Slashdot Mirror


Rent A Bit Of Weta Digital

An anonymous reader writes linking to this story at stuff.co.nz, excerpting: "Five hundred powerful computers used by Weta Digital to help create the special effects for the Lord of the Rings may be put up for hire.... The pizza-box sized IBM blade servers each incorporate dual 2.8 gigahertz Intel Xeon processors and 6 [gigabytes?] of memory." Update: 03/22 07:08 GMT by S : The linked story says 6 megabytes of memory, we don't believe 'em.

210 comments

  1. 6MB? by Biogenesis · · Score: 2, Interesting

    Shoulden't that read 6GB?

    1. Re:6MB? by Biogenesis · · Score: 0, Troll

      Heh, didn't think that'd go unchecked for long...

    2. Re:6MB? by Anonymous Coward · · Score: 0

      I don't think so. A 32 bit pointer can only address 4 GB, 2^32.

    3. Re:6MB? by tankdilla · · Score: 1

      How much RAM can they put in those Xeon boards? I'm assuming they figured 6 GB per board would be sufficient, but how much RAM would be the max for the board?

      --

      -Look lively. LOOK LIVELY!!! --Mr. Shmallow

    4. Re:6MB? by Anonymous Coward · · Score: 0

      Look up the acronym "PAE".

    5. Re:6MB? by Anonymous Coward · · Score: 0

      1.75921860444E13 Mega Bytes would be the amount it could physically address using 64bit addressing.

    6. Re:6MB? by Anonymous Coward · · Score: 0

      Maybe it's referring to the processor cache, which might as well be 6MB.

    7. Re:6MB? by 1SmartOne · · Score: 0

      An AS400 can run 12GB+ of RAM a Blade server can also run a max of 12GB.

  2. Imagine by Anonymous Coward · · Score: 5, Funny

    A beowulf .. oh wait ...

    1. Re:Imagine by Anonymous Coward · · Score: 1, Funny

      Well I never metabeowulf I didn't like.

    2. Re:Imagine by walter_kovacs · · Score: 1

      Imagine all the porn you could download with that!

  3. huh? by FS1 · · Score: 0, Redundant

    The pizza-box sized IBM blade servers each incorporate dual 2.8 gigahertz Intel Xeon processors and 6 megabytes of memory."

    umm check your stats there

    --
    A Fatal OE Exception has occurred, Sig will now reboot.
  4. Lamenting the fall of pizzabox desktops by baryon351 · · Score: 1, Offtopic

    Mildly off topic, but I seriously miss good pizzabox desktop boxes. Something simple, plain, fast, and with room for a couple of PCI slots on a riser card.

    The world needs more of them

    1. Re:Lamenting the fall of pizzabox desktops by Anonymous Coward · · Score: 0

      Oh how I loved my old Performa 6115. Damn nice pizza box. Only 1 Nubus slot though. :(

    2. Re:Lamenting the fall of pizzabox desktops by baryon351 · · Score: 1

      Curiously that's one of the machines I was thinking of when I posted, along with sun's lovely ones.

    3. Re:Lamenting the fall of pizzabox desktops by sTalking_Goat · · Score: 1

      I don't miss em at all. Ever try to overclock a Radeon 9600Pro? Where would I fit this thing

      --

      My days of not taking you seriously are certainly coming to a middle...

    4. Re:Lamenting the fall of pizzabox desktops by Anonymous Coward · · Score: 0

      When I think pizza box, I think of things like the sun sparcstation one for example... couple of sbus slots, and actually the same form factor as a pizzabox.

      What you describe is perhaps the NTX... something that went out of fasion when the slot 1s came into being, but slightly more practical now that we no longer do big arse cartrages. They are perfectly fine if all you need are two PCI slots and don't mind doing without agp.

    5. Re:Lamenting the fall of pizzabox desktops by Jexx+Dragon · · Score: 3, Funny

      Buy a good 1U rack. Sit it on your desk. Instant "Pizzabox" desktop.

      --
      I don't have time to comment my code, the program is late already.
    6. Re:Lamenting the fall of pizzabox desktops by cft_128 · · Score: 1
      Buy a good 1U rack. Sit it on your desk. Instant "Pizzabox" desktop.

      And about as loud as a huey starting up.

      --

      Underloved Movies and Pub Quiz: donotquestionme.org

  5. Cost? by nb+caffeine · · Score: 5, Funny

    What would this cost? Do they charge something like cpu/hours or the like? Will the average person have the ability to rent some clock cycles? I just want something that will be able to run doom3 when it comes out.

    --

    "Something's wrong with you...and I hope we never do meet again." - Deftones When Girls Telephone Boys
    1. Re:Cost? by Anonymous Coward · · Score: 0

      It will be incredible...a blazing-fast 2 seconds-per-frame running over VNC!

    2. Re:Cost? by nb+caffeine · · Score: 1

      Im sure it looked cool on the server though...

      --

      "Something's wrong with you...and I hope we never do meet again." - Deftones When Girls Telephone Boys
    3. Re:Cost? by Pottsynz · · Score: 1

      Meh, I live an hour and a half away from Wellington - I'll just rock on down there with a truck and ram-raid the place. Just have to avoid the cops and the odd cave troll.

    4. Re:Cost? by rrreese · · Score: 1

      The University Of Otago has a deal with Weta. It costs $1NZ per cpu hour.

  6. Pizza-delivery! by The_Ace666 · · Score: 5, Funny

    Now where can I find a pizza-delivery company to get one of these babies delivered to my door?

    1. Re:Pizza-delivery! by DigiShaman · · Score: 5, Funny

      Either way, they'll be hot! (pun intended)

      --
      Life is not for the lazy.
    2. Re:Pizza-delivery! by T-Kir · · Score: 2, Funny

      ...and if they don't deliver within a certain time, then hopefully you'll get it for free! :)

      --
      Are you local? There's nothing for you here!
    3. Re:Pizza-delivery! by idttau · · Score: 1

      i believe i speak for others as well when i say that i'd spend more money on a pizza in a box than something with 6MB memory...

      --
      well, i'm glad.
    4. Re:Pizza-delivery! by dthree · · Score: 1

      Will peter jackson come deliver a personal apology if the deliverator didn't get it to you in 30 minutes?

      --
      "I forgot my mantra."
    5. Re:Pizza-delivery! by Anonymous Coward · · Score: 0

      I love Snow Crash!!! But, then, who didn't?

    6. Re:Pizza-delivery! by Anonymous Coward · · Score: 0

      The mods, apparently. I thought that comment was hilarious.

  7. Wow by KU_Fletch · · Score: 4, Funny

    A whole 6 megabytes of memory?! Way to beat up my 486.

    --
    It's not stupid. It's advanced.
    1. Re:Wow by yletelpmoc · · Score: 1

      Or my IBM PCjr, with the fully upgraded 128K ram. And an off topic tangent, a beowulf jr. cluster. Any takers?

    2. Re:Wow by xkenny13 · · Score: 2, Funny

      A whole 6 megabytes of memory?!

      Yup!! It's amazing what you can accomplish once you get rid of all the bloatware.

    3. Re:Wow by Daleks · · Score: 0

      A whole 6 megabytes of memory?! Way to beat up my 486.

      Of course it supports 6 MB of memory. It didn't say exactly or at most 6 MB. Oh no... I've turned into that annoying person at work that corrects everyone's grammar.

    4. Re:Wow by Anonymous Coward · · Score: 0

      I've turned into that annoying person at work that corrects everyone's grammar.

      The boss? Or the one that corrects veryone's grammar and gets it right?

    5. Re:Wow by petecarlson · · Score: 1

      Ahh 6 megabytes... What I could do with that

      # cat meminfo
      total: used: free: shared: buffers: cached:
      Mem: 3076096 2887680 188416 0 221184 1466368
      Swap: 0 0 0
      MemTotal: 3004 kB
      MemFree: 184 kB

  8. Wow, talk about capacity. by oGMo · · Score: 0, Redundant

    Six whole megabytes? That's like, ten times 640K, and everyone knows that's all anyone needs!

    Did the article mean 6 gigabytes? Or a 6MB cache, or what?

    --

    Don't think of it as a flame---it's more like an argument that does 3d6 fire damage

    1. Re:Wow, talk about capacity. by Anonymous Coward · · Score: 0

      Read the title: "Rent A Bit Of Weta Digital" They're not renting whole bytes or megabytes. Hmm... I'd read the SLA before renting some CPU time...

      [memory not included]

  9. retirement.... by AngstAndGuitar · · Score: 1, Funny

    this reminds me of this.

    --
    Less look fast, more go fast.
  10. Update by hlopez · · Score: 5, Funny

    Update: 03/22 07:08 GMT by S
    -we don't believe 'YOU-

  11. Wow! by FS1 · · Score: 1

    Less than one minute after posting the story, and not proofreading it. There is an update correcting an obivious mistake. I'm surprised that you corrected it that quickly.

    --
    A Fatal OE Exception has occurred, Sig will now reboot.
    1. Re:Wow! by Roman_(ajvvs) · · Score: 1
      if you proofread the update, you'd realise they're referencing the article...

      But it goes to show how inherent assumptions and habit are made and what happens when they're broken. Noone assumes MB anymore...
      Remember the days when 600 MHz was blazing fast? now people might say "0.6 GHz" just to be able to express speed on the same order of magnitude..

      --
      click-clack, front and back. I'm not moving this car otherwise.
  12. I'd like to run ray tracing real time on this by SexyKellyOsbourne · · Score: 4, Interesting

    I'm rather tired of waiting for graphics to progress to the level they will be in in the year 2010 or so. I'd like to see these machines, which rendered Lord of the Rings, use their nearly unlimited processing power to let me play a game -- perhaps Half-Life or Quake 2 with a new rendering DLL -- to spit out 60fps of pure ray-traced bliss.

    Or just fire up InTrace with a scene of 1 billion polygons of a super-detailed scene of sunflowers, with multiple reflections and all the other goodies, and crank it to 1600x1200.

    I can dream, can't I? :)

    1. Re:I'd like to run ray tracing real time on this by Shinglor · · Score: 1

      The latency would be too high for a real-time action game.

    2. Re:I'd like to run ray tracing real time on this by troon · · Score: 5, Funny

      I'm rather tired of waiting for graphics to progress to the level they will be in in the year 2010 or so.

      Just give it six years or so, and you should see the improvements you are waiting for.

      --
      Ydco co ,df C erb-y go. a Ekrpat t.fxrapev
    3. Re:I'd like to run ray tracing real time on this by Viceice · · Score: 4, Funny

      you know, if you ONLY wanted so SEE something like that, you could go out doors and look for a field covered in sunflowers.

      --
      Sometimes I wish I was a plumber, then I'd know how to deal with other people's shit.
    4. Re:I'd like to run ray tracing real time on this by QuantumFTL · · Score: 5, Informative

      Check out http://www.worley.com/fprime.html

      My part-time employer (when I'm not working for NASA/JPL) Maas Digital just bought a copy of the software... it utilizes stochastic methods to allow flexible real-time raytrace rendering (with good motion blur!)

      It turns out that motion blur in 3D graphics is a very hard problem because it's essentially a high-dimensional integral, and it turns out the best method of doing generalized high-dimensional numerical integration is a stochastic algorithm (monte carlo method) so it's not surprising to me that it's a great way to do motion blurs.

      My favorite aspect of stochastic methods is their ability to be continuously refined (for instance, in a video game, the longer you spent looking at an object, the better it would get etc, and the graphics performance would degrade very smoothly with changes in system load etc). It is also ideal for parallel processing, as it can be dynamically parallelized to completely heterogeneous computing nodes.

      Dan and I agree that there's going to be a lot of stochastic algorithms in the future of computer graphics (though he is hopeful that analytical methods will eventually make a comeback, as they have better asymptotic performance).

      Cheers,
      Justin Wick

    5. Re:I'd like to run ray tracing real time on this by Dogtanian · · Score: 1

      you know, if you ONLY wanted so SEE something like that, you could go out doors and look for a field covered in sunflowers.

      I liked the mod for this one; Score:4, Informative.

      Insightful might have been fine, but "informative" suggests that the moderator has been sitting at their computer for too long and forgotten about the real world.

      BTW, if you want an exciting game, you can get a gun (*) and *shoot* the sunflowers.

      (*) This offer void where prohibited by law.

      --
      "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
    6. Re:I'd like to run ray tracing real time on this by chendo · · Score: 1, Funny

      I find it absolutely hillarious that the parent post was modded "Informative". Well, unless the moderator didn't know that you can simply go outside and look at a field covered in sunflowers...

      --
      Founder of Mirror Moon - Tsukihime Game Trans
    7. Re:I'd like to run ray tracing real time on this by iwein · · Score: 2, Funny

      I tried your suggestion and to be honest, compared to the way graphics will look in 2010 or so it looked like shit... i mean there was even _fog_ there...

      maybe you have some tips to tweak it to a more acceptable level?

      --
      Show a man some news, distract him for an hour. Show a man some mod points, distract him for the rest of his life.
    8. Re:I'd like to run ray tracing real time on this by NotAnotherReboot · · Score: 1

      yes, but what happens when I ONLY want to SEE your gibs covering those sunflowers?

    9. Re:I'd like to run ray tracing real time on this by ckaminski · · Score: 1

      Paintballs. Neon Pink Hellfire paintballs. Preferably on your neighbors dogs who've been chewing up your rabbits. Or on your neighbors. I'm not picky. :-)

    10. Re:I'd like to run ray tracing real time on this by ckaminski · · Score: 1

      Explain that in ingrish for us poor schleps who didn't get that the first time around?

    11. Re:I'd like to run ray tracing real time on this by Anonymous Coward · · Score: 0

      Yes, they're called *glasses*... ;)

    12. Re:I'd like to run ray tracing real time on this by JDevers · · Score: 1

      The best current graphics using that particular engine are obtained when the rendering processor is overclocked with lysergic acid diethylamide or a combination of specific aureal stimulation and 3,4-methylenedioxymethamphetamine. Either of these produce a substantially improved visual experience.

    13. Re:I'd like to run ray tracing real time on this by forkazoo · · Score: 2, Informative

      Basically, a normal renderer will render the scene from the top down. A Stochastic raytracer like F-Prime renders by shooting random rays all over wherever-the-fuck. As you leave the algorithm running, the image starts to look better and better. The more CPU time is spent on the image, the more rays are traced, and the better everything is. But, if you only have a small amount of CPU time, you still get a rough idea of what the scene look like, rather than an exact idea of what the top thirs looks like. That's really rough. To understand the point about motion blur, it really would be best to understand multidimensional integrals.

    14. Re:I'd like to run ray tracing real time on this by cfuse · · Score: 1
      Just give it six years or so, and you should see the improvements you are waiting for.

      Given what software release cycles are like, if you say six you really mean twelve.

  13. Woot! by SillySnake · · Score: 2, Funny

    Finally a computer able to run the super-ulta-mega high detail Duke Nukem forever! Yes, that's right, the game is finished and just waiting for the computer graphics and processing worlds to catch up to it.. err, right? I mean.. Doom 3! err.. wait.. bah.. Never mind that Still, I would think that unless a company needed results very quickly a seti like application would be much cheaper. If the software guys can code one that can run on the company's network overnight or just at random downtime during the day, then the company ought to save a bunch of money. If they can make it pretty and flash like SETI, then other people might even use it. It just makes more sense to save money in a non-critical manor like that.

  14. One thing to say... by linuxkrn · · Score: 5, Interesting

    seti@home!

    1. Re:One thing to say... by MagicDude · · Score: 4, Funny

      No, we need something nerdier and more useless, like the biggest prime number ever.

    2. Re:One thing to say... by CGP314 · · Score: 5, Interesting

      folding@home

      I used to run seti@home instead of folding@home, but then one day I realized I needed to switch. While finding extraterrestrial life would be the most important development in human history to date, the chances of finding it in my lifetime are very small.

      On the other hand, the chances of my getting cancer or any of the other of the diseases folding@home works on is very great. Plus, if folding@home cures any of these diseases, it will extend my life and increase the chances that extraterrestrials will be found within my lifetime.


      -Colin

    3. Re:One thing to say... by terremoto · · Score: 1
      >seti@home!

      These are their WU totals for the last few days...

      65818

      69106

      73928

      and right now they're closing in on 5th place in New Zealand

    4. Re:One thing to say... by Yehtmae · · Score: 0

      If you're really concerned, buy another PC and run both.

    5. Re:One thing to say... by sakusha · · Score: 1

      Using your backassward logic, it seems more logical to devote your CPU time to researching automotive traffic patterns, so you don't get killed in an auto accident or get hit by a bus.

    6. Re:One thing to say... by CGP314 · · Score: 4, Insightful

      Using your backassward logic, it seems more logical to devote your CPU time to researching automotive traffic patterns, so you don't get killed in an auto accident or get hit by a bus.

      If there was a project that I could devote my CPU cycles that could reduce the possibility of me getting into a car accident, then I would drop folding@home for dontgethitbyacar@home. What's backassward about risk assesment?


      -Colin

    7. Re:One thing to say... by Gopal.V · · Score: 1

      Isn't it a bit too soon to give up on *this* planet ? (if you're not already an alien that is).

    8. Re:One thing to say... by sakusha · · Score: 1

      You obviously have no sense of irony. Or humor.

      If you really did the risk assessment, you'd give up the stressful job you work at to earn money to buy overpriced computer hardware, it will give you a heart attack. You'd find a job without a daily commute where your risks of traffic death are high, you'd go work on a chicken ranch in Montana, selling eggs. Or maybe you should move to Alaska and become a hermit that avoids all human contact, so you don't pick up communicable diseases like influenza or AIDS.

      Sheesh!

    9. Re:One thing to say... by cartzworth · · Score: 1

      Too cold in Alaska...risk of hyopthermia too high.

    10. Re:One thing to say... by Felipe+Hoffa · · Score: 1

      Did you consider that ETs might already have the cure for cancer?

      Go SETI!

      Fh

    11. Re:One thing to say... by ckaminski · · Score: 2, Interesting

      No offense, but if I'm an ET, and the race I just dropped into visit hasn't gotten around to figuring out how to stop the #1 genetic suicide mechanism built into their own bodies, I'm NOT helping them.
      Then again, that's the human in me talking.

    12. Re:One thing to say... by Scurrilous+Knave · · Score: 1

      Too cold in Alaska...risk of hyopthermia too high.

      And don't forget about bird flu. So Montana is right out as well.

    13. Re:One thing to say... by fedux · · Score: 1

      I wish I had those "@ home" !

    14. Re:One thing to say... by dustmite · · Score: 1

      That's a rather silly response to someone who basically just made the quite logical, straightforward statement that he switched to folding@home because it has more chance of producing useful results within his lifetime!

    15. Re:One thing to say... by ravloony · · Score: 1

      It is hardly about him really, I mean he's not the only one liable to get cancer, is he? In any case it somehow seems more useful to try to help cure cancer, which we know exists, than try to find aliens, which probably don't anyway...

    16. Re:One thing to say... by Knight2K · · Score: 1

      Traffic where you live must be wicked if you are at risk of getting hit by a car in your house.

      --
      ======
      In X-Windows the client serves YOU!
    17. Re:One thing to say... by Anonymous Coward · · Score: 0

      ...if I'm an ET, and the race I just dropped into visit hasn't gotten around to figuring out how to stop the #1 genetic suicide mechanism built into their own bodies...

      Voting Republican?

    18. Re:One thing to say... by jhobbs · · Score: 1
      If there was a project that I could devote my CPU cycles that could reduce the possibility of me getting into a car accident, then I would drop folding@home for dontgethitbyacar@home. What's backassward about risk assesment?

      If you need a computer to figure out how to not get hit by a car while @ home, you need to fire your real estate agent.

    19. Re:One thing to say... by binarybum · · Score: 1

      Uh, no. it's risk analysis... choices are weighted.
      the opportunity cost of giving up a few cpu cycles for something that may save you life later is not high and therefore this decision is weighted more heavily than say abstaining from sexual intercourse to avoid disease and possibly death.
      don't they teach this stuff anymore? decision trees, risk analysis diagrams?

      --
      ôó
    20. Re:One thing to say... by Shurhaian · · Score: 1

      "Risk analysis" doesn't need to mean "flailing away at the absolute greatest risk factor to no gain". As mentioned in the grandparent post, there's not much that CPU cycles can do to reduce the incidence of car accidents - but they CAN give concrete results to studies of protein folding, and that is likely to result in, if not cures, viable treatments for a variety of genetic disorders. It's a far more efficient way to deal with a problem than abstaining from everything that makes life something approaching fun or worthwhile: solid gains for, really, negligible cost.

      --
      NB: YMMV. IANAL. Take the above with a grain of salt.
  15. Nice by Duncan3 · · Score: 0, Troll

    While renting out unused machines is not even close to a new thing, it's the LoTR machines, so it's way cool here on /.

    This is what all that "on demand" hype is about after all... *yawn*

    but machines with that much memory in each aren't the norm, so it is a rather sweet cluster.

    --
    - Adam L. Beberg - The Cosm Project - http://www.mithral.com/
    1. Re:Nice by celimage · · Score: 1

      yes but these have magic locked within created by Gandalf

  16. Re:6 megabytes? by nb+caffeine · · Score: 0, Offtopic

    ugh. enough already. shouldnt it be:
    1: 640k
    2: ???
    3: PROFIT!

    or
    imagine a beowulf cluster of 640k!
    or
    litigous 640k
    or
    goat640k.cx
    or
    in soviet russia, 640k needs no more than you!

    maybe i read slashdot too much, but i just see the same crap moderated "funny" all the time...

    --

    "Something's wrong with you...and I hope we never do meet again." - Deftones When Girls Telephone Boys
  17. They're upgrading . . . by Libraryman · · Score: 0, Flamebait

    to dual G5 Xserves!

  18. Distributed.net... by rthille · · Score: 4, Interesting

    Imagine distributed.net being a CPU co-op. They take problems from clients in need of a ton of CPU, farm it out to distributed.net members, and at the end of the month/year you get a small check for all the CPU cycles you spent helping solve problems.

    --
    Awesome furniture, accessories and cabinetry in Santa Rosa, CA: http://humanity-home.com/
    1. Re:Distributed.net... by SillySnake · · Score: 3, Insightful

      A great idea in theory, but how would they track the amount of help that you did in a way that would be one hundred percent hack proof? I don't think you'd want to pay people to analyze every packet that you get back to make sure it's had whatever needed done, done to it. Granted, it would be possible to elimnate most unwanted results with a couple of filters, but when money becomes an issue the community will do what they can to get the most of it.

    2. Re:Distributed.net... by irc.goatse.cx+troll · · Score: 2, Interesting

      Easy -- Make the 'money' be not real money, but a lack of ads/nagging.

      Imagine getting prompted upon installing an application whether you want to A) pay B) have ads or C) donate cpu cycles.
      This would then allow developers to make money off of their software without making it unusable due to ad annoyance (xfire, aim, most shareware)

      --
      Pain lasts, kid. Its how you know you're alive. Sometimes I think this growing up thing is just pain management-TheMaxx
    3. Re:Distributed.net... by bobthemonkey13 · · Score: 4, Funny
      Better yet, let's make a program that makes you pay, has ads, and forces you to donate CPU cycles.

      We could call it KaZaA.

    4. Re:Distributed.net... by Motherfucking+Shit · · Score: 5, Informative
      Imagine distributed.net being a CPU co-op. They take problems from clients in need of a ton of CPU, farm it out to distributed.net members, and at the end of the month/year you get a small check for all the CPU cycles you spent helping solve problems.
      This was already tried, by a company called ProcessTree. The idea was that they'd sell your CPU cycles out and you'd get a cut. They also had it set up in a pyramid fashion, so that you also got an extra few cents for each person you referred to the program.

      The best I could find was this mirror of the FAQ. Since ProcessTree.com now belongs to a domain poacher, I'm guessing they never did find a paying client...
      --
      "BSD: Free as in speech. Linux: Free as in beer. Windows 10: Free as in herpes." --Man On Pink Corner in #52607549.
    5. Re:Distributed.net... by Anonymous Coward · · Score: 0

      What a cool business model.. Yeah.. if you could get kazaa for free if you donated a months worth of spare CPU cycles that'd well rock.

      Mod parent up!

  19. Re:6 megabytes? by harlows_monkeys · · Score: 4, Informative
    Bill Gates said it best...

    No he didn't.

  20. 6 megabytes by circletimessquare · · Score: 0, Redundant

    6 megabytes ought to be enough for anyone

    --
    intellectual property law is philosophically incoherent. it is your moral duty to ignore it or sabotage it
    1. Re:6 megabytes by Anonymous Coward · · Score: 0

      0 mod points will have to be enough for you, it seems.......

  21. I'm signing up right now! by teamhasnoi · · Score: 4, Funny
    I'm going to re-fake the moon landing, but do it right this time! No numbers on rocks, no waving flag, or overlapped crosshairs.

    I may have to re-release the Mars landing too, depending on how well they did...

    Beagle was a great idea, btw. Spend the money and then oops! no mission to render. Sheer genius.

    1. Re:I'm signing up right now! by Anonymous Coward · · Score: 0

      We are sorry to inform you that all available capacity has been sold to George&Tony Inc. for their WMD [re]search project.

      Sincerely,

      Telecom&Weta

  22. Maybe they're right by ctr2sprt · · Score: 4, Interesting
    Update: 03/22 07:08 GMT by S: The linked story says 6 megabytes of memory, we don't believe 'em.
    They might mean 6MB of L2 cache. I don't know what cache sizes are available for Xeons, but probably when you order 1000 CPUs at once Intel are willing to give you hard-to-find stuff.
    1. Re:Maybe they're right by Moonpie+Madness · · Score: 1

      I suppose that's possible, but really. When you describe a box, the first two pieces of info are usually speed and memory. I mean, those are the two most important variables right? This is a typo, though perhaps the reaction is kinda overblown. It is amazing to me that we could use 6 gygabytes of ram... I can't even conceive of 640,000 pieces of info, much less millions of bits. It's crazy crazy stuff

    2. Re:Maybe they're right by hkroger · · Score: 1

      I sincerely don't think so. Ordering 1000 custom CPUs would be very expensive. 1000 pieces is rather small amount for customization.

    3. Re:Maybe they're right by Tore+S+B · · Score: 1

      Indeed, the Itanium machines at our university has 6MB L2. And the 9MB series is coming up soon.

      --
      toresbe
    4. Re:Maybe they're right by samhain_tm · · Score: 1

      Yeah, but they are dual processor systems... 2000 pieces

      --
      I'm the root of all that's evil, yeah, but you can call me cookie.
    5. Re:Maybe they're right by slash-tard · · Score: 5, Informative

      Xeons only go up to 4 megs of cache and those were just recently released. At the time these were bought the max was 2 megs.

    6. Re:Maybe they're right by Aczlan · · Score: 1

      if you had read the story you would have seen that it says 1600 Dual CPU servers (3200 CPU's) "Mr Houston says Weta Digital owns about 1600 servers incorporating 3200 processors in total"

      --
      "Democracy is two wolves and a lamb voting on what to have for lunch. Liberty is a well-armed lamb contesting the vote
    7. Re:Maybe they're right by drudd · · Score: 2, Interesting

      Trust me, 6 GB goes by very quickly.

      So let's say I'm doing a simulation of structure formation in the universe.

      I have a cube grid of cells, 512 on a side (my own code uses adaptive mesh refinement to increase resolution, but we'll ignore that for simplicity).

      So each cell requires 3 floating variables to compute gravity, and 8 floating variables to calculate hydrodynamics. At 4 bytes per variable, that's a total of 5.5 GB just for the mesh.

      Then you need to add dark matter particles, allow for star formation and cooling, track different element species, and data structures to allow for adaptive mesh refinement.... each of which have similar memory requirements.

      Doug

      --
      Venn ist das nurnstuck git und Slotermeyer? Ya! Beigerhund das oder die Flipperwaldt gersput!
    8. Re:Maybe they're right by OS24Ever · · Score: 1

      Each processor in the cluster has 512k of cache. These are Xeon DP systems, not Xeon MP.

      --

      As a rock-in-roll Physicist once said, No matter where you go, there you are.

  23. Renderfarms online - old news by Anonymous Coward · · Score: 5, Interesting

    Posting anon as I have an interest in some of these companies :
    http://www.respower.com/ - 250+ machines (~500GHz), 250GB ram
    http://www.rendercore.com/ - 700 machines
    http://www.render-it.co.uk/ - 82 cpus (131GHz), 82GB ram)

    The only 'interesting' thing here is that it's WETA's farm. Other than that, I doubt they offer the wide selection of software (lest they struck deals lately) not to mention field experience with 'oddball' files.

    Good luck to them, though

    1. Re:Renderfarms online - old news by sakusha · · Score: 1, Troll

      And the big liability here is the same, it's WETA's farm. It is obvious they didn't really think it through when they set up this farm.

      My buddies in Australia and NZ tell me their internet costs are extremely high, they pay little for incoming data but pay up the wazoo for outgoing data. So let's say I zap a few gigs of model and map data from my studio in Hollywood, no problem, but when they want to send back terabytes or more of uncompressed, rendered frames, it's going to cost a whole lot more than that render farm down the street which is easily accessible by cheap US networking, or I could just drive in and pick up a stack of Exabyte tapes. No wonder you heard tales of WETA fedexing iPods around with compressed rushes. I worked with a lot of Hollywood producers and they're always in a hurry, Fedex from NZ isn't going to work too well.

      One big lesson I learned in Hollywood is that you'd have to be an idiot to actually BUY a huge CG render rig. Everyone who builds a big rig is absolutely the state of the art when they BEGIN the project. But by the time they finish, the rig is obsolete, the studio down the street with the NEW project is now the state of the art. I've seen CG studios take huge losses on Big Iron like Connection Machines, Crays, etc, they were all acclaimed for their work, but after the big project, they all limped along trying to rent out the CPU for other projects, until they went bankrupt after a few more months. So it makes no sense to build your own render farm when you can lease it and create a virtual studio. Why accumulate hardware, which depreciates so quickly? Boy did WETA fuck up on this one.

    2. Re:Renderfarms online - old news by rimu+guy · · Score: 3, Insightful
      Boy did WETA fuck up on this one.

      Boy, did they ever. The graphics in the Lotr and Master and commander sucked. The movies were released late. No one won any awards. And the NZ film industry is in tatters.

      No wait. I mean the opposite of all that.

      Weta knew up front the boxes were only of any use to them for a couple of years. They _budgeted_ on throwing them away after the Lotr trilogy was done. If they can get anything back on them now, more power to them.

      Personally, I think its very cool. I'm even seeing if I can get a couple of machines from them to host some of my Lotr-fan customers on. I for one would be keen to run on an ex-Weta server.

      - Linux VPS Hosting

    3. Re:Renderfarms online - old news by sakusha · · Score: 2, Informative

      You don't get it. They're going to throw away more money trying to rent the server farm than if they just send them to a toxic waste dump in China. Unless, of course they can get nutball otaku like you to buy the old blades at extortionate prices as your little trophy, just so you can say "hey dude we can host your pr0n website on a machine they used to make LOTR!"

    4. Re:Renderfarms online - old news by op51n · · Score: 1

      I don't think it'll be quite true of WETA, that they will go under having bought the hardware.
      If you look at what they are lined up to do - Eva live action movie, King Kong... There are a few others I saw listed as being worked on by them.
      Basically, they have garnered so much positive attention from their work on LotR that they are in no worry of losing money any time soon. Not with the business they're getting.

    5. Re:Renderfarms online - old news by blair1q · · Score: 1

      Just tell us what "otaku" means and we'll let you go.

    6. Re:Renderfarms online - old news by Anonymous Coward · · Score: 1, Informative

      It means "nerd, loser; a person who has nothing better to do with their life so they pass the time by watching anime, playing videogames, surfing the internet (otaku is also used to refer to a nerd/hacker/programmer)."

    7. Re:Renderfarms online - old news by sakusha · · Score: 1, Flamebait

      The point isn't that WETA is going to go bankrupt. It's that their render farm has a bad business model, it's going to suck up money. It's unsustainable. They wouldn't be trying to rent out the farm if they had a current business model that was sustainable. I don't know how WETA's structured, but if it's anything like Hollywood, it's all phony accounting and even the most profitable movies have zero profits on paper, it gets siphoned off by investors and never gets plowed back into the production companies. That's just how it works. So the production companies have to stand on their own two feet financially, they have to make a profit on their own.

      The article says their primary advantage is that people can use WETA's proprietary software which kind of defeats the whole idea of outsourcing your render to them, you can't set it up yourself and let it run on their hardware without having WETA do it for you. You can't just rent the farm, you have to rent the whole company and outsource the design too.

      And BTW, whoever modded my oringinal msg down as flamebait is abusing their privileges, someone mod it back up. It may be unpopular to criticize WETA, being godlike figures to LOTR fanatics and all, but I actually worked in the industry and know how it works, unlike 99.99% of /. users with mod points.

    8. Re:Renderfarms online - old news by Anonymous Coward · · Score: 1, Informative

      Otaku translates as "fan", usually in a bad sense where you will do something bad for your life to enhance whatever you are a fan of.

    9. Re:Renderfarms online - old news by Anonymous Coward · · Score: 0

      their render farm has a bad business model

      Got news for you: the entire CG industry is a bad business model.

      The only way a CG company survives is to be owned by a major studio.

      There is a glut of talent, and everybody thinks they can start their own CG house - so they max out their credit cards (the days of business loans are long gone, although if they're extremely lucky, they might land a project first, then use the advance money to buy equipment), buy some equipment, and bid on projects.. and since they're starting out, they lowball the project, hoping to get established. Everyone puts in 20+ hour days, they finish the project on time, and go looking for another project.

      But since there are three more CG startups, they realize that they can't stay in business by lowballing (their first job left them heavily in debt), so they bid the same as every other 'established' house, and get beat out by new startups doing exactly what they did when they started.

      It's a vicious cycle.

    10. Re:Renderfarms online - old news by ScrewMaster · · Score: 1

      Bragging rights, eh?

      --
      The higher the technology, the sharper that two-edged sword.
    11. Re:Renderfarms online - old news by sakusha · · Score: 1

      Your point is essentially true for the bulk of the CG biz (and it's the same argument I was making) but it isn't totally true. There are companies like ILM and Pixar that have self-sustaining business models. They even own their own render farms. But those studios are definitely the exception. WETA is no ILM or Pixar, they're the upstart trying to finance their projects with their credit cards (so to speak) as must now be obvious by their need to raise cash by renting their farm.

  24. Interesting combination isn't it? by toesate · · Score: 1

    It would be interesting to hear out to anyone that might have really tried such a combination - Xeon with let say 8MB RAM(existence?)..

    "It blazingly fast.. but it ran out of memory during bootup.. using kernel 1.2.."

    --
    Hey, that's my password you are typing
  25. Cool! by xxx_Birdman_xxx · · Score: 1

    Some PCs, mostly older systems used to help create the first film in the trilogy, The Fellowship of the Ring, have been donated to a local school.

    Those machines would still have to be pretty good, even if they are called 'older systems'.. Some of the local school geeks would love to think they are working on a machine that may have been used to create Gollum!

    --
    Live in your skin. Keep changing the scenery.
  26. LAN Connection ? by ultranova · · Score: 5, Funny

    Surely they used Token Ring to connect them ?

    --

    Forget magic. Any technology distinguishable from divine power is insufficiently advanced.

    1. Re:LAN Connection ? by Anonymous Coward · · Score: 1, Funny

      You try make funny.

      You type Tolkien ring next time, you no type Token ring again.

      You no funny man, no karma for you.

    2. Re:LAN Connection ? by renec · · Score: 1

      No, Tolkien Ring

    3. Re:LAN Connection ? by Anonymous Coward · · Score: 2, Insightful

      That joke is so old that people get it even when you misspell the punch line.

    4. Re:LAN Connection ? by Anonymous Coward · · Score: 0

      No, they lost their token in the ether

    5. Re:LAN Connection ? by spacefrog · · Score: 1

      Nope

      (drum roll)

      They used Tolkien Ring

  27. Re: Rent A Bit of Weta Digital by Anonymous Coward · · Score: 0

    Slashdot needs a -1: Tired Old Joke mod like I need to get laid.

  28. Nasty hobbits. They tricked us! Thieves! by pariahdecss · · Score: 5, Funny

    Nasty fat hobbit probably sold the extra RAM to buy Twinkies(R)

  29. Re: Rent A Bit of Weta Digital by Anonymous Coward · · Score: 1, Funny

    So you DON'T need to get laid.

  30. Excuses, excuses by rjch · · Score: 0
    The linked story says 6 megabytes of memory, we don't believe 'em.
    Be careful, you might just give old Billy boy a way out of the comment that's been dogging him for years...

    "No, no, I meant nobody would ever need more than 640 gigabytes of memory!!!"
    1. Re:Excuses, excuses by BiggerIsBetter · · Score: 1

      The time when we need in excess of 640 GB or RAM will be closer than you think. I give it 5 years absolute tops. Probably less.

      --
      Forget thrust, drag, lift and weight. Airplanes fly because of money.
    2. Re:Excuses, excuses by zcat_NZ · · Score: 2, Funny

      The time when we need in excess of 640 GB or RAM will be closer than you think. I give it 5 years absolute tops. Probably less.

      Depends on how early they get Longhorn out the door, I guess :)

      --
      455fe10422ca29c4933f95052b792ab2
  31. I don't see why not. by torpor · · Score: 2, Insightful

    If you've got renderman set up to render to disk, and your disk arrays are pretty fast, I don't see any reason why these dedicated render machines shouldn't have only 6 megabytes of RAM per CPU.

    okay, it doesn't make a -ton- of sense to render direct to disk, but maybe it can be done and not require so much RAM?

    --
    ; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
    1. Re:I don't see why not. by Jexx+Dragon · · Score: 2, Insightful

      You said it right there... 6MB of RAM per CPU... Five hundred computers... Thats a mighty big number. Since its a cluster each node has to render only a small part of the image and can render to disk.

      --
      I don't have time to comment my code, the program is late already.
    2. Re:I don't see why not. by Stephen+Samuel · · Score: 1
      Insightful??? How about funny?

      We're talking dual 2Gz Pentiums... I doubt that you could find dimms that could fit into those boxes that held less than 64Meg without special ordering (( That's right -- for the price of 512Meg of ram, we can give you a whopping 6Megabytes!)).

      Possible sane explanations would include:

      1. 6 Meg cache
      2. 6Gig of RAM
      3. 6Gig if Disks (a bit too small to believed)
      4. 6Meg video cards. (again, a bit small these days)
      I'd be betting on #1 ir #2.
      6 gig disks are hard to come by, these days., and with 6 meg of RAM, you could cache the entire OS in a ramdisk and obviate the need for a real disk altogether -- and make a nice, fast box, once it's loaded over the 'net (Memory to memory, you could transfer a 1GB OS image in about 10 seconds with a gigabit ethernet link).
      Similarly, a 6meg video card doesn't make much sense... The only reason to have a vidwo card in one of these boxes would be to take advantage of hardware rendering tricks. I can't see getting a video card fast enough to be worth programming for that didn't have at least 32Meg of ram.
      --
      Free Software: Like love, it grows best when given away.
    3. Re:I don't see why not. by torpor · · Score: 2, Interesting


      (i'm thinking less general-purpose computing purchase, and i think you are thinking more ...)

      yeah, so i thought 6Megs was a typo at first, but then i considered the mere possibility that they may just have spec'ed their RAM to their direct process requirements, 'embedded system' style.

      and, i still don't see why not... though your point about RAM being available in sizes less than 64 megs is valid, i've seen 8meg dimm's for 2ghz Pentium systems, cheap, all over the place. remember, this is new zealand we're talking about, not fry's, burbank. they want something easily replaceable, locally.

      maybe then the question would be 'where did the other 2megs go', and that might answer your videocard situation. plenty of 2ghz Pentium mobo's do video sharing...

      i know it doesn't make 'sense'. but, on the other hand, i don't see why not. why buy so much ram if you've determined that you don't really have to for your specific application? i've seen tons of systems designed, and put into exceptional use, that way ... not all general purpose computing laws (of economics, of use) are applicable in specific-purpose stuff ...

      but hey, it could be a typo. 6gigs would 'make more sense', I suppose...

      --
      ; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
  32. 6 Gigabytes on a 32bit CPU? by ProfessionalCookie · · Score: 3, Interesting

    Correct me if I'm wrong here but aren't the Xeons currently 32 bit? Doesn't that mean they can't address more than 4 Gigs? I thought that's what the whole big deal was with 64 bit. Now maybe if they were G5s...

    1. Re:6 Gigabytes on a 32bit CPU? by Xpilot · · Score: 4, Informative

      Well, initially 32-bit Intel chips could only address 4GB's, but recently we have crazy shit like PAE that allows up to 16GB RAM to be installed and addressed by the OS that supports it, but applications can still only use 4GB at a time.

      --
      "Backups are for wimps. Real men upload their data to an FTP site and have everyone else mirror it." -- Linus Torvalds
    2. Re:6 Gigabytes on a 32bit CPU? by Duty · · Score: 1

      IIRC, they can (using a hack that would make assembly programmers faint in horror, as usual) but no one process can use more then 4 gigs. Anyone know if this limit applies to different threads owned by the same process?

    3. Re:6 Gigabytes on a 32bit CPU? by gunix · · Score: 1

      Isn't there some feature in Xeon that makes them able to use 36 bit adressing?

      --
      Evolution of Language Through The Ages: 6000 BC : ungh, grrf, booga 2000 AD : grep, awk, sed
    4. Re:6 Gigabytes on a 32bit CPU? by Anonymous Coward · · Score: 0

      "Intel(R) Extended Server Memory Architecture--expanded 36-bit memory support which allows operating systems and applications to utilize memory greater than 4 Gbytes" Intel

    5. Re:6 Gigabytes on a 32bit CPU? by bbrazil · · Score: 2, Informative
      PAE that allows up to 16GB RAM to be installed
      Actually its 64Gb. Around the PII 4 extra bits were added to bring it to 36bits.
      Of course its a bit faster to access 16Gb rather than 64Gb and faster againt access 4Gb for some PAE reason.
    6. Re:6 Gigabytes on a 32bit CPU? by germ!nation · · Score: 1

      as its been said, it was a typo...but more to the point, with a rendering farm, RAM isn't that relevant as you are just after CPU grunt...the only reason 3d workstations have large amounts of ram is so yo ucan cache hi-res textures in the viewports

    7. Re:6 Gigabytes on a 32bit CPU? by elec1cele · · Score: 1

      Some application's can use more than 4GB of RAM: SQL Server 2000 and Exchange 2000 & 2003 to name a few.

      I think the deal is they have to be PAE aware, I know there are some special settings you have to set on SQL Server to get it to use more than 4GB and I imagine the same is true for Exchange.

      Also in SQL Server you loose some functionality (Dynamically allocating only the amount of RAM it needs jumps to mind)

  33. Sell 'em on e-bay by GloomE · · Score: 5, Funny

    Wouldn't they make more by selling them as (framed) collector's items?
    Blade 1 of 500: current bid $1(insert zeros here).

    1. Re:Sell 'em on e-bay by Anonymous Coward · · Score: 0

      Wouldn't they make more by selling them as (framed) collector's items?

      They will be soon providing manuals with instructions on how to obtain them shortly. Please understand that you are not receiving the items themselves, but just purely information!

  34. interconnect by painehope · · Score: 5, Insightful

    the real killer is that there's quite a few industries that can't rent time on their cluster because the gigabit interconnect ( IBM blade chassis have a switch module internal to each chassis, and I don't think you can get any HSLL - high-speed, low-latency - network interconnect modules ( Myrinet, SCI, Quadrics, etc. ) for them ) has too high of a latency for their applications.

    Bandwidth-wise they should be fine, as each chassis has at least four ports that could be trunked to a top-level switch w/ a beefy backplane ( I could tell you the # of ports per chassis if I was at work, as I've been messing w/ some of their blades lately ), giving a peak per-chassis bw of > 400 MB/sec.

    Of course, I'm wondering how Weta got around it themselves, as I would think that rendering digital video is fairly heavy on inter-node communication. This would still be aswesome for web-servers or problems that are "embarassingly parallel".

    --
    PC moderators can suck my White pierced, tattooed dick. If you think pride == hate, s/dick/Aryan meat mallet/g.
    1. Re:interconnect by 2megs · · Score: 5, Insightful

      Rendering digital video is about as parallel as compute loads get. Generally each frame can be an independent computation. For most ray-tracing algorithms, computing each pixel of each frame is fully parallelizable too.

      The global AI things they did to have 10,000 troops all interacting together is obviously not quite so independent, but I'm willing to be the bulk of the compute load goes into creating pictures of those interactions, not the interactions themselves.

    2. Re:interconnect by Anonymous Coward · · Score: 0

      From what I understand, their application is "embarassingly parallel" so the interconnects between bladecenters doesnt really matter very much. They use Gigabit ESM's (Ethernet Switch Modules) in each Bladecentre and they are connected to a Foundry Backbone switch.

    3. Re:interconnect by Anonymous Coward · · Score: 0

      The big killer is usually the textures needed for every node for each frame, you have to come up with a nice cacheing mechanism or something similar if you don't want your server to be the bottle neck.

      As to the AI, usually the simulations for such a thing are separately 'baked' before the real render happens, kind of like multipass rendering on graphics hardware.

    4. Re:interconnect by sakusha · · Score: 4, Informative

      You obviously have never worked in CG. Many common, simple effects cannot be parallelized. For example, Maya's particle effects are notorious for their inability to be parallelized and run on render farms, if they use randomness (and most particle fx do use randomness in positioning). Those fx must be rendered sequentially on a single CPU. Each frame's particle positions are used to calculate the next frame's particle positions, they're all calculated at runtime.

    5. Re:interconnect by HeghmoH · · Score: 1

      Yeah, basic raytracing is certainly an embarrassingly-parallel problem. I wrote a basic parallel raytracer using straight TCP to communicate between the nodes. Using 15 computers, located all over the place (several in the same room, several across campus, one on the other side of the country) resulted in basically a 15 times speedup with no noticeable overhead. Of course, the raytracer itself was very simple (no fancy effects, just shadows, reflection, refraction, etc.) and very slow, which helps make it parallelize better.

      --
      Mod down posts with a "Free Mac Mini/iPod" sig, they're spam!
    6. Re:interconnect by Obasan · · Score: 2, Insightful

      Actually, rendering is fairly light on network requirements and very heavy on memory/cpu. (Download scene files & textures then crunch numbers for 10-40 minutes depending on layer complexity.)

      But the bladecenter chassis also does in fact support a Myrinet interconnect if you so desire.

    7. Re:interconnect by Anonymous Coward · · Score: 0

      Actually the blade chassis that IBM uses is very modular. You can use the default gigabit switch but you can also swap it out with a switch of your choosing. I think Cisco was working on a switch module for the IBM chassis.

      I know that IBM *wants* other manufacturers to build the modules, precisely because of the wide range of requirements peaople might have on this hardware, IBM won't be able to service them all anyway.

    8. Re:interconnect by kdogg765 · · Score: 1

      For 3D this can be true. However, for 2D rendering (like from Shake for instance), the network can quickly become a huge bottleneck when using large renderfarms as all the nodes are pulling hundreds of elements across the network to be put into a single composite, then writing the final out to disk. You can easily end up with CPU's waiting for elements to load as the network gets jammed. -K

    9. Re:interconnect by fajoli · · Score: 1

      Never having worked in CG, I am having some trouble understanding this concept.

      What prevents the particle locations from being pre-calculated? Does the particle position rendering determine its next position? A link to the algorithm would be helpful.

    10. Re:interconnect by sakusha · · Score: 4, Informative

      That's a very complex subject, but it boils down to this: there's no technical reason you can't precalculate all the particle positions over time, but that's not how they did it in Maya.

      Let's say for example, you set a particle generator to run 60 frames, emitting smoke from a point, like from a cigarette tip. Smoke particles start emitting on frame 1, and continue on their path, particles persist through frame 60 as they drift upwards in a path influenced by random air currents. If you roll forward to frame 30 and render the last half only, you start all over with no smoke from the first 30 frames, it starts from scratch, they emit right from the tip in a new smoke trail, there's no history of past particle movement. So you'd get a huge discontinuity if you rendered the frames in batches.
      As far as I can tell, the actual image rendering doesn't influence the positions of the particles. It's just that they're calculated sequentially as each frame is rendered. Yeah, it's a huge pain and there aren't many good workarounds. But that's what you have to work with in order to use the particle generators, which are hugely powerful. Its the worst possible method, except for everything else anyone's ever thought of.

    11. Re:interconnect by TedCheshireAcad · · Score: 1

      This is what happens when Computer Scientists try to play Mathematician.

    12. Re:interconnect by Anonymous Coward · · Score: 0

      Weta as many other big facilites use Maya/RenderMan for their CG work. Pixar's RenderMan can redistribute a job/frame to different machines, so you need a fast connection to move millions of files in less than a second.

    13. Re:interconnect by Anonymous Coward · · Score: 0

      wow. and you do work in CG?

      Bake the particle simulation into keyframes. Then render. Maya/CG 101.

    14. Re:interconnect by Anonymous Coward · · Score: 1, Informative

      A dynamics/particle cache takes care of this. It's right there on the menu - and in the docs. Try it sometime!

    15. Re:interconnect by sakusha · · Score: 1

      Hey, this wasn't in v4 was it? It must be new in v5. I haven't done serious particles since v4, I learned to avoid them due to the pain involved.

      So there are new workarounds, but it looks like there are still problems for render farms. Like for example, the docs say it's endian-dependent, so I can't whip up a particle cache on my Mac and run it on a PC render farm.

    16. Re:interconnect by Anonymous Coward · · Score: 0

      It was in v1. You haven't done serious particles ever (you must not work in CG.) Disk/mem cache is the only way to view complex effects in real time, or scrub the timeslider. Caching the various simulation data is a must to get any work done, not just rendering.

      The endian stuff for binary files is handled by Maya - we routinely render the same scene on mips and intel.

      If you're running maya on a mac, you're running a slow, buggy port that is missing features on overpriced hardware that you can't get a pro video card for.

      Maya on Mac and (intel) render farm don't exist in the same universe.

  35. no reason to doubt 6GB by Anonymous Coward · · Score: 4, Informative

    The IBM HS20 has 4 DIMM slots used in banks of 2. No reason to think 2x2GB and 2x1GB would not work.
    Linux, FreeBSD or Windows 2000 AS would support PAE allowing an app to use close to 4GB, leaving 2 GB for OS kernel , so seems reasonable.

    Ay one who doesent believe me check at crucial.com. I wont provide a URL but look for IBM, Bladecenter, HS20

  36. One word. by Anonymous Coward · · Score: 0

    Massive.

    Now you can rent their software and pay them to run it for you on their cluster. None too shabby.

    Maybe they can't make a crappy episode of Triping the Rift lowering expectations everywhere. I can't tell you how disappointing that is. But if you need an army of anything, they're probably the people to call.

  37. The choice by FraggedSquid · · Score: 0

    I'll have the one on the left.

    --
    You don't need a lab to make mud.
  38. STOP THAT 6MB LAME JOKES by robbyjo · · Score: 4, Interesting

    Please...

    This may be an old news, but the details of that machine is here. That's some stuff to drool over. Some excerpts:

    ... provide a combination of 4TB of online storage and more than 20TB of nearline storage as a global storage repository ...

    ... create and manage up to 100TB of data ...

    And now this machine is up for a rent. Here's the company website.

    --

    --
    Error 500: Internal sig error
    1. Re:STOP THAT 6MB LAME JOKES by Anonymous Coward · · Score: 0

      Wrong! The article is about the IBM BladeCenter, Intel Xeon based blade server not SGI IRIX based hardware as the link you provided indicates.

    2. Re:STOP THAT 6MB LAME JOKES by Anonymous Coward · · Score: 0

      That's the extra server, my man. RTFM carefully.

  39. Not 6 gigabytes, or megabytes by Mixel · · Score: 0, Redundant

    6 [gigabytes?]

    To do that, they'd have to be 64 bit machines and I dont think they are. Maybe it was originally intended to read '600 megabytes'.

    1. Re:Not 6 gigabytes, or megabytes by Wiz · · Score: 1

      No, that is not true. I could run a 32-bit machine with 64GB of memory if I wanted.

      There is however a 4GB limit per process! Unless you use Intel's PAE, which gives you about 64GB IIRC.

  40. We did it on the cheap in NZ... by Anonymous Coward · · Score: 0

    that's why PJ is so keen to get those Oscars home. We are gonna melt them down for more processing power...

  41. Marketroid Amalgamation. by Behrooz · · Score: 2, Funny

    Maybe it's 6MB of L2 or other on-CPU high-speed cache. An odd number, but it makes a lot more sense than any other explanation I can think of.

    I'm betting it's another marketroid amalgamation... something along the lines of:

    "1MB of L1 cache and 2MB of L2 cache per processor, for a total of 6MB per machine!"

    Just like those old '64 bit!' console advertisements. Uhh, yeah, 16 bits pipeline times three pipelines plus two extra 8-bit memory thingamajiggies may add up to 64 bits, but it for damn sure isn't a 64-bit machine.

    --
    "We have to go forth and crush every world view that doesn't believe in tolerance and free speech." - David Brin
  42. six megs by chaos4u · · Score: 0, Troll

    See its true !!

    we dont need these bloated memory sizes
    if programmers would all write cleaner tighter code

    we all would only need six megs !!

    if the rings can be done six

    windows can be done 4

    linux in 2

    and our apps would only need 512K

    our games 1 or 2 megs

    six megs

    it was good enough to play xcom !! it should be good enough play DOOM III damn it

    you hear that john !! i want my doom cramed into six megs !!

    if they can cram gollum into 6 freaking sticks
    i want eve online starwars galaxies everquest doom III and halflife II all running while i poke around in excel spread sheets .

    its time we computer users stand up to bloated overly commented crappy code !!

    i want my six megs to generate me Gladriel
    and the 7 drawfs

    call corsair to day and DEMAND your
    hyper X dual ddr 5000 xms twin 3 meggers with lcd's today !!!

    --
    Music the Paint dancefloor the canvas your body the brush
  43. memory by Anonymous Coward · · Score: 0

    Isn't 6 Mb of memory enough for a cluster?

  44. Rather a contrast to the computer they used..... by zmollusc · · Score: 3, Funny

    to develop the military tactics used in the battle scenes. Cavelry charge (with lances) against infantry dug into rocks and buildings. Most inept castle defence ever devised. Etc etc. I assume it was all worked out on an unplugged (insert archaic/obscure home computer).

    --
    They whose government reduces their essential liberties for temporary security, receive neither liberty nor security.
  45. Flipping bits.. by adamofgreyskull · · Score: 1

    Just think of the fun you could have with that bit though..flipping it at random from time to time..making big hollywood movies go late and over-budget.

    1. Re:Flipping bits.. by Anonymous Coward · · Score: 0

      Just think of the fun you could have with that bit though..flipping it at random from time to time..making big hollywood movies go late and over-budget.

      So there's even more money down the drain. Where's the fun in that? Or you can cause 'em to stress out. Hahahaha. R u 433|\|?

  46. Well, jeez man, why not just "make it so"? by Colin+Smith · · Score: 1

    I mean, if you're tired of waiting and everything.

    --
    Deleted
  47. Re:what? by Anonymous Coward · · Score: 0

    "The linked story says 6 megabytes of memory, we don't believe 'em."

    Why not? What's so hard to belive about that? Considering how much that movie sucked, I'm amazed it's that MUCH! And besides, why would they use more powerfull computers when all they're doing is some silly kid's film.

  48. Wise words by Anonymous Coward · · Score: 0, Redundant

    The linked story says 6 megabytes of memory, we don't believe 'em.

    I don't blame you, why would anyone want more than 640k?

  49. [OT] Millbyte? by Mick+Ohrberg · · Score: 1

    Off topic, but along the same lines if your post... I'm getting SO tired of seeing computer ads for computers with 256/512/1024/whatever millibit (mb) of memory instead of MegaByte (MB). Before we got into the GHz range for CPU's, it was...well, since the unit 'hz' doesn't exist, I would have to assume they meant 450/550/650/whatever milliHertz (mhz). *sigh*

    --

    Quidquid latine dictum sit, altum sonatur.

  50. Defeat cheating? by Dogtanian · · Score: 1

    A great idea in theory, but how would they track the amount of help that you did in a way that would be one hundred percent hack proof?

    Obfuscate the work being done and insert test/checking operations between the 'real' work operations. Verify that the results of the test operations were what would be expected if they had been carried out.

    Do not reveal what the test operations are (or even what the 'real' work is). Do not reveal what percentage of operations are test operations. Change the test operations arbitrarily. Note any discrepancies immediately, and check recent results supplied from that source.

    It wouldn't be 100% hack-proof, but it would be a major PITA to hack; since you are only being asked to carry out a set of operations without knowing what they are, the payers can change obfuscation algorithms, and the nature/quantity of test/check routines around any time they like, *without notice*.

    If this is done, the major weakness would be payers getting lazy; i.e. not altering the nature of the check routines, or using weak/consistent obfuscation.

    --
    "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
  51. do us all a favor..... by Anonymous Coward · · Score: 0

    occupy weta servers and stop the rendering of the sure to be vomit inducing evangelion live action movie. wont some one please think of the "children"?!?

  52. Comma splice by wurp · · Score: 1

    The linked story says 6 megabytes of memory, we don't believe 'em.

    When you are expressing two complete thoughts (that could stand on their own as sentences) in one sentence, you separate them with a semicolon.

    Like this: The linked story says 6 megabytes of memory; we don't believe 'em.

  53. How much would you like to bet.... by ConnortheMad · · Score: 1

    That it's currently just being used to play solitaire and minesweeper?

  54. that annoying person by my+sig+is+bigger+tha · · Score: 1

    WHO corrects everyone's grammer...

  55. And even if he did... by bonch · · Score: 1

    640K was enough for anybody in 1981.

    That's like me saying now "1GB of RAM should be enough for anybody." I didn't say "ever."

  56. Re:Rather a contrast to the computer they used.... by PitaBred · · Score: 1

    You might get a bit more respect for your opinion if you spelled things like "defense" and "cavalry" correctly.
    Either way, it was a lot of action. Sieges are not action. They're not fun. They were usually months of nothing. Bombardments and nothing else are also not fun. They lost appeal after about 60 seconds. They're not what movie-goers want. Besides, the orcs had the advantage of overwhelming numbers. Who cares if a lot of them died, as long as enough of them didn't?

  57. Now we find out if "grid computing" sells by Animats · · Score: 2, Insightful
    OK, "grid computing" fans, here it is, a big CPU resource open for commercial customers. Let's see if people line up to buy cycles. There must be paying customers out there who want to do rendering, or VLSI simulation, or numerical wind-tunnel tests of wing sections, or something.

    We're waiting...

    As I've pointed out before, if there was a market for this, ISPs would be selling off-peak CPU time on their hosting farms.

    1. Re:Now we find out if "grid computing" sells by sakyamuni · · Score: 1
      OK, "grid computing" fans, here it is, a big CPU resource open for commercial customers. Let's see if people line up to buy cycles.

      As I understand the "grid computing" concept, it's more about doing this internally in a company. In other words, departments and business units will be making use of unused CPU cycles and disk space anywhere in the company's worldwide data centers.

      It makes sense, too. I mean, who is going to ship company data (most of which is likely considered company confidential or business secrets) to some random place to be processed? No, it's about using your own (company) resources more efficiently.

  58. Grammar whore by Shurhaian · · Score: 1

    Alternately, since the two thoughts are closely related(the second needing the first for context to make any worthwhile statement), the second clause could be phrased as a dependent clause, thus:

    "The linked story says 6 megabytes of memory, but we don't believe 'em."

    --
    NB: YMMV. IANAL. Take the above with a grain of salt.
    1. Re:Grammar whore by wurp · · Score: 1

      Damn, I shoulda thunka that.

  59. Re:Rather a contrast to the computer they used.... by zmollusc · · Score: 1

    Darn. Must get one of those modern dictionary books. There could have been better use made of the castle and the defenders and STILL have them overwhelmed. This would have been more exciting, more 'realistic' and less annoying.

    --
    They whose government reduces their essential liberties for temporary security, receive neither liberty nor security.
  60. correction: Myrinet *IS* available by Anonymous Coward · · Score: 0

    Although WETA did not buy the option, Myrinet interconnect *IS* available for the IBM BladeCenter.

    For WETA the standard GigE interconnect would have been price/performance cheaper since rendering is more a batch style job then a parallel job which would have benefitted more from such a high-speed low-latency interconnect.

  61. Wake Up Mods!!!!!! by decepty · · Score: 1

    Funny - Definately.
    Offtopic - Maybe.
    ...but redundant??? What is this, free crack for mods day? Mod this post funny or underrated - PLEASE!!!!

    --
    Be careful! Bears shouldn't consume large furry dogs.