be at least a few) whereas Irix couldn't. You could add a Linux syscall layer, like the BSD's have done, but then you have to track changes to GPL'd software into something that SGI couldn't GPL even if they wanted to (as Irix contains source from some other vendors). So basically, it's a) difficulty of the port from a technical standpoint and b) application capture. Presumably, IBM had similar considerations for using Linux instead of AIX.

Re:LINUX OS

[wayne606]

I would say that AIX definitely does distinguish IBM from its competitors, just like showing up naked for a job interview would distinguish me from my competitors... What's their catchphrase? "It will vaguely remind you of UNIX?"

Re:LINUX OS

[chefren]

Lets feed the starving troll, then: The linux 2.6 kernel promises better overall scalability and performance on high-end machines whereas 2.4 is kind of lame in these respects (VM is worse than 2.2 infact) so maybe 2.4 really isn't the best (free) choice for a supercomputer? It remains to be seen exactly how good 2.6 is, coming 2003 to an ftp site near you!

Re:LINUX OS

[Anonymous MadCoe]

What strikes me even more about the thing is that they actually chose a GPL kernel and not a BSD licence kernel... Maybe the BSD licence isn't as superior as some people would like us to believe.

Re:LINUX OS

[d^2b]

I trust HP and Sun to be around longer than SGI though, and they won't fuck you over like SGI will.

As someone burned by the demise of Alpha, I can attest that all vendors suck. More precisely, their interests (never mind what the crack-heads in charge think are their interests) often diverge from those of their customers.

Re:LINUX OS

[sql*kitten]

True. The more relevant question would be: is AIX worth the bother of maintaining and porting? What value does IBM derive from that R&D expenditure. Does any of that serve to distinguish IBM from it's rivals in the marketplace?

IBM (and Sun and SGI) are hardware companies, so you might think that they would prefer a common OS and to compete on hardware. But that strategy has been shown to be disasterous for HP, Gateway, Compaq and even IBM themselves in the PC market. All these companies use their OS to position their hardware and leverage its capabilities to their target market.

Even today, the Linux community are working on the questions "how do we make a free Unix?", and the answer is of course Linux. But from day 1, IBM thought "how do we facilitate people running their data processing applications on our hardware?" and their answer was AIX. Sun thought "how do we facilitate people running their network applications on our hardware?" and their answer was Solaris.

So there is a lot of stuff in proprietary Unix implementations that adds value to them. I don't think anyone (not even IBM) seriously thinks Linux will ever replace AIX, but it does represent an avenue for them to penetrate back into the low-end space. (If you recall, IBM got their asses handed to them on a plate in the commodity x86 marketplace by Compaq and others). SGI have, for whatever reason, decided to make an Intel-based mainframe, and Linux is the way they can do that... but absolutely the last thing they can do is give away any IP that IBM could use to bolster its own Linux offering at their expense.

Re:LINUX OS

[Anonymous Coward]

but Sun stands alone behind the SPARC

That's not entirely accurate... There's several system vendors on the SPARC list.

Re:LINUX OS

[r0xah]

So help me and moderator's be kind, this is offtopic, but I'm pretty impressed that a Troll... which I am not... posted a message that got a Score:0, Troll was able to stem a conversation like it did. So if getting trolled for starting a 19 reply thread is what should be done I guess I will take it. The question was a honest one and I really did not know the value of Linux as an operating system for a supercomputer. PS. NO I don't want to see Windows 98SE or any Windows for that matter on one, but I just did not know if it would be the greatest choice.

Re:LINUX OS

[fitten]

There is more to a big machine than simply which OS gets the most bogomips. Can Linux be partitioned across a Sun 15K like Solaris can? Can you hot-swap processors/harddrives with it? There are lots of questions like these that have to be answered depending on what you intend to do with the machine.

The IBM 390 machines are not fast. People didn't buy them for their MIPS or FLOPS. They bought them because of their stability and uptime. It's less important that OS1 can serve up X amount of web pages per sec and OS2 can serve up 1.1X web pages per sec when what you want is that the machine *doesn't* go down because a CPU board just burned itself out. *That's* what big iron is about.

Re:LINUX OS

[Strog]

They also have OS/390, OS/400 and tons of things patented. I think they have they resources to build about anything they want. It probably isn't worth it right now to them to go that route.

Re:LINUX OS

[jaymz168]

This is more SGI schizo behaviour. They can't really decide what they want to do or be, what hardware platform they want to push or what OS they want to use. Another sad day in a long line of sad days for a once cool company.


Maybe they just use the right tools for each job instead of making a deal with one hardware co and pushing their products no matter it's suitability to the job.

Re:LINUX OS

[Strog]

While that is true, most are either niche or embedded. Sun is a driving force in SPARC but they don't enjoy the leverage they once did.

Re:LINUX OS

[fitten]

- Linux is a lot like Un*x. The type of people who mess around with these type machines are already familiar with Un*x (and many frankly refuse to even try to learn anything else). Stick with what's familiar.

- Un*x type OSs already have time-sharing down (many users on a single machine). While this isn't an issue on a desktop (because everyone has their own), it is an issue when lots of people want to share the $3M machine.

- Un*x type OSs already have remote login capability down (like the previous point). The locality of a machine you are using doesn't matter except for possible latency/bandwidth issues.

- Developers at the respective companies tweak the kernel quite a bit I would imagine. They aren't using the latest RedHat distro ISO they downloaded last night on it.

I've seen a number of MPI distibutions that simply did silly things like

foreach machine in machinesfile
rsh machine command

because it was easy. Of course, these run into problems with many machines (timeouts and takes forever to get started) *but* they wouldn't use anything else because "rsh was standard". This kind of software doesn't work for large systems. The people/companies who support these large systems like this have to solve these types of problems.

The other area of concern is compilers. These type machines have lots of processors but if you have a compiler that produces less-than-efficient code, you are robbing yourself. In a number of cases, GCC isn't going to be your best choice here so you need to find/make good compilers. It doesn't do much good to have a single processor that is capable of 10GFLOPS when your compiler will never be able to get more than 3GFLOPS out of it.

IBM, SGI, and the other companies that are moving to Linux are tackling these types of problems (they have to in order to be successful) and they have their own distributions for their machines.

Re:LINUX OS

[binaryDigit]

Well sorta. Notice that there are only two major computer manufacturers that support two major hardware architectures, IBM and HP. Everyone else sticks to a single primary arch. because it just gets too expensive to support any more than that. It makes it a lot easier when there is no overlap between the products as well. Now SGI has Irix/MIPS and Linux/Intel product lines and in many ways they compete with each other (one of the reasons they dropped the workstations, well that and no one was buying them). Now on the high end they've once again introduced product overlap.

Ditto for the OS. Though I guess one saving grace is that the nature of the software for these hpc systems is vastly different and simpler than those for a "general purpose" desktop machine, so it's not like they have to try to support a wide variety of apps across two os's.

You have to remember that SGI is a hardware manufacturer, not an integrator. They don't just pick and choose commodity parts and through a machine together (well ok, their Intel boxes were kinda like that). This is what I mean by schizo.

Re:LINUX OS

[nagora]

IBM (and Sun and SGI) are hardware companies

That's an over-simplification in the case of IBM; their consultancy arm makes more revenue (NOT profit) than the whole of Microsoft. They do hardware too but in recent years that has been seen as a method of increasing demand for their consultancy, which includes bespoke software.

If you recall, IBM got their asses handed to them on a plate in the commodity x86 marketplace by Compaq and others

But what they learnt from that is that allowing someone else to control the OS is madness. Since they can't get everyone else to use AIX it might make more sense for them to switch to Linux (or any Free OS, but Linux is probably the best option for them now) so that no one controls the OS.

I assume that you've heard the old joke "IBM and Microsoft got together to run a goldmine; Microsoft got the gold, IBM got the shaft".

TWW

What's in a name...

[swordboy]

Wow!

NumaFLEX... And to think... All that AMD could come up with was Athlon 64.

You'da thunk that they'd at least stuck a period or an 'e' on there somewhere...

eAthlon.64?

Re:What's in a name...

[gbv23]

Isn't anyone going to bash Intel? Oh wait its early yet. It is interesting that this SGI supercomputer is running Linux too. I do know that Intel is officially agnostic about what OS one chooses to run on their microprocessors.

Re:What's in a name...

[FaasNat]

eAthlon.64?
Dan Quayle says it's Athlone 64

Re:What's in a name...

[pete0t2]

the name actually has to due with the architecture of the computer - NUMA short for Non-Uniform Memory Access.

Pete

Re:What's in a name...

[Anonymous Coward]

No, but I am going to bash you because of your soft pear-shaped physic, thick glasses, and pasty white flesh. Here is some free advice- if you didn't hide in your parent's basement all day stuffing your face with Funions and tweaking your Gentoo install until it is 'just right', you might have some better luck with the ladies.

Re:What's in a name...

[Anonymous Coward]

THE PSYCHOLOGY OF MODERN LEFTISM
6. Almost everyone will agree that we live in a deeply troubled society. One of the most widespread manifestations of the craziness of our world is leftism, so a discussion of the psychology of leftism can serve as an introduction to the discussion of the problems of modern society in general.

7. But what is leftism? During the first half of the 20th century leftism could have been practically identified with socialism. Today the movement is fragmented and it is not clear who can properly be called a leftist. When we speak of leftists in this article we have in mind mainly socialists, collectivists, "politically correct" types, feminists, gay and disability activists, animal rights activists and the like. But not everyone who is associated with one of these movements is a leftist. What we are trying to get at in discussing leftism is not so much a movement or an ideology as a psychological type, or rather a collection of related types. Thus, what we mean by "leftism" will emerge more clearly in the course of our discussion of leftist psychology (Also, see paragraphs 227-230.)

8. Even so, our conception of leftism will remain a good deal less clear than we would wish, but there doesn't seem to be any remedy for this. All we are trying to do is indicate in a rough and approximate way the two psychological tendencies that we believe are the main driving force of modern leftism. We by no means claim to be telling the WHOLE truth about leftist psychology. Also, our discussion is meant to apply to modern leftism only. We leave open the question of the extent to which our discussion could be applied to the leftists of the 19th and early 20th century.

9. The two psychological tendencies that underlie modern leftism we call "feelings of inferiority" and "oversocialization." Feelings of inferiority are characteristic of modern leftism as a whole, while oversocialization is characteristic only of a certain segment of modern leftism; but this segment is highly influential.

Beowulf cluster of cooling necessary :)

[Meat Blaster]

Having helped set things up, I was offered an opportunity to see the system in action. It's fast, much faster than previous offerings in the line, and apparently enough so (as marketing tells me) it's well worth upgrading aging supercomputers or clusters.

Additionally, it offers unparalleled scalability in the line of Linux supercomputing. This is a system built to grow with a business, although your business better be pretty much grown already to back the check you'd need to fill out to buy it.

My conclusion: it's an excellent largish solution for academia seeking a more stable environment than can be achieved with Beowulf clustering and excellent pricewise solution for businesses seeking to expand without sinking a lot of money into unnecessary costs.

Re:Beowulf cluster of cooling necessary :)

[binaryDigit]

it offers unparalleled scalability in the line of Linux supercomputing

Wow, sorry but that sentence smacked of marketing/speak. "Unparalleled scalability"? Hopefully this was just a play on words ;)

businesses seeking to expand without sinking a lot of money into unnecessary costs

What would those "unnecessary costs" be? (just asking).

Re:Beowulf cluster of cooling necessary :)

[Meat Blaster]

What would those "unnecessary costs" be? (just asking).

Proprietary software. The bulk of the costs with anything supercomputing falls across the non-standardized but more reliable hardware, the service contracts necessary in a mission-critical environment, and the software that runs on the system. Having Linux cuts back on that, although no doubt some software tailored to work in this environment will still be pricier than its counterparts on our x86 hardware because of the smaller customer base and ability to pay.

Re:Beowulf cluster of cooling necessary :)

[Sinical]

My problem with one of these is that Itanium2s are so damn hot, I wonder about the density of computational power. Granted, an individual Itanium2 smokes the hell out of an R14k, but since our 600MHz R14ks use on the order of 15W and I think an Itanium2 is up around 150W, we can get many times the computrons (R14ks aren't fast, but they aren't *that* slow) per Watt. Cooling is kind of limiting factor, because these machines go in labs, not prepared computer rooms.

Right now we have a couple of 8-way Onyx2s and we're in the process of building an 8-way Origin 300. For the kind of work we do (realtime simulations), where latency is king, we prefer to put each part of a task on its own CPU, so having 8 processors is nice, whereas having an 8-way Itanium2 would be prohibitively costly to cool, although it'd be nice for when we just crank: see 483/499 SpecInt/FP base for 600MHz R14k vs. 810/1350 SpecInt/FP base for 1GHz Itanium2.

I *would* like to move to Linux from IRIX, I think. I really like the IRIX realtime support (all the REACT stuff), but I am tired of poor tool support and limited lack of updates, etc. I think $500k worth of machines (in *that* lab) would warrant a better resolution of some issues we've had.

Finally, I very much anticipate the day that these Linux scalability improvements filter down into something like a 4-way Clawhammer system. That system could very likely do a lot of our work (at what, maybe $20k for a system?) that we now drop $50k on for SGIs.

According to...

[SexyKellyOsbourne]

According to SGI will unveil its

According to who?

I demand an answer!

Re:According to...

[eddy]

According to who?

SGI. The sentence use the practical reverse-bananana compression idiom, the original which was first revealed in the holy book of HAKMEM

Please add the string "I am not a" in front of your Geek Member Card.

Re:According to...

[jarrod.smith]

My original submission had the URL inserted between "to" and "SGI". So it read: According to http://www.sgi.com/features/2002/nov/hpc/ SGI will unveil...

almost made it

[painehope]

yep, I was slated to go, and then got told "no, we don't have the money in the budget"...and to top it off, even /. is rubbing it in...
puts head down and weeps as images of shiny, multi-colored SGI systems float through my head

(which runs Linux as its OS)

[Anonymous Coward]

(which runs Linux as its OS)

WRONG! It runs linux as it's kernel.

Re:(which runs Linux as its OS)

[Anonymous Coward]

No, it runs Linux as its operating system. "Linux" is a registered trademark of Linus Torvalds, and has been since 1994. The name "Linux" describes "computer operating system software." In other words, the name "Linux" describes the entire operating system, not just the kernel as some people from the FSF would have you believe.

Because "Linux" is a trademark, it is illegal to modify, combine, or otherwise dilute the mark without explicit permission from Linus Torvalds. So the use of the name "GNU/Linux" is not only inaccurate, it's also infringing, and therefore illegal under United States jurisdiction, and jurisdictions in countries signatory to the Berne Convention.

If i remember correctly

[Nazmun]

SGI was working on Linux (as in modifying the linux kernel and some other software components) for something like this.

Can you give me one good reason why Linux will not be a good supercomputer?

Re:If i remember correctly

[Anonymous Coward]

Can you give me one good reason why Linux will not be a good supercomputer?

Because it is an operating system, not a computer?

Re:If i remember correctly

[khuber]

Technically Linux is just a kernel. You can't do much at all with just a kernel. You could print AAAA from one process and BBBB from another, but who would want to do that?

-Kevin

Damn straight! It runs OSCAR, not "Linux"

[SexyKellyOsbourne]

Linux = kernel
GNU/Linux = operating system

It does not run GNU/Linux -- it runs OSCAR.

Get it right, Ho^Hemos!

Re:Damn straight! It runs OSCAR, not "Linux"

[Anonymous Coward]

actually, OSCAR is a GNU/Linux fork.

After all, most GNU/Hippies are grouchy and live in a garbage can.

IABCOT

[Jungle guy]

The obligatory post....

Imagine a Beowulf cluster of these!

Re:IABCOT

[Anonymous Coward]

idiot

You're way behind the times.

[aussersterne]

The "open source developers" of which you speak now count among their number professional developers from companies like IBM and SGI who have been working hand over foot for the last few years to bring Linux to large computing platforms. Check the development mailing lists.

It's not like Linus has been sitting in his bedroom coding for a decade and now suddenly SGI is going to download the kernel and throw it at supercomputing hardware. Big companies are and have been investing development dollars in Linux in order to make Linux ready for platforms like this one. And the great thing about Linux is that whatever SGI or IBM adds, the community tends to get back in the form of permanent enhancements to Linux.

NUMA the lion

[Anonymous Coward]

watched over the pridelands
while the terrible Scar
hunted the antelope into extinction

2.5 has full support

[DarkMan]

Well, damn as nearly. Linux is only in catchup when the manufacturor will not release spec on how to use thier hardware.

When it comes to NUMA machines, Linux is up there. It may not excel at everything (yet - I'm sure that it will get there if it's not already). I'm mostly talking about the 2.5 kernel series.

From the status list

New scheduler for improved scalability (Ingo Molnar)
Support for Next Generation POSIX Threading (NGPT team)
Syscall interface for CPU task affinity (Robert Love)
Hotplug CPU support (Rusty Russell)
NUMA topology support (Matt Dobson)
Per-cpu hot & cold page lists (Andrew Morton, Martin Bligh)
NUMA aware scheduler extensions (Erich Focht, Michael Hohnbaum)

The biggest performance changes in 2.5 seem to be in the many thread and many CPU region, including NUMA.

I'd trust it. (Yes, I do do scientific supercomputing).

it may be called linux

[ArchieBunker]

But at the core it won't resemble anything you've seen. They use linux has a base and design it exactly to their needs. It won't be of much use to about 99.95% of the linux user base. The only reason they chose linux is because its already established and porting over IRIX would mean a near total rewrite. BTW they also own the original UNIX trademark so you can legally call IRIX "UNIX".

Re:it may be called linux

[Twirlip of the Mists]

WTF are you talking about? SGI does not own the original UNIX trademark. The Open Group owns that trademark. SGI has gotten various versions of IRIX certified by The Open Group as conforming to various UNIX standards, and that's why they're entitled to call IRIX "UNIX."

But

[Anonymous Coward]

Can you run hurd on it?

Sound of one hand clapping

[Sponge Bath]

Imagine a Beowulf cluster of these!

I wonder which is worse, Beowulf posts or goatse.cx links?

Re:Sound of one hand clapping

[stevejsmith]

Well, let's do a test:
asdf
Imagine a beowulf cluster of these!

Now which one made you wish you had mod points more?

Re:Sound of one hand clapping

[Sponge Bath]

Now which one made you wish you had mod points more?

Neither. Suffering is caused by desire and I am on the noble path.

WHY LINUX!?

[stevejsmith]

LINUX!? WHY LINUX!? Why not a stable OS...




Like Windows ME!

Re:WHY LINUX!?

[shaitand]

who modded this flamebait?? this is hilarious. *hint* mod *hint* he COULD have been sarcastic...

Re:WHY LINUX!?

[Anonymous Coward]

Why the hell would I have been sarcastic? I still don't understand why everybody thinks it's funny that one of the world's most powerful computers would run one of the world's bugg^H^H^H^Hfeature-filled operating systems.

MOD DOWN! GOAT LINK

[Anonymous Coward]

That link gets me every time.

Let's TRY to be objective...

[erroneus]

...okay so Linux is being applied to all these terrific projects of scale both large and small. Is it because it's an open system with seemingly hyperactive development or is it because it's simply better than anything else out there?

I'm trying my best to maintain a level of respect for the MS operating system product so I'd like to know if anyone knows of any amazing projects MS OSs are being used for. For that matter, what about other OSs in general?

I think it's terrific that Linux is used this way but I wonder if it's because of its availability or because of its technology. I tend to think it's for its availability but I'm no expert. I think answers and other points of perspective from others in the Slashdot community would help to show some objectivity here.

Re:Let's TRY to be objective...

[sql*kitten]

...okay so Linux is being applied to all these terrific projects of scale both large and small. Is it because it's an open system with seemingly hyperactive development or is it because it's simply better than anything else out there?

Linux is being used because there's no x86/Itanium port of Irix. SGI use Irix, which as of 6.5 is a superb Unix implementation, on their MIPS hardware. IBM use Linux because of all the software that's available for it, but Linux runs within a virtual machine on top of their proprietary zOS.

XFS has already made it into Linux, maybe some other Irix stuff like GRIO will be next.

Re:Let's TRY to be objective...

[ChaosDiscord]

I think it's terrific that Linux is used this way but I wonder if it's because of its availability or because of its technology.

I'm involved with a number of high energy physics experiments around the world (from a "physicist needs an obscene amount of computer power but a minimal budget, I try to give it to them" standpoint). Everyone is using Linux clusters at the moment. Why? Two reasons.

The first is price. None of these projects are rolling in money. Saving a few thousand dollars while setting up a hundred node cluster is a big win. The people working on the projects are technically skilled enough that a Unix varient is not significantly harder to use than a Windows variant, so there is no increase in TCO due to support.

The second is trust. They've been repeatedly burned by proprietary software. They run into a problem and the publisher isn't inclined to help (or wants more money than they have to fix it), and they're forced to fine another solution. Linux may not be perfect, but they're free to fix their own problems. They don't view it from a "Free Software is Ethical" view, but from a pragmatic "we've been repeatedly screwed and it isn't happening again" view.

Re:Let's TRY to be objective...

[bmajik]

http://www.microsoft.com/windows2000/hpc/

Cornell has some windows clusters that they seem to like ok.

http://www.tc.cornell.edu/

Re:Let's TRY to be objective...

[Anonymous Coward]

Exactly, I've been once burnt by proprietary
OSes, not for supercomputing but for astronomical
data acquisition systems (not very fast embedded
systems, the real time properties being almost
irrelevant).

The story:

- We get a copy of a software, find a showstopper bug, mentioned it after having the certainty that
it was in the OS and not in our code.

- we receive an upgrade less than 2 weeks after mentioning the bug(there was a release every 3 or 4 months and we had been developing our own software in the meantime).

- install the upgrade in a very optimistic mood
since the first ilne in the release notes was
that the specific bug we mentioned had been fixed

- test again, bummer, the bug had not been fixed
or at least not properly. Waiting another 3 months for the upgrade would have a major setback

- I did disassemble the relevant part of the software, ended up with about 50Mb of text files
on the disk and found the bug in about 2 days.
I patched the code with a hex editor (6 bytes
to patch).

This was in 1992, the system worked fine with my patch until we upgraded it wit faster processors
in 1999. Guess what, the new systems run Linux.
There may be bugs, but at least I have the source code so fixing or tuning the code is easy.

Re:Let's TRY to be objective...

[mt-biker]

I think your two reasons are somewhat conflicting. An institute that will choose Linux to save a few thousand dollars is unlikely to be able to spare the manpower to debug/develop Linux. To put this another way, how many months of Linux-developing does your few thousand dollars buy you?

Also, in my experience, institutions with this much computing power (and they _do_ buy a lot of power), have a lot of clout when it comes to getting OS problems fixed.

I think the main reason is the cost of the hardware - it's simply much cheaper to rack up cheap IA32 boxes than to buy RISC workstations/servers.

The result is, as you say, a total dominance of Linux in the HEP computing world.

Re:MOD DOWN! GOAT LINK

[Anonymous Coward]

We should probably include "MOD DOWN! GOAT LINK!" in there too. Anybody stupid enough to leave domain name showing off and to not check the link's location ought to be doomed to stare at a...er...I can't say it. Too disgusting to put into words.

kernel version?

[botmfeedr]

what kernel version?

Re:kernel version?

[Anonymous Coward]

Windows XP.

A general SC2002 comment...

[isaac]

I've been hanging out at SC2002 all day, and I can tell you that nearly every booth on the show floor is showcasing Linux. Of course all the Linux cluster vendors have it, but so does sgi, Sun, IBM, Intel, AMD, HP, Compaq (separate booths - guess the merger isn't *really* done yet), and all the smaller vendors, to say nothing of all the research labs, etc.

Large linux systems and clusters are really all the rage right now in SC circles. I think the only booths I saw here not using Linux were the Apple booth (though they did have one gorgeous brand-new G4 running Xfree and twm, the sick bastards!) and the Japanese manufacturers NEC and Fujitsu (off in their own worlds, as always).

Linux isn't a big surprise to the SC set, though - this is a group that's used to UNIX. Hell, Microsoft doesn't even have a booth here, and they were at the last LinuxWorld conference.

-Isaac

Re:A general SC2002 comment...

[zuhl]

Apple Computer has a booth there? Wow. Guess they really are trying to live down that whole "it's just a toy." complex they got a long time ago. :-)

I saw on the floor plan that this is indeed correct. Amazing how times change. Maybe they really are getting their act together. The new XServe looks like a nice 1U server.

Wish it were time to upgrade our main servers again.

Re:A general SC2002 comment...

[telemonster]

Cray anywhere in sight pimping anything other than NEC hardware? SV2? SV2? Where are you? Does SGI have the Origin 3900 system there as well?

Re:A general SC2002 comment...

[isaac]

Cray's pushing the X1 right now. SGI does have a lot of O300 and O3000-series hardware including the 3900 (which is just an Origin 3000 using super-dense CPU bricks - 16 cpus per 4u, compared to the previous 4).

Supercomputers are expensive.

[raehl]

You pay a lot of money to get a very large computer that can do very large tasks very fast.

Wasting 20-40% of the resources of your $2k desktop on your OS's feature bloat may not be too bad, but wasting 20-40% of the resources of your $5 mil supercomputer is a lot of money.

Or put another way, Linux is used in supercomputers because it can be set up to do exactly what you want it to, and ONLY that - which for most HPC applications is compiling and running custom code to solve Big Problems.

You're not going to use a 512 processor supercomputer to Save Christmas by being able to get those pictures off your digital camera without spending 3 hours trying to download the drivers.

Re:Supercomputers are expensive.

[mt-biker]

Wasting 20-40% of the resources of your $2k desktop on your OS's feature bloat may not be too bad, but wasting 20-40% of the resources of your $5 mil supercomputer is a lot of money.

<sarcasm>Well, it's a pity that the supercomputer vendors haven't realised that then, isn't it?</sarcasm>

Come on now, you think that the vendors don't optimise their OSs for every last bit of performance? Of course they do. They're all in competition here, and every one of them is struggling to get every last FLOP out of their processors.

The reason that we're only just now starting to see large CPU counts in Linux boxen is because it's only just now becoming viable to scale Linux. Other vendors' UNIXs mostly scale much better than Linux.

I believe that SGI's Linux will (at first) scale to only 32 CPUs, and I'll be interested to see what sort of performance they get on such machines. I'd wager that Linux will not scale nearly as well as, say, IRIX.

OTOH, the recent slashdot thread on the performance of the 2.5 kernel is reassuring - way better performance on parallelised tasks. I suspect that these improvements are being driven by all the vendors who want to use Linux on their high-end, high CPU count machines.

It makes sense, really

[tyler_larson]

Linux is great for many projects like this because it posesses some qualities you won't find most other places. In particular:

• No royalties. They can use it, hack it, sell it. Whatever they want, and never have to cut a check to anyone.
• The resources. The Linux development community is unlike any other. Using Linux means you have access to all sorts of development and product resources for absolutely free. The newsgroups are friendly, the documentation is deep. And if you're doing something weird, do it with Linux and chances are someone will help you.
• The name. If you need to impress the suits and get funding, Linux is a name you want to include. For a lot of people, Linux=cutting-edge technology. They don't understand it, but they know it's powerful, and they know it's gaining ground fast.
• The power. There's no two ways around it. Linux is a powerful and flexible system. You can push it, pull it, tune it and tweak it to do just about anything. Unlike some other OSes, the kernel was written to stand on its own, not necessarily part of any prefab package. There's no GUI code in the TCP/IP stack, and it's just as happy in a PDA as it is in a supercomputer. Could you honestly immagine LLNL buying a Windows-based clustered supercomputer? Yeah. Me neither.

Using Linux helps companies keep from having to re-invent the wheel while at the same time keeping their options open and their money in their own pocket. It works so well it's a wonder more companies don't use it.

For those afraid of the GPL, BSD presents a tempting alternative. But again, you lose a bit of the development resources and don't have the name to use to get your funding. For most people, though, GPL isn't a problem.

thats cool and all, but

[paradesign]

i want to SEE it. What does it look like, give me some jpgs to oogle over. Im sick of just imagining these supercomputers and beowulf cluster, lets see them now! Or dont they have digital cameras at these fancy affairs.

Re:thats cool and all, but

[Omega996]

http://www.sgi.com/features/2002/nov/hpc/images/lg _origin_3900_out.jpg

Loopback

[Anonymous Coward]

I'd like to know if the loopback interface was optimised for such a powerful system.

Re:Loopback

[Anonymous Coward]

i know that the /dev/null device driver has been optimized for data throughput. Evidently it's O(0) speed.

WHY ME!?

[Anonymous Coward]

Hehe...

Numaflexes

[Anonymous Coward]

Imagine a Beowolf Cluster of THESE!!!

This morning...

[dargaud]

...I had a visit from my friendly SGi representative and he was trying to sell me... this thing after I asked about Linux clusters. I didn't pay too much attention but he was all hush-hush about it, saying that it hadn't been announced yet. It seems impressive. The smallest machine will have 16 nodes and NumaFlex certainly beats the shit out of a Gb Ethernet. He couldn't quote prices, not that I wanted to know...

What's special about this is...

[leeet]

You can buy this machine and run redhat out of the box. But if you want to kick some ass, you need to install all the tweaked out drivers and modifications SGI made in the kernel. This is the stuff that makes the difference (the secret sauce).

Recent benchmarks showed that SGI's customs modifications gave it almost 2x on throughput performance (versus IBM).

Don't forget that some people don't care how much it cost, they only care about real performance. A linux cluster just won't cut it...

Re:What's special about this is...

[Twirlip of the Mists]

You can buy this machine and run redhat out of the box.

Are you absolutely positive about this? Like, have independent confirmation on this from a knowledgeable SGI employee? Because I'm almost completely certain that this is not, in fact, even remotely true. My understanding, which is only slightly out of date, is that you will have to run a kernel built with SGI's patches, of which there are many.

But if my info is wrong, I'd like to be corrected by somebody who knows better than I do.

Re:What's special about this is...

[Anonymous Coward]

He's right. I work for SGI, and can confirm that the goal is to have standard RedHat work out-of-the box on this machine. But as the poster said, if you want the best performance, you'll need SGI's optimized drivers. (I know this doesn't mean much coming from an A.C....)

this is true

[leeet]

SGI has been coding for many years (3-4 at least). It released many code in the public domain such as the (defunct) Apache acceleration program which was simply amazing. Don't forget XFS, one of the best filesystem out there. I feel that for marketing reason, they will not release any "performance tuning" code anymore and keep it for themselve. That's good for customers but not so good for us. In a certain way, such code is probably proprietary to their architecture.

Why LINUX OS?

[leeet]

Because if you take a kid fresh out of the college, he can run Linux. IRIX? hum not so sure.

Another reason? Oracle. You will see some kick ass performance and that'll bring big sales for SGI I'm quite certain! Oracle doesn't run on IRIX although IRIX on MIPS hardware has one of the best performance ratio in the supercomputing area.

It's not about the cost. Everyone knows very well that the cost of the OS isn't really helping sales. It's how familliar people are. Which one would you buy? an IBM box running AIX or Linux? I bet you don't want to learn AIX and will probably choose Linux if you can get pretty much the same performance..!

Re:Why LINUX OS?

[Liam]

Oracle most certainly does run under IRIX. We run it, as do several other organizations that I know of. Of course, you'd never know it to talk to Oracle. They have the most confusing product matrix I've ever seen, but it's there. You may need to bug a sales person (and bug, and bug...)

Re:Why LINUX OS?

[Twirlip of the Mists]

Some months ago-- earlier this year or late last, I forget which-- Oracle announced the official end of support for IRIX. Their 9i series of products will never run on IRIX, at least unless the plan changes. The last version of Oracle to run on IRIX was, and will continue to be, 8i. I believe the specific version is 8.1.7.

This is moderately important. Lots of people still use 8i, so it's not the end of the world yet. What is the end of the world is the fact that Oracle will no longer develop the Oracle client library for IRIX. In theory, the 8i client library will let you talk to a 9i database, but as soon as Oracle breaks that compatibility (with 10i, or whatever) your Oracle client apps will no longer work on IRIX either.

So you're both right. Oracle runs on IRIX, but only in older versions.

In other words, "Girls, girls. You're both pretty."

Re:Why LINUX OS?

[telemonster]

Actually, Oracle licensed the SGI Origin 300 to use as a "database appliance." Rumor has it Oracle ran faster when tuned on IRIX than it did on Solaris and the other platforms. The Origin 300 was going to be rebadged as an Oracle product, and sold as a complete solution.

Don't know what happened. SGI might have screwed up the deal, or maybe McNealy got mad and rolled over and spanked Ellison. Oracle never sold the appliance, and never admits to having 9i on IRIX.

It would probably make Sun look too bad.

And all you whiney Linux people, IRIX isn't extremely wierd or unique. It is actually quite nice.

I don't know why, but anytime someone mentions Linux the press goes apeshit. The IRIX/Mips versions of these systems scale larger, have a prooven track record on a robust 64 bit operating system, and consume less power and produce less heat. But this is slashdot, and if it ain't Linux the kiddies freak out.

Long live IRIX! SGI, get your marketing together you fuckups.

If you're interested in what SGI is doing...

[avonhungen]

...there will be a link to an SGI rep discussing what they brought to the show this year. He specifically discusses the Intel-based stuff they're working on.

http://www.sc2002.org/

in qt and real

Aaron
SC'02 webcasting committee

Close to linear scalability

[leeet]

SGI's tweaking allows them to achieve very close to linear scalability.

Just remember when a few months/years ago, Linux wasn't scaling well over 8 cpu's. SGI has a 128 CPU solution already. I have to admit that these guys made a VERY good job!

Easy equation...

[leeet]

SGI = best throughput/bandwidth, Database = Need throughput, Oracle != IRIX but Oracle = Linux.

Obviously, SGI is in need of money. They know how to do the right thing with performance so this will open some doors that were closed before...

Also, you can bring machines closer to the admins w/o IRIX experience. Some people are scared to learn, you know...

Now remember, SGI offers up to 128 cpu in single system image. This is serious compute power and no one else can offer it. You're not talking beowolf, clusters, etc. It's *1* machine.

Re:Easy equation...

[ninewands]

Quoth the poster:

Also, you can bring machines closer to the admins w/o IRIX experience. Some people are scared to learn, you know...

Sssssh ... don't tell anybody this ... but a competent Linux admin can probably get up to speed on Irix in about one day ... well ... maybe not on hardware like the Origin 3000, but on SGI workstations the system layout is so similar it's scary ...

ahem...

[/Idiot\]

You want to see images: http://www.sgi.com/features/2002/nov/hpc/images/lg _origin_3900_out.jpg

This is also true..

[leeet]

..that some people DON'T CARE ABOUT THE PRICE! All they want is serious kickass performance. They want the answer NOW!

This is what sets SGI apart, their performance...

Even if the Dodge Viper is a fast car, how come you don't see it racing against F1's...? It's simply because don't care about the price. They don't mind spending $20k on a friggin' steering wheel...!

That's because windows != supercomputing

[leeet]

Windows can scale to what? 32 cpu's?
Are they any x86 solutions that offer 32 cpu's systems anyway?

My conversation with one of the sales reps

[Leebert]

It's funny, I talked with an SGI rep there and he said "We haven't annouced this yet, so you don't see it sitting there." To which I replied "Why don't you not tell me about what's not sitting there." "Sure, I won't", he said, and proceeded to tell me all about it. :)

Seriously, it looks pretty sweet, but I was more excited by the Origin 3900 -- 16 processors in one C-Brick (4U).

Re:My conversation with one of the sales reps

[Anonymous Coward]

Seriously, it looks pretty sweet, but I was more excited by the Origin 3900 -- 16 processors in one C-Brick (4U).

Shh. Don't tell anybody. The new server is nothing more than an Origin 3900 (a.k.a. SN2) with Itanium2 processors instead of R14000 processors. The inside of a MIPS CX-brick is mostly empty space. It was designed this way, back in the mid-1990s, specifically to accommodate IA-64 CPUs. The original plan was to release an SN1 (or Origin 3000) variant with Merced chips, but Intel kinda dropped the ball there, so the plan was changed to include an SN2 variant with McKinley chips. That's what you'll be able to buy starting in January.

Posted anonymously to protect my job.

Re:My conversation with one of the sales reps

[Refried Beans]

Seriously, it looks pretty sweet, but I was more excited by the Origin 3900 -- 16 processors in one C-Brick (4U).

Shh. Don't tell anybody. The new server is nothing more than an Origin 3900 (a.k.a. SN2) with Itanium2 processors instead of R14000 processors.

Wrong, the Origin 3900 is just a repackaged Origin 3000. It doesn't use the SN2-related ASICs at all.

The inside of a MIPS CX-brick is mostly empty space. It was designed this way, back in the mid-1990s, specifically to accommodate IA-64 CPUs.

The CX-brick is the new C-brick for the Origin 3900. The old C-brick was mostly empty space.

Here is a close up...

[leeet]

Here
Maybe someone can describe the bricks?

Re:Here is a close up...

[Twirlip of the Mists]

Maybe someone can describe the bricks?

Yeah, maybe.

Speed

[leeet]

Having the chance to work with an IRIX version, I can tell you that you can actually do TCP over Numa at the speed of 3.2Gpbs so it's more than 3 times.

They also have a faster interconnection that allows 6.4 Gpbs so you can copy the equivalent of a whole CD rom per SECOND(!).

I wish my ISP could do that, unfortunately, my PC is decades behind that kind of performance...

Gigabit vs GigaByte... even more speed

[green pizza]

The current generation of SGI NUMAflex based machines use a mesh of full duplex 3.2 GByte/sec interconnects. That's 25.6 Gbit/sec.

That's way more than 3 times. Plus the latency is several orders of magnitude less.

The tradeoff is cost. A fully populated rack (32 Itanium2 CPUs or 128 MIPS R1x000 CPUs) starts at $1M can can easily run upwards of $4M. If your task is CPU bound, then a homebrew cluster will be almost as good. If your task is I/O bound, you can't beat the Origin. Until the Cray X1 ships, anyway.

Also keep in mind that while an Origin system can be partitioned, they are typically run as one single image system. The beasts easily expand from 2 CPUs up to 512 (even 1024 with special support from SGI). The cross-system memory latency increases with the larger configurations, but the net cross-section bandwidth/thruput increases linearlly with the CPU count. Very efficent design.

Pretty sweet machine. Again, until the Cray X1 ships! :)

Imagine a Beowulf cluster of this post!

[Anonymous Coward]

Imagine a Beowulf cluster of this post!

== TrollBuger
(acting like a CHICKENSHIT TOSSER by posting ANNONYMOUSLY!)

on only one processor?

[Anonymous Coward]

in some sort of 32-bit emulation mode? using only a half gig of ram? yeah, i bet that would be GREAT.

Last Post!

[alpg]

For if there is a sin against life, it consists perhaps not so much in
despairing of life as in hoping for another life and in eluding the
implacable grandeur of this life.
-- Albert Camus

- this post brought to you by the Automated Last Post Generator...