Slashdot Mirror
SGI 750 Itanium Server
foobar104 writes: "Today SGI announced their SGI 750 server, a dual-processor IA-64 system based on the W460GXBS2 motherboard from Intel. The 750 will ship with Linux (probably SGI's tweaked version of Red Hat; that's what they've used before), and they say it'll be available in July. (Usually that means first customer shipment in July, with volume shipments coming sometime after that.) The press release is here, and more technical info can be found here. In other news, HP also announced some IA-64 products today."
--
Forget Napster. Why not really break the law?
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
Ok, then what -is- relevent?
What's relevent is that a big-name company is shipping Linux on an Itanium box, as a -STABLE- configuration, before Microsoft can get theirs out of beta.
What's revelent is that this is a publicity coup for both SGI (a company that -was- supposed to be dead, by now), and Linux (some "toy OS" from a country where they all speak funny).
What's relevent is that, when executives ask "But can we run Application XYZ, from our old 98 machine on it?", the answer is YES! (That question, and variants thereof, have made or destroyed more systems than every coder alive has had hot dinners.)
THESE are the "details" that are relevent, because THESE are the details that could see Linux fade from view, or double its userbase, overnight. These are the details that could spell the final chapter of SGI, or mark the start of a turn-around that could yet terrify the supercomputer industry, once more.
Yeah, sure, all of us on Slashdot (ignoring trolls) already know Linux can run WINE, is mostly (or totally) 64-bit compliant for the ia64, and we all know that the media LOVES stories of David vs Goliath. We alread know all that.
But we're not the ones that matter, in all of this. We're already using Linux, *BSD, QNX, Exopc, BeOS, etc, or some combination of the above. The people who matter are Joe and Jane Doe, who financially advise a bunch of largish firms and who know nothing about technology apart from what the front page says.
The people who matter are the executives, the managers, the key people who make key decisions. The moment they're Turned to the Linux Side of the Force, you're talking big numbers of desktops.
The people who matter are the people who, when they stand up to speak, the media is there, listening. Get one of those to believe that this could bring financial propsperity, and/or a local industrial boom, and you could yet see a penguin added to the stars and stripes.
SGI's decision is small, in and of itself. It won't make any major waves, alone. But all it takes is a tiny pebble, to create an avalance, given the right conditions. Some of those conditions exist, and the rest are not beyond the existing Linux community and some of the key Linux players (eg: SGI and IBM).
Between now and Microsoft's true 64-bit offering, Microsoft are vulnerable to a market coup. Pull that coup off, and it won't be Microsoft with a 98% presence on the desktop. This is a potentially critical moment. Strategy and timing will be everything.
But will it happen...?
Tune in to next month's exciting episode of...
Linux Trek III - In Search Of Sparc
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
The fact is that SGI is the only ones really using the MIPS chips. So they decided to use standard parts, and do they intense customizations themselves like they've always done. The problem is that it was going to be insanely hard to port IRIX, so instead, they decided it would be easier to make Linux into IRIX than to port IRIX to a new chip. On top of that, you get the support of the free software community - and the people who will be buying SGI are those in-the-know.
As for the Origin, they are still planning on doing the major engineering work to make it completely robust, only using the more popular Itanium chips.
Also, IRIX is no longer needed. Why? Previously they needed an O.S. that was geared directly to their hardware. With Linux being free software, they can tailor it completely to their hardware without the problems of completely writing an operating system. They can use the standard Linux tools and configurations rather than having their own.
I think it's a great move.
SGI needs to get back to what it knows how to do - make kick-butt super-high-end hardware. When they went down to the midrange with their NT boxes, they found out they couldn't compete. It's still hurting them. If they can throw off all of the unnecessary junk - proprietary operating system, strange chipsets, etc., and just stick to making super-high-end graphics production boxes, they will do well.
Engineering and the Ultimate
This is not a cheap toy, you have to wonder what SGI has in mind for its target audience... I mean, they are bundling "NAG Libraries, Vampir, CAPTools [and] SCSL", all either math or parallel computing oriented. It's got one full gigabyte of RAM and the monitor is optional. That makes you think SGI wants to sell this thing as a node in parallel computing cluster. But then you note it's got a big fat SCSI drive with a big fat SCSI controller, neither of which have much to do in a Beo-node type of machine. So, it's a workstation. But then again, the monitor is optional and the graphic card (ATI XPERT 2000, read: Rage 128 Pro) is lame, to say the lest. If this is a workstation, why didn't they include the SGI VPro (read: GeForce)? Are they having trouble getting NVIDIA to support the IA64 architecture?
Other than its ability to run on cheap (price and often quality) hardware, I still don't understand SGI's movement to Linux. I guess that I am showing my ignorance here, but it seems to me that Apple and SGI are in similar situations right now in some respects. Both companies historically have relied on income from the hardware side of things while making a closed OS/hardware system that for each of their respective markets is very effective. The difference between Apple and SGI however is that SGI already has a UNIX OS with a GUI (however difficult it is to manage compared to OSX), and Apple is developing UNIX with a GUI (easier to manage, more powerful in some respects etc etc etc...). Both companies need major transitions to survive, but why Linux/Intel?
IRIX is already mature, stable, fast, with great graphics capabilities and IO capabilities, so I ask again, why move to Linux and Intel? I'm not expecting anyone to defend SGI here, I just don't understand. Both SGI and Apple obviously want to benefit from the open source paradigm while still remaining in business with proprietary OS's. (I am guessing here for SGI as I assume that they will make their OS on a proprietary linux model like the Red Hat setup they have used before). The approach Apple is taking certainly makes sense to me by developing a UNIX OS that includes the opensource Darwin, but I am totally clueless as to what SGI is doing here. What makes Linux more attractive than simply continuing to develop IRIX and putting more effort into improving, simplifying some features, and pushing development for IRIX? (among other changes to their business model) Again it seems to me that SGI is making another crucial mistake here as the developers that have tapered off work for IRIX have not for the most part started developing for Linux (although I know of quite a few examples), primarily they have lost ground to Wintel. (thus SGI's misguided attempt at Wintel/SGI boxes I guess)
In short it appears that they are trying to make Linux/Intel into what they already have in IRIX/MIPS, only with cheaper hardware which seems awfully dangerous to me for both end users and the company.
Visit Jonesblog and say hello.
Is that economies of scale trump superior hardware all day. SGI sees the inexorable creep of NT boxes slowly coring their market and they had to make a decision: Either go head to head with microsoft or take a risk in another type of market.
The commodity software market is totally separate from the standard one. You cant really make money by selling copies, so you have to find another way. Value-added services and brand recognition are the biggest assets in this market, which is not nearly as lucrative as selling shrink-wrap.
It is a huge risk for SGI, trying to take a growing share of a smaller market, versus a shrinking share of a larger one. It is a calculated risk though. They are not going whole-hog however: they will still ship proprietary code.
That's not a server, it's a workstation (though it ships with low-end ATI graphics). The 750 has been available to "qualified developers" since early March so I doubt it will take long for the machine to ship in volume. I have no idea how it performs, the two demos of the machine I've seen (SC2000 and earlier this year at an IA64 conference) were little more than "look, KDE!... look, GNOME!". Interesting none the less.
They are the same box, built by HP. In fact, they've both been around since late 2000. If you look at photos of early Itanium clusters or even looked at the various Itanium demos at SC2000 you would notice that they all have the same case are were badged either HP or SGI. The only machines SGI builds itself are the O2/Octane/Origin/Onyx MIPS/IRIX machines. Mostly built in Chippewa Falls, WI (home of Cray) with some assembly done overseas. The MIPS R12K/R14K CPUs are fabbed by NEC and the PCBs are made by Celestica. That's just MIPS/IRIX. All of SGI's Intel-based machines (both IA-32 Pentium and IA-64 Itanium) are OEM'ed. VA Linux builds some of SGI's rackmount servers, and I'm not sure who builds their PC workstations. HP builds the 750 Itanium workstation.
If you haven't noticed, SGI's goal is to become the next VA Linux, Penguin Computing, or Dell. And they're not even doing a good job with that!
*sigh*
No kidding. And before MIPS R10K there was the beast that was the R8K *chipset*. To date I still don't think there is any CPU that was faster in fp per clock cycle than the R8K. SGI's been doing 64bit since the early 1990s.
64-bit alone is nothing new, but I guess SGI needs all the buzz they can get. They've all but left their own MIPS/IRIX market and have entered the competitive and very non-SGI-like OEM world.
It's sort of like a corporate version of Frogger.
Contrary to popular belief they haven't ditched Irix. They plan to keep going with it, but to use Linux to increase their market share. I doubt it'll work. Linux users are likely to buy a cheaper PC anyway. They need to concentrate on making Irix actually work. I've administered Irix systems and I know just how miserable it is! I strongly disagree with the "stable" statement that someone else brought up. Stable relative to Windoze maybe, but not when compared to other unix based OSes.
Security - laughable. SGI's notion of security is to make all sysadmin tools graphical, make then setuid root, and then ask for a password. No concept of keeping high-secure details to a nice small compact "su" program. Result - virtually EVERY sgi admin tool has been hacked, often by many means. SGI also used to ship systems with "+ +" in hosts.equiv.
Ease of use - again laughable. It's getting better slowly, but for a long time you couldn't admin an SGI (except by knowing what goes on underneath) remotely unless you were also sat at another SGI machine. Their desktop is hideous too.
Ease of installation is hideous too. There's umpteen dependencies to (manually) resolve for doing the most trivial of things. Nothing seems to come by default (including NFS), and example which compiler do I want - is it the "Ansi C compiler", the "C compiler (ANSI)" or the "C compiler". (Ok so that's paraphrased, but you get the picture.)
Compatibility - ugly. We tried connecting several SCSI CDrom drives to our sgi and all failed. We couldn't load the installation CDs remotely from another system as they use an SGI specific format (non ISO-9660). They also refused to provide CDE as an optional desktop. OK so CDE is hideous, but it's almost as if they _want_ to be out on a limb!
Maintainability - improving slowly. In the past we've had hideous problems with supporting software on multiple OS releases. They're not even concecutive with Irix 6.3 and 6.4 both being splits from 6.2, and only merged back in again at 6.5.
Support - patchy. Sometimes it's good, but other times it is downright hideous. We found a large bug in their Fortran compiler. We provided them with a 10 line source example, but they refused to fix the compiler (or even acknowledge the bug). One year later (give or take) I mention this to a large pharma, who use many many SGIs and wanted our software to run (which it didn't acknowledge the bug). One year later (give or take) I mention this to a large pharma, who use many many SGIs and wanted our software to run (which it didn't - due to the bug). The very next day SGI release a patch. Right - so I don't count because there's only one of me, despite paying for support?
Ahh, I feel better for that whinge!
Anyway, as far as I'm concerned the sooner SGI curl up and die the better. It'll certainly make my life easier!