Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
×
Technology (Apple) Businesses Apple Technology

Own a Piece of An Apple-Based Supercomputer 296

Graff writes "Now that Apple has come out with the Xserve G5, Virginia Tech has been swapping out parts of their 'System X' supercomputer for the more compact 1U Xserves. MacMall is selling some of those System X component G5 systems with an approximate $200 savings and an extra 512 megs of RAM over a normal G5. You can read more about it at MacCentral."
This discussion has been archived. No new comments can be posted.

Own a Piece of An Apple-Based Supercomputer

Comments Filter:
  • first dibs (Score:3, Funny)

    by pytheron ( 443963 ) on Thursday February 12, 2004 @07:00AM (#8256832) Homepage
    I bag the 'go-faster' stripes on the case !
  • Proof? (Score:5, Funny)

    by OlivierB ( 709839 ) on Thursday February 12, 2004 @07:04AM (#8256843)
    I wish there was some kind of engraving on the aluminium casing stating something like "Virginia Tech, Supercomputer node #758 - 2003" Then they could definitively sell it at a Premium. I mean I can get this kind of computer off ebay for more or less the smae price. I need some kind of souvenir that it's from Virginia. How about sending it through the IPOD engraving shop?
  • by Bones3D_mac ( 324952 ) on Thursday February 12, 2004 @07:07AM (#8256848)
    Only 6 months of use out of these things and VT is tossing them out like yesterday's trash. Gee, thanks for doing this after delaying my order for 6 weeks back when the G5s were originally supposed to be shipping to the rest of us. Apparently you didn't need them that badly after all.
    • by Emil Brink ( 69213 ) on Thursday February 12, 2004 @07:15AM (#8256874) Homepage
      Hardware that has seen use for six months in a super-computer, i.e. probably been run 24/7 and really stressed, sold for $200 below the price of new is considered to be priced as "trash"? Your trash must be worth its weight in gold, then. I think it sounds expensive, but then it's Apple hardware so I shouldn't be surprised. ;^)
      • by Bones3D_mac ( 324952 ) on Thursday February 12, 2004 @07:24AM (#8256911)
        VT isn't the one selling these systems... Apple is. VT is tossing them back at Apple for shiny new Xserves. Apparently being the 3rd fastest computer in the world isn't good enough anymore.
        • by assemblyline ( 664755 ) on Thursday February 12, 2004 @08:39AM (#8257228)
          Virginia Tech wanted Xserves in the first place. Apple didn't reveal them until January. Look at the benefits. Smaller case, less heat generated, less power consumed, error corecting code memory; all things which would be extemely useful in a supercomputer like this. From what I have read, the upgrade will use 25% less power and take up a third less space. If I were Tech, I would throw the current G5s back too.
          • You forgot one (Score:5, Interesting)

            by BoomerSooner ( 308737 ) on Thursday February 12, 2004 @09:27AM (#8257579) Homepage Journal
            They used to run all simulations twice to verify the non-ECC RAM was returning the desired result. As a consequence the system will speed up two-fold in real life use. Now that is a performance gain!
            • This may be juuuuuust a bit off-topic, but...

              With the inclusion of ECC in the new XServes, and Apple's slow-but-steady propogation of high-end features towards the lower end, how likely is it that we'll see ECC in some future rev (maybe even this alleged-real-soon-now bump) of the desktop G5s?

              It's been many years since my computer architecture coursework, so I am not sure that there's even a real cost-benefit reason to do so. I look forward to reading any brilliant insights that /.'ers are capable of bri
              • by Hoser McMoose ( 202552 ) on Thursday February 12, 2004 @12:03PM (#8259207)
                Well, from what I can see there is barely any difference between the memory controllers on the two systems. It looks like it was just a new revision of the same ASIC. Apple doesn't exactly provide many details on this, but it looks like the new memory/processor controller chip would be a drop-in replacement for the chip used on the original Powermac. Therefore it's possible (even likely) that they will use this new revision on the next revamp of the G5 line. In fact, they could well start slipping them into the current line-up without telling anyone about it.

                I don't anticipate that Apple will sell any desktop G5's with ECC memory installed at the factory, but if the memory controller supports ECC you could easily replace the factory memory with third-party ECC memory.
          • by Tassach ( 137772 ) on Thursday February 12, 2004 @09:46AM (#8257751)
            You are 100% correct. In a big server farm, space, heat, and power consumption are major concerns. Assuming your figures are correct and the replacement hardware has similar specs to what they are replacing, they can improve the overall performance of the system by at least 25% at the same power consumption, not counting the additional power savings that would see from the lower heat load. Less heat also translated directly into longer life.

            I'll admit that a 6-month replacement cycle is pretty short, but it actually makes sense because they're avoiding the worst of the depreciation. I'm not up on used Mac prices, but x86 server hardware depreciates around 50% per year (refurbished 2 year old x86 servers routinely sell for around 20% - 30% of their original price; refurbished 3 year old gear sells for well under 10% of it's original price. You can get a maxed out Quad processor P-III server for well under $5000 which cost $50K when new.

            That said, I don't think that this is a good deal. $200 savings on a $3000 box is only a 6.7% discount for 6 month old hardware; a 20% - 25% discount would be more in line with current market.

            • I think Mac hardware depreciates more slowly than PC stuff; there's not quite the same desperate impetus to have the very latest hardware, probably because people tend to buy Macs to do work rather than play games.

              But yeah, they could have cut a better deal.
            • Depreciation (Score:3, Interesting)

              by Paladeen ( 8688 )
              In my experience the price of Macs depreciates far less with time than your standard x86 boxen.

              First of all, buying a new Mac is generally expensive.

              Secondly, Apple's computers are generally made with solid, high-quality components and last a long time.

              I just sold a single-processor G4/450Mhz Sawtooth for $400 the other day: that's a 4 year old machine that cost about $2000 new, yet can still be sold at %20 of original price.

      • I'm going to have to disagree with you concerning the amount of wear and tear.

        Most computers fail either in the first month or so of use or after many years of good use. In the first case it's usually a bad component that slipped by quality control. In the latter it is simply the ravages of time. Longer quality control "burn-in" times would eliminate many of those first month failures, but the vendor really doesn't have the time/space for long burn-ins.

        Now, the Number One way to shorten the life of your computer is to turn it on and off frequently. The computer heats up when you run it and cools when it's off. The expansion and contraction of components associated with these temperature changes stresses every solder joint on every component -- and may even stress the chip-level components themselves. To lengthen the life of your hardware (at the cost of extra electricity), leave your system on unless you aren't going to be using it for a significant length of time (i.e.: don't power cycle more than once a day).

        These G5's have been on for approximately six months straight in a very well-controlled temperature environment. This is a burn-in that virtually guarantees that there were no manufacturing defects. However, since they weren't power-cycling on a regular basis, it was actually a VERY low-stress environment.
    • Apparently you didn't need them that badly after all.

      They did need them that badly or it wouldn't have qualified in time to make the list.
    • by mbbac ( 568880 ) on Thursday February 12, 2004 @08:35AM (#8257200)
      They did need them badly. Without having them so soon there wouldn't currently be a Virginia Tech supercomputer on the TOP500 list and they'd have to wait another year to try to get listed.
    • by Rasta Prefect ( 250915 ) on Thursday February 12, 2004 @09:49AM (#8257783)
      Only 6 months of use out of these things and VT is tossing them out like yesterday's trash. Gee, thanks for doing this after delaying my order for 6 weeks back when the G5s were originally supposed to be shipping to the rest of us. Apparently you didn't need them that badly after all.

      I'm fairly sure Virginia Tech wanted the 1u cases all along (makes more sense). However, they needed the cluster up in time to make the Top 100 list. Being on that list brings in _lots_ of research money. So yes, they did need them.

    • Gee, thanks for doing this after delaying my order for 6 weeks back when the G5s were originally supposed to be shipping to the rest of us.

      Six weeks? VT neeeded 1100 machines. Apple shipped 220 000 G5s the first quarter. 0.5% of all machines went to VT. That ammounts to appoximately half a day of delivery delays.
      • Apple redirected G5s that were originially scheduled to fulfull pre-orders to VT, resulting in (at least) 1100 people, who'd placed preorders and been promised a ship date, being out of a G5 and having to wait till a second ship (which may very well have been 6 weeks, I dunno).

        It grates on people being told that they're less important than a PR move.

    • They wanted to place highly in the top 500. The top 500 runs in "sweeps," meaning they have to be up and running on the DATE when the results are calculated. I don't know how often the sweeps are run -- ever 6 months or year or so.

      So they most certainly WERE in a hurry. Now they can swap them out for more space-efficient Xserve G5's (and maybe gain some more speed with the extra space).
  • PCI-X (Score:3, Interesting)

    by freerecords ( 750663 ) <slashdot@NOsPAm.freerecords.org> on Thursday February 12, 2004 @07:10AM (#8256859) Homepage Journal
    It is nice to see the inclusion of PCI-X, we can hope that this is the start of the end of "old" PCI. I was a bit confused by the decision to include Firewire in this machine. I know it is an apple kind of penchant, but surely a server won't need firewire. Who wants to use a firewire hard disk with a server? You're more likely to back up onto tape. It seems akin to a High End commodity intel server having an Audigy sound card with optical out, I don't think there is much point. I think some of the features could have been thought about more on the machine rather than lamely following the tradition of previous iMACs. However, it looks like a great machine, and Mac is coming up in mine, and many other x86 users (I believe) opinions.
    • Re:PCI-X (Score:5, Interesting)

      by TheRaven64 ( 641858 ) on Thursday February 12, 2004 @07:18AM (#8256887) Journal
      Who wants to use a firewire hard disk with a server?

      I believe that the Apple recommended restore procedure for an XServe involves booking from a copy of the OS installed on your iPod (which connects via FireWire).

      You're more likely to back up onto tape.

      There's no reason why you can't plug the tape drive in over FireWire. FireWire is basically a serial variant SCSI (okay, I'm oversimplifying a bit here) and with speeds of up to 800Mb/s it's fast enough for most things. You probably wouldn't want to connect your RAID array via FireWire, but for backups it's plenty fast enough. Many tape drives only let you write at Oh, and by the way the G5 units they are selling are intended as workstations not as servers (hence the digital audio out and the Radeon 9600 Pro, neither of which is really required for a server).

    • Re:PCI-X (Score:5, Interesting)

      by binaryDigit ( 557647 ) on Thursday February 12, 2004 @07:25AM (#8256915)
      I was a bit confused by the decision to include Firewire in this machine. I know it is an apple kind of penchant, but surely a server won't need firewire.

      Actually there are lots of reasons to include firewire on a server.

      - You can hang a firewire mass storage device off of it to backup (tape, disk, etc), boot from (recovery, etc), add extra storage in a pinch, etc.

      - You can create various types of clusters using firewire. One product is the sancube.

      - It's cheaper to design in a feature that may not be used in one incarnation of a product, but may be usable in others. Case in point your comment about Audigy sound cards on high end Intel servers, those very same motherboards are probably used in both servers and high end workstations, no point in having two different motherboards just to save a few pennies off of a $500+ mobo.
    • Re:PCI-X (Score:4, Informative)

      by tr0llb4rt0 ( 742153 ) on Thursday February 12, 2004 @07:48AM (#8257001) Homepage
      You can do some good high speed networking using firewire.

      It's available in Mac OS and Linux.

      http://www.homenethelp.com/network/firewire.asp

      400mbps isn't to be sneezed at. With repeaters it'd probably make a decent fail-over network in case the main gigabit link failed.
    • Re:PCI-X (Score:3, Informative)

      Don't confuse PCI-X with PCI Express. PCI-X is PCI, clocked at 100/133 MHz. PCI Express is the former 3GIO technology
    • OS X supports TCP/IP over firewire. Firewire has significantly lower latency than ethernet, and it's a shared bus.

      So Apple's biotech clusters use FW800 as a large, shared bus for distributing work packets. It's like a "free" high speed low latency third ethernet port... great for shared high-speed communications.
  • My question is: (Score:3, Interesting)

    by SB5 ( 165464 ) <freebirdpat@nOspAm.hotmail.com> on Thursday February 12, 2004 @07:13AM (#8256865)
    Did Virginia Tech's System X have any impact on Apple release the Xserve G5?

    Did the Xserve get any benefit from the optimization of the Big Mac?

    Is Virginia Tech going to lose money on this deal? /still pissed at Dell for not offering Athlon's, I wanted a 64 bit processor and AMD and Apple were the only companies offering them three months ago
    • Re:My question is: (Score:5, Informative)

      by Selecter ( 677480 ) on Thursday February 12, 2004 @08:17AM (#8257112)
      They looked at Opterons and they looked at Dell( Xeons.) THEY WERE REJECTED based on cost and performance issues ( the G5 can perform a fused multiply + add in one clock cycle, multiply that times billions of iterations ) and thats something the Opteron cannot do.

      The G5 was the clear winner out of all the chips on the market, and Apple was the clear winner of the platforms considered, and they considered *ALL* of them worth considering.

      The success of the venture simply proves the superiority of keeping an open mind and not bringing tired old pre-conceptions (Apple's slow, Apple sux, etc.) to your work.

    • IBM offers e325 Opteron servers at least....
  • by henryhbk ( 645948 ) on Thursday February 12, 2004 @07:13AM (#8256866) Homepage
    So they got them at least at educational if not below educational (must be extra discounting for thousand+ machines). They then use them for 6 months, tax free (educational institution) and then sell them only $200 off list? The apple store for education lists the G5 DP 2.0 GHz with 512mb and 160gb drive at $2699. Hmmm... Doesn't seem like it's such a deal for people, and seems like a virtual profit for them!

    As someone else noted, if they were engraved or etched or something that would make them special.

    • by blorg ( 726186 )
      Although, I agree that a bit of engraving would go some way towards supporting their value. Is there anything at all, beyond that 1 sentence on the website, for a purchaser to establish that they really do have one of the Virginia Tech machines?
    • No, Virginia Tech paid FULL PRICE for each and every one of the G5s. That was part of the deal of getting them first. Apple wasn't about to tell other people they wouldn't be getting their computers for a bit and then also take a financial hit for selling them cheaper than others were willing to pay.

    • The apple store for education lists the G5 DP 2.0 GHz with 512mb and 160gb drive at $2699.

      These come with 1 gig of RAM, so compared to the educational price it's just about a wash. The difference is that these systems are being sold to the general public, who would normally have to pay $2995 for these machines. That's a savings of around $200 with a bonus of 512 megs more RAM.
  • by Coutal ( 98822 ) on Thursday February 12, 2004 @07:15AM (#8256872)
    Why couldn't VT hold their horses?
    my bet is... they could.
    no one likes building any cluster (not to mention a supercomputer) out of desktops, esp. ones configured like desktops (gfx, no ecc, ...)
    but apple really wanted the PR of having the computer cluster, and perhaps to list the revenue in 4Q2003.
    so i can't blame them - looks like a fair deal.
    • by LennyDotCom ( 26658 ) <Lenny@lenny.com> on Thursday February 12, 2004 @07:21AM (#8256895) Homepage Journal
      apple really wanted the PR of having the computer cluster

      No VT needed the PR probably more then Apple now they get grant money out the wazoo
      • by zerocool^ ( 112121 ) on Thursday February 12, 2004 @09:06AM (#8257417) Homepage Journal
        No VT needed the PR probably more then Apple now they get grant money out the wazoo


        Please don't begrudge us this. Virginia's state legislature has cut over 28% from our 2002 level of funding, while just recently passing laws which effectively cap tuition hikes at about 5% per year. My tuition has gone from $1500/semester (2001 in state) to almost $2200/semester (2004 in state).

        And please don't respond with "blah blah, if they used the money more effectively". We're up against the wall here. About 5 professors in my department (History) out of 25 or so have been laid off, or sent on research sabbatical so that they don't have to be paid. We've fired over 1/2 of the maintenance staff, and people on campus no longer have trash cans in their dorm hallways - they have to take their trash outside to a dumpster. The snow trucks in Blacksburg have far less salt than they had last year to clear the roads (I only think of this as I sit here at Netmar and watch today's 3 inches of snow fall). I now this isn't grave hardship, but seriously, we've cut about everything we can.

        The supercompuer gives us both grants and positive PR. Students see that, despite the state of the economy, we're trying to push to the top of research institutes. We're trying to push ourselves above 67th (or whatever) on that college engineering school ratings, trying to compete with our neighbor down interstate 64, who, for no discernable reason, has an engineering program with the inflated ranking of ~ 15th. And yes, we get grants from the government and money from private industry in exchange for timesharing on the bigmac.

        Just let this one go. We need the money, the BigMac has not only made us money, but has raised awareness of the university. It's a good thing.

        ~Will
    • by despik ( 691728 ) on Thursday February 12, 2004 @07:37AM (#8256950) Homepage
      but apple really wanted the PR of having the computer cluster, and perhaps to list the revenue in 4Q2003. so i can't blame them - looks like a fair deal.

      You fool. Apple wanted the PR, so they forced the G5s down VT's collective throat. Yeah, right.

      Why couldn't VT hold their horses?

      Because they had a deadline to meet if they wanted to make that Top CPUs list.

    • Top 500 list (Score:5, Interesting)

      by Troy Baer ( 1395 ) on Thursday February 12, 2004 @09:09AM (#8257436) Homepage
      Why couldn't VT hold their horses?

      My guess is that both they and Apple wanted to have a spot on the last Top 500 list [top500.org], with all the associated press at the Supercomputing 2003 [sc2003.org] conference. Apple's been trying to convince somebody, anybody to build a large HPC cluster with their hardware since the G3 came out. Until the G5 came out, it made very little sense economically -- the per-system price for Apple kit was 30-40% more than comparable Intel-based stuff, and the memory bandwidth and 64-bit floating point performance was the same or worse. The G5 fixed that, for the most part

      Nobody in their right mind wants to build a cluster out of machines in desktop/deskside chasses. We've done it once, with the first generation Itanium systems where there was no rackmount option for a 2-way box, and we'll never do it again -- remote management of those machines was and is actively painful. (Our 1st-gen Itanium cluster is out of production service now, but it's been partitioned up into smaller clusters at universities around the state as part of the Cluster Ohio project [clusterohio.org], which we still manage.)

      --Troy
  • 'Never buy the first version of anything' - even if it is $200 less than list price, has been well looked after, comes with an extra 512Mb and used to be part of a supercomputer. Rev2 or 3 is always a better purchase.
  • Wear issue? (Score:5, Interesting)

    by weave ( 48069 ) on Thursday February 12, 2004 @07:22AM (#8256898) Journal
    What about the wear issue? I assume those processors were cranking around 100% for good portions of the time, generating a lot of heat. The room had some pretty intense cooling, but individual computers probably still heated up a lot.

    Should that be a concern? Do these 6 month old computers already have 2-3 years of typical mileage on some of their components?

    • Re:Wear issue? (Score:5, Informative)

      by dario_moreno ( 263767 ) on Thursday February 12, 2004 @07:40AM (#8256961) Journal
      on the contrary. My 4 years experience with clusters show that after the first two months of burn-in where many components fail, you aftewards have a higher MTBF than with PCs used "normall", because in the Beowulf case the AC power is regulated, the machine is almost never switched on and off (major cause of damage because at startup every component consumes power at the same time, voltage drops, and damage occurs), temperature is kept constant, the machine is kept in a safe room where nobody ventures more often than once a week because of the cold and the noise, therefore there is no dust in the machines or grease on the contacts.
      • Re:Wear issue? (Score:3, Informative)

        by Graff ( 532189 )

        My 4 years experience with clusters show that after the first two months of burn-in where many components fail, you aftewards have a higher MTBF than with PCs used "normall"

        Lol, you're right. Think of these as "extended pre-tested" machines! Virtually guaranteed to have a lower rate of failure because they've been burnt-in already and the chances of a manufacturing defect affecting operation is lower!

        Kidding aside, these machines are gone through Apple's refurbishing program. I've bought about 20 ref

    • Not to mention that PowerPC chips "load" non-linearly compared to other architectures -- that is, they become far less efficient at, say the top 8-10% of CPU usage time, both electrically and logically. If true, this could definitely shorten their lifespan if it causes excessive heat stress.

      Unfortunately, I don't have anything to back that up. Occasionally Google is not so friendly.
    • Re:Wear issue? (Score:3, Interesting)

      There is a large number of cases in the engineering world where running something continously flat out is far better than starting and stopping. Cases that come to mind are gas turbines (gas turbines for power generation have a lifetime measured in 100s of starts, the number 500 springs to mind). There is also a class of heat exchangers (printed circuit heat exchangers, transfers approx 5 to 15 MW of heat in a block of aluminium the size of a typical car engine) which are also very sensitive to thermal cycl
  • by Peter Cooper ( 660482 ) on Thursday February 12, 2004 @07:23AM (#8256904) Homepage Journal
    This is an educational and research establishment, not a commercial enterprise.

    You'd have thought (as some students were hinting here at /.) that Virginia Tech would have sold the units to students, freshmen, whatever, at a knock down rate. Or even used a ton of them within the university itself.

    Yet more profiteering from a supposedly educational institution.
    • I think you need to look up the word profit. These are sold at less than current retail price and you can bet both MacMall and Apple (if they did the refurbishing) are getting their piece of the cake so VT will probably only regain a part of the initial cost of the system, and they are probably spending that money, plus a little extra on the new system. Which in turn will benefit VT as an research establishment (probably not very benefitial for most _students_ though.) I'm guessing they wouldn't have been a
    • by Raven42rac ( 448205 ) on Thursday February 12, 2004 @08:14AM (#8257096)
      First of all, how is this profiteering? They are trading in their G5s to upgrade their cluster, Virginia Tech is not selling the "old" ones, MACMALL IS! Virginia Tech is simply trading them in. So you would rather have Virginia Tech eat all the money that they spent to purchase the original lot of 1,100 instead of making them look much better to potential customers who want to purchase the use of their cluster, by leveraging the money they have already spent? It is in business to make a profit, like it or not, it is not their primary main objective (Chinpokomon!) but it can not be ignored, either. I respect your opinion that some of the G5s should have been kept around for use in labs, by students, etc. Then again, we don't know if VT traded ALL of their G5s, they just might have kept some for the uses that you and I laid out. I suppose this just shows, on a grand scale, the high resale value of Apples!
  • by Anonymous Coward on Thursday February 12, 2004 @08:07AM (#8257070)
    oo..damn.. it was!
  • by mactari ( 220786 ) <rufwork AT gmail DOT com> on Thursday February 12, 2004 @08:26AM (#8257143) Homepage
    Apple's online store is charging $2399 for refurbed dual G5s, and the student store's price for a new dual G5 is $2699, $100 less than the MacMall refurbs from Tech. You can even take $26 more off for getting rid of the internal mode, which the supercomputer refurbs don't have either.

    Even if you add the extra 512 megs of RAM from Apple's site (where prices aren't the best), these Va Tech refurbs are only $100 less than what a student would spend on the same box new. Not to mention these 2 GHz duallies are rated as "Buy only if you need it - Approaching the end of a cycle" on the Macrumors buyers' guide page [macrumors.com].

    So not a deal at all if you're a student (though I have to think students at Va Tech could get the inside track on the boxes -- anyone know?) and not a great price for a refurb if you're Joe Schmoe. And not a box with great longevity, relatively speaking, either, if Macrumors has the lifecycle pegged.

    Wait for a processor speed bump unless you're dying to own a little bit of celebrity.
    • And not a box with great longevity, relatively speaking, either, if Macrumors has the lifecycle pegged.

      It's not like the machines are going to stop working or anything. It's just that the rumor mill has Apple about to roll out speed-bumped G5's.

      I say this is a sweet time to pick up a dual 2 Ghz G5. Given the speed increases the rumor sites have been talking about (like 200-400 Mhz more) the new systems are not going to be that much faster than the current ones so the lower price is a win for someone lo

    • Interesting page. I'd say that your guess is probably right. I think Jobs did promise 3GHz G5s sometime mid to late 2004. For all we know, Big Blue is stockpiling some 2.5GHz rated chips right now.
  • by bjb ( 3050 ) * on Thursday February 12, 2004 @08:27AM (#8257150) Homepage Journal
    Looking at the specs of those machines, it seems that there is a Radeon 9600 in every G5. Now I know that OS X takes advantage of 3D hardware, but as a server, this is almost a wasted expense, especially considering the number of servers that they bought.

    What would be spiffy if there was a way that they could do SOME of the math on the GPUs. I never saw a product that could do that, but it would be rather fast. No?

    • Ok, everyone keeps calling these servers and wondering why they've got firewire and a nice video card. Apple sells XServe's if you want a pure server. Typically, these machines would be used by some media professional (layout, design, audio, movies, animation) for which these things make complete sense. These aren't XServe's, these are PowerMacs and as such should be loaded to the gill.

      VT didn't buy XServe's to start because there was no G5 version. Now that there is, they are, which over the long run
    • There actually IS a way to do math on GPUs, take a look at what these people are doing [gpgpu.org]. I don't know if there is any software yet that will run on Macs and OS X, I think most of it is targeting PCs running Linux, but at least in theory you can do some some pretty high performance math on GPUs.

      Of course, there are some downsides to this. First off, it only works on the latest and greatest generation of GPUs that are programable (the Radeon 9600 should qualify here). Second, GPUs only support single-prec

  • by OnanTheBarbarian ( 245959 ) on Thursday February 12, 2004 @08:45AM (#8257282)
    Hey, that's cool. Where else could you get G5s with ECC memory so cheaply?

    They do have ECC memory, right? Having been part of a supercomputer....

  • by johnpaul191 ( 240105 ) on Thursday February 12, 2004 @09:31AM (#8257619) Homepage
    There is a lot in these machines that a clustered supercomputer setup REALLY doesn't need. One article i read about this said the VT designer wanted to buy the chips right from IBM initially. It came down to the PowerMac G5 being the ONLY way to get those chips at the time. I guess when he made his pitch to Apple they either would not say when they expected to ship Xserves, or they were worried about looming supercomputers. i also read elsewhere that in the next year or so there are a few other massive machines that will be coming online and it's possible they would fill up the top 5. it came down to timing where a $7 Million setup could land in the top 5 machines up against machines costing 20 times as much.

    anyway if you look at the specs you can see all the silly stuff.... that cluster does not need 1100 Superdrives, or 1100 Radeon 9600 cards..... let alone size and whatnot... i'm sure it was done because the Xserves were just too far off and it was the only machine out there with the G5/970 chip for sale to anyone.

    look at the specs:


    The systems sold by MacMall are listed as 2.0GHz Power Mac G5s equipped with 1GB DDR SDRAM (2 512MB memory cards); equipped with 160GB ATA drives, a SuperDrive, ATI Radeon 9600 Pro graphics processor, Gigabit Ethernet, 3 USB 2.0 ports, 2 USB 1.1 ports, 2 FireWire 400 ports and 1 FireWire 800 port, along with an AirPort Extreme card slot and no modem -- in other words, a stock Power Mac G5 Dual 2GHz system with a memory upgrade from 512MB to 1GB


    it does seem the pulled the fibre cards out... they are optional in Xserves... maybe they just swapped those? i don't know if they are the same in both machines normally.

    • Umm.... the G5's that were being built for normal use had what VT needed. To order specially built G5's would have pushed back delivery while either special ones were built or the supposedly superfluous parts were removed from G5's rolling off the normal assembly line; either option would have also increased costs and reduce eventual value.

      Even if the new XServes weren't ready for another year, it's obvious that eventually these computers would be broken up and replaced. If they are full-functioning G
  • I'll be jumping to buy one. :P

    (proud Mac owner already)

    GJC
  • by Photo_Designer ( 473497 ) on Thursday February 12, 2004 @01:21PM (#8259960) Homepage Journal
    Just called, no need to call.. they're all gone.. shucks.

    -Jim

To be awake is to be alive. -- Henry David Thoreau, in "Walden"

Working...