Weta Digital's Render Farm Upgrade

Headspace2 writes "Weta Digital (The graphics company behing LOtR computer effects) has just purchased 220 2.2GHz dual Xenon machines, each with 4GB of ram, to add to their current render wall of 350 1 Ghz P3 systems. They have also placed an order for another 256 Xenon servers. And it's all running Linux. My favorite quote is 'it is thought the server farm will be the most powerful processing site in the Southern Hemisphere'. They should use that in the FotR ad campaign... 'Rendered using the most powerful processing site in the southern hemisphere' Congrats the guys that get to play with all those clock cycles. Make more movies.

Comments

Xenon?

[syates21]

Powered by noble gas. Woohoo!!

Re:Xenon?

[Paul the Bold]

Yes, molecular computing is finally here.

I am still trying to figure out what the "F" in "FotR" means.

Note to CmdrTaco: use the preview button.

Re:Xenon?

[Dahan]

Yeah, except being a noble gas, you can't get a dual Xenon... I don't know where these guys are getting 'em; my supplier only has single-atom configurations.

Re:Xenon?

[Alan Partridge]

have you pushed the Super Nashwan button for extra speed?

Re:Xenon?

[spongman]

yeah, but you only get 15 seconds and then you have to go buy another one... oh, man! was that a waste of money?

Block Crunching

[krugdm]

Wow. I wonder what their Distributed.net keyrate would be?

Re:Block Crunching

[ambit]

Actually the P4 core is really terrible at RC5. See here: http://n0cgi.distributed.net/speed/query.cgi?cputy pe=all&arch=0&contest=rc5
There is something about the core missing a 'hardware based rotate function' from what i have gathered.

Re:Block Crunching

[Tmack]

Well, the dnetc.exe thats on the current release isn't optimized, but the Beta is. The old core was getting about the same keyrate as a p3-1.1G on a p4 1.8A. The new core increased that to close to 3MKeys/s. T

*sigh*

[ottffssent]

Xenon is an element. Xeon is an expensive CPU. I see "Intel Xenon" too many times at work. Please not on Slashdot too.

Re:*sigh*

[CanSpice]

Maybe this is a reference to a vaporware CPU offering from Intel?

Re:*sigh*

[Anonvmous Coward]

"Xenon is an element. Xeon is an expensive CPU. I see "Intel Xenon" too many times at work. Please not on Slashdot too"

It's really funny how people posting on a public forum act like it's really painful to see bad spelling and grammar.

Re:*sigh*

[jerde]

It's really funny how people posting on a public forum act like it's really painful to see bad spelling and grammar.

But when isn't painful? I see it as exactly analogous to hearing a note out of tune.

I think his comment was that the actual stories on /. should be edited for correctness. Isn't that what the editors are for?

- Peter

Re:*sigh*

[drsmithy]

For those of us who learnt language from books instead of from listening to TV, it *is*. As another poster said, it's as painful as listening to out of tune music.

Re:*sigh*

[Anonvmous Coward]

I think it's fine to expect that from the article itself. To expect that in the summary that's submitted by individuals is akin to expecting it from from every single person who comments on Slashdot.

If ya understand them, don't wince. I can understand the inchs vs. centimeters thing earlier, but Xeon vs. Xenon isn't that ambiguous.

Re:*sigh*

[the way, what're you]

Despite your formidable encryption scheme, I'm on to you two terrorists. You have been reported.

Re:*sigh*

[psamuels]

I think it's fine to expect that from the article itself. To expect that in the summary that's submitted by individuals is akin to expecting it from from every single person who comments on Slashdot.

You didn't answer his objection: "isn't that what editors are for?" He wasn't talking about Emacs, he was talking about Taco. If editors don't edit, what exactly do they do?

Re:*sigh*

[Chasuk]

I do find it painful. Not in a literal sense, of course, but I cringe in the same way that I might if I were addressed by a drunk standing too close to me, reeking of halitosis, with snot dripping from his mustache.

No, I'm not trolling, this isn't flamebait, and I'm not being elitist. I'm just pointing out that some readers do experience a visceral response to poor spelling and grammar.

Grammar doesn't have to be perfect, or I would never post. Spelling is a nearly impossible chore for some: it is acceptable, for them, if dyslexia or a similar disorder is their excuse. However, poor spelling and grammar, if due to laziness or indifference, does offend me.

Further, from experience, I have seldom read a thought worth reading that was contained within a syntactical nightmare.

I've been reading Slashdot for years, and I have noticed that the literacy levels - and levels of intelligibility and thoughtfulness - have declined as it has become a destination visited by more people.

Has anyone else noticed this deterioration? It has gotten so bad that I'm now reading www.kuo5hin.org more often than Slashdot.

Now that this message has rambled entirely off-topic, can anyone recommend intelligent, literate forums with a high volume of traffic? They _don't_ have to be tech-oriented.

All suggestions welcome.

Re:*sigh*

[tapiwa]

one Xenon is bad spelling....

two is gross negligence on the part of the editors.

Re:*sigh*

[skamma]

uhh... maybe there's an r missing.... remember the saying about who shall throw the first stones?

Re:*sigh*

[ryanvm]

Wow - that has to be the most pathetic rant I've ever witnessed. I hope you find your other forum, because we certainly don't need elitist, grammar nazis like you trolling around here.

Re:*sigh*

[Citizen of Earth]

Grammar nazi mode activated...

They _don't_ have to be tech-oriented.

You shouldn't use the word "have" in this way. "Have" is a verb that means to possess something, so you are saying "They _don't_ possess to be tech-oriented". Instead, say "they don't *need* to be tech-oriented" or "they aren't required to be tech-oriented". (Yes, I put my periods outside of literal quotes; what's your problem, buddy!)

And while I'm at it, it also bugs me the way that people say "different than". It's "different from"! The former is like saying "compared than", which doesn't make any sense.

Re:*sigh*

[Citizen of Earth]

Grammar nazi mode activated...

Er, make that "Grammar-nazi mode activated".

Re:*sigh*

[Anonvmous Coward]

Or the result of a Spell Checker...

Re:*sigh*

[dogstone]

eh.. make that kuro5hin

Re:*sigh*

[orange7]

You should have capitalised Nazi, too.

A.

Re:*sigh*

[ottffssent]

While we're being petty, you might check a dictionary to back yourself up. A nice thick one, since the definition of "have" won't support you, so the book might as well. Have, in the sense the above poster was using it, is an accessory or helper verb.

Don't you mean...

[nemesisj]

Dual Xeon ?

Re:Don't you mean...

[delta407]

From the article:

The machines are rack-mounted dual Xeon-processor systems operating at 2.2GHz with four gigabytes of memory each. The 950 processors will be added to 350 existing 1GHz Pentium 3 systems as part of a dedicated "render wall" comprising 22 racks.

Now, see, if they could get xenon doing anything useful in a CPU, I would be impressed.

I want a dual Neon machine...

[fmaxwell]

Give the the warm orange glow of dual neon machines any day.

Slashdot Success Stories

[jjohnson]

Wow. It could only be more politically correct if the chips were Athlon MPs.

Re:Slashdot Success Stories

[Alan Partridge]

I'm not sure that's fair, AMD can compete just fine with the 2200 Xeons. It's the 2530 P4s that are giving it headaches.

just wondering...

[Savatte]

could they also claim that it is the most powerful processing site in the eastern hemisphere?

Re:just wondering...

[Viking Coder]

"hemisphere". Defined using a 2d map. Right. Where'd you come up with that piece of twisted logic?

According to those idiots at the USGS, "The northern hemisphere has positive latitudes. The southern hemisphere has negative latitudes. Longitudes are perpendicular to the Equator are range from -180 degrees (International Date Line) to +179.99999... degrees (just west of the International Date Line). Under this convention -- the western hemisphere has negative longitudes and the eastern hemisphere has positive longitudes."

Yeah. All Americans are dumb. Good call.

Re:just wondering...

[Myco]

I don't think so. Isn't that big new weather-prediction site in Japan? I would imagine that's bigger, though I haven't checked the numbers.

Re:just wondering...

[Mad Marlin]

Actually it is the British who decided where 0 degrees longitude was, and thereby the Eastern/Western hemispheres. Why do you think it runs through Greenwich Englind? If an American had first invented the Naval Chronometer instead of Harrison, 0 degrees longitude would run through Washington D.C. or New York City, and not the British Royal Naval Observatory.

Re:just wondering...

[WIAKywbfatw]

Actually it is the British who decided where 0 degrees longitude was, and thereby the Eastern/Western hemispheres. Why do you think it runs through Greenwich Englind? If an American had first invented the Naval Chronometer instead of Harrison, 0 degrees longitude would run through Washington D.C. or New York City, and not the British Royal Naval Observatory.

You couldn't be more wrong if you tried. You could try, but you'd fail.

Yes, the Prime Meridian (0 0' 0"), is situated at the Royal Observatory and Planetarium (that's its correct name), but its adoption as the international standard has nothing to do with the invention of the "naval chronometer" by John Harrison in 1735.

I'll let the Observatory's own pages tell the story:

Until the nineteenth century, each country tended to keep its own zero meridian. The Prime Meridian for the world was adopted in 1884, at the International Meridian Conference in Washington DC. Twenty-five countries were represented and voted to adopt the Meridian at Greenwich as the Prime Meridian for the world. It was also agreed that longitude would be measured in two directions from the Prime Meridian, 'east longitude being plus and west longitude being minus.'

In 1960, shortly after the transfer of the Royal Greenwich Observatory to Herstmonceux (and, later, Cambridge), Flamsteed House was transferred to the National Maritime Museum's care and over the next ten years the remaining buildings on the site were also transferred. Here the collections of scientific, especially astronomical, instruments has continued to grow. Following the closure of the RGO at Cambridge in October 1998, the site is now known as the Royal Observatory Greenwich.

So, it was an internationally agreed meridian, not an imperically imposed one.

One of the main reasons why Greewich was chosen over its rivals (including the French alternative of a meridian running through the centre of the Eiffel Tower) was that Greenwich time was widely used worldwide by many industries.

Most notably, it was the standard time by which all US railroads ran their timetables. Rather than adopting yet another time system, the railroad operators preferred sticking to their existing standard for obvious reasons (familiarity and cost).

Perhaps, next time, you'll check the historical facts before you start giving history lessons.

Re:just wondering...

[hdparm]

Read carefully - parent's post is a reply to the question about Eastern hemisphere, where Japan aparently is and where few of the most powerfull machines in the world are located.

Thus, moron qualification is more appropriate if assigned to you.

Re:just wondering...

[hdparm]

Or to me, if talking about HTML tags...

Re:just wondering...

[roofingfelt]

Twenty-five countries were represented and voted to adopt the Meridian at Greenwich as the Prime Meridian for the world.

Just wondering if the majority of those twenty-five countries were owned by the British at that time ;-)

Re:just wondering...

[Mad Marlin]

You couldn't be more wrong if you tried. You could try, but you'd fail.

My, aren't we hostile!

Yes, the Prime Meridian (0 0' 0") ...

What, one zero wasn't enough for you?

... situated at the Royal Observatory and Planetarium (that's its correct name) ...

Sorry, your magical Google powers failed you this time. The Prime Meridian runs right through the Old Royal Naval Observatory. The buildings have been inactive since 1998 and under the control of the National Maritime Museum.

... but its adoption as the international standard has nothing to do with the invention of the "naval chronometer" by John Harrison in 1735.

It had everything to do with Harrison's naval chronometer. King Charles II founded the Royal Observatory in 1675 to solve the problem of finding longitude at sea. [cite] Harrison's chronometer was the first instrument which managed this, and for quite a while, the British had exclusive use of it. This allowed them to produce vastly more accurate nautical charts than everyone else. Since they were British charts, they used the British Prime Meridian. Since they were vastly more accurate than all other charts at the time, any sea navigator who could get his hands on them would have used them instead of their domestic naval charts, and very quickly nearly all naval charts in use put the prime meridian through the British Royal Naval Observatory.

I'll let the Observatory's own pages tell the story: ... [large block quote] ...

By the time of the conference, the British Prime Meridian already was The Prime Meridian in all but name, and had been for over a century.

So, it was an internationally agreed meridian, not an imperically imposed one.

Incorrect, it was an empirically determined meridian that eventually the rest of the political world accepted.

... The Prime Meridian for the world was adopted in 1884 ... One of the main reasons why Greewich was chosen over its rivals (including the French alternative of a meridian running through the centre of the Eiffel Tower) ...

Impossible. Construction of the Eiffel Tower did not even start until 1887, so how could it be used as a landmark for a prime meridian in 1884?

Perhaps, next time, you'll check the historical facts before you start giving history lessons.

Perhaps next time, you will realize the ability to type in Prime Meridian into a search engine does not make up for a complete and total lack of understanding about the subject.

I bet everybody...

[Anonymous Coward]

...will correct you on "Xenon" while completely missing "behing".

Typical Slashdot.

Re:I bet everybody...

[showboat]

What about "Congrats the guys"? Isn't it either congrats TO the guys or conratulate (no 's') the guys?

100Gbps?

[willith]

"The servers run in parallel and major jobs are broken down for each server. It is networked together with 100Gbps ethernet and Foundry networking switches...."

A hundred gigabits per second? Dude! Sign me the hell up!

Re:100Gbps?

[sharkey]

A hundred gigabits per second?

It needs to be fast. Those Xenon servers are a real gas.

Re:100Gbps?

[en4ca]

The article actually says "It is networked together with 100Mbps ethernet and Foundry networking switches."

Re:100Gbps?

[freakmaster]

They must have fixed it. we're not that stupid.

About those Xenon wisecracks...

[Devil's BSD]

You could use xenon to power a quantum computer. Dual xenon = 2 xenon atoms = 2 qubits, which could be roughly 64 bits, or the processing potential of a potato.

Re:About those Xenon wisecracks...

[AA0]

why do you think they bought 220 of them?
They can now have several bags of potato processing.

these guys aren't stupid!

Do I see some movement ...

[Nostrada]

... in some of the decentralized computing efforts, coming from the southern hemisphere?

Team LotR strikes at Distributed Folding, ECCP, Folding@Home, Genome@Home, OGR (24 and 25), RC5, Sengent D2OL, SETI, UD ...

Re:Do I see some movement ...

[H3XA]

Just as well it is in New Zealand and not Australia, otherwise Hollywood unions would boycott the crap out of the render studio...... though this may happen yet, the NZ dollar is weaker than the Aussie dollar when compared to the US dollar, so the incentive is still there.

- HeXa

Re:Do I see some movement ...

[phriedom]

What Union? Is there a Movie Producers Union?

Re:Do I see some movement ...

[KewlPC]

There are, as far as I know, unions for VFX people. I don't have any hard facts to back this up, but I remember seeing a jobs page at the ILM website months and months ago that described some of the positions as union jobs.

Re:Do I see some movement ...

[phriedom]

so the artists at ILM might refuse to work on your movie if you do your rendering at a non-union shop in Australia or New Zealand? So the non-union shop wins ALL the VFX work, (or none of it). I'm not seeing a down side for the movie producer or the non-union shop here, if they can get the work done. The only danger I see is if the actor's union does a sympathy boycott and all the actors refuse to work on movies that aren't 100% union. I suppose that is a possibility, but not a likelyhood.

Re:Do I see some movement ...

[KewlPC]

The VFX unions may boycott the shop. Weta hires people from all over the world, USA included. This means that people in one of the US VFX unions would be unable to work at Weta unless they wanted to leave the union. Once you're out of the union, it would be tough to get back in, and a VFX shop that only hires union people (like ILM) wouldn't hire you until the union lets you back in.

Most VFX artists don't stay at the same studio for long, so this can be a problem for them.

The whole bit about Weta not being in Australia is that a lot of film work is migrating over there. No unions AFAIK, so much of the cost of shooting in Hollywood goes away. And directors like it because they're further from the studios, which means the studios don't bug the director and other creative people as much.

Imagine...

[Quixote]

... a Beowulf cluster of.. waitaminnit. It probably *is* a Beowulf cluster. :-/
No, I haven't read the article. Is that necessary?

So much power...

[Toasty16]

And yet they still can't make Frodo look like a guy.

Re:So much power...

[waspleg]

he's supposed to look like a child (hence halfling) not a big burly broadsword wielding man..

a side note: do you like movies about gladiators?

Re:So much power...

[juhaz]

Halflings are not supposed to look like kids, they are small, humanoid fantasy race and they have kids as well as adults. What comes to their looks, they are supposed to look a lot smaller, that's true (and hence the name), but their face, and other features associated to age are not like those of kids, but about equal to those of human of same age (in relation to average lifetime, if that differs).

Re:So much power...

[Happy Monkey]

True, but Frodo is 33, which translates to about 18 in human terms. The actor is in his twenties, so all is well.

Re:So much power...

[falzer]

Frodo? I have absolutely no idea who this person is. Frodo who? Am I supposed to have heard of him? I'm sorry, but I haven't.

I'm guessing it's because I don't read books. In fact, I don't even own one.

Does anyone know how to compare these?

[NeMon'ess]

Since there are all kinds of benchmarks, which would be most appropriate here? I'm thinking heavy fpu performance. Most gaming sites only compare single processor performance. Can anyone dig up a benchmark of a dual P4 of 2.2GHz or thereabouts? Then compare to the P3s. I'm guessing this more than doubled their capacity.

Re:Does anyone know how to compare these?

[kawaichan]

All from Gamepc but here they are

Pentium 4 Xeon Multi-Processor Under Linux
Prestonia Xeon 2.0 GHz vs. Athlon MP 1900+

Re:Does anyone know how to compare these?

[Kether]

the standard benchmark of supercomputers is HPL.

checkout top500.org for, well, the top 500 rankings.

Is one day too much to ask....

[Rebel Patriot]

...without a front-page type or two? Xenon machines, FotR... I understand typos happen everywhere, but when you're putting out a product like slashdot.org, even asking people for money for ad-free browsing, you would think you could expect some basic editing of the stories. Is it that much to ask to have some one read over the story once or twice before it's posted?

Out of 10 or 12 stories a day, there are always one or two with bad grammar and/or spelling. This definately takes away from any sense of professionalism slashdot.org presents on itself. Consider this editors, everyday this website is your best resume`. You wouldn't submit a resume` that has grammatical errors on it, would you?

Re:Is one day too much to ask....

[zerofunk]

Yeah, but Fellowship of the Ring has already been made. So the new machines added to the render farm shouldn't really apply to its advertisement.

Re:Is one day too much to ask....

[recursiv]

Nice spell job on "definately"

Re:Is one day too much to ask....

[danap611]

um, you spelled "definitely" wrong.

Im still trying to sort through the subject....

[night_flyer]

Weta Digital's Render Farm Upgrade

is it the "Render Farm" of Weta Digital that is being upgraded?

My head hurts...

distributed.net

[Prizm]

Any chance they could use those extra cycles for cracking RC5 blocks? Give the slashdot.org team a run for their money, eh?

Make better movies...

[Hollinger]

I wouldn't say make more movies, I'd say make better movies.

Re:Make better movies...

[Em Emalb]

using the infinite monkeys with infinite word-processors theory, I'd have to say that make more movies is the way to go. Would have a much better chance of a monkey pounding out a better movie than the throw a script together crap we see these days.

Great marketing idea!

[DearSlashdot]

They should use that in the FotR ad campaign... 'Rendered using the most powerful processing site in the southern hemisphere.'

Sure, who cares about plot or character development? We've got a server farm!

Who submitted this? George Lucas?

Re:Great marketing idea!

[Anonvmous Coward]

"Sure, who cares about plot or character development? We've got a server farm!"

Normally I'd agree with you, but since it's based on a book all that stuff's accounted for. At least we know that they have the CPU horsepower to render out some wild stuff.

Personally, though, I'd rather know that they hired super-talented animators. Them'z worth heaps more than the most powerful render farm.

Re:Great marketing idea!

[phriedom]

I agree completely, and I think that judging from what we saw in FotR, they already have super-talented animators. Now I think they are just needing to remove some of the constraints on those artists. I'm guessing that the giant battles taking place in the next two movies are justifying the increase in computing power. I think we may really get the best of all possible movies here.

seriously though

[freakmaster]

that is a typo. to some it's obvious, but to some it's not.

Re:seriously though

[Oculus Habent]

Maybe they use channel bonding? ;)

Re:seriously though

[freakmaster]

they very well might. or maybe they use something like the klat2 supercomputer but they're still not getting 100 gigabits. 66mhz 64 bit pci (if they've got it) theoretical max is 4 gigabits. I believe that fast RAM throughput is on the same order of magnitude. Not to mention how many nic's you'd need to get 100 gigabits.

CPU vs data transmission speeds.

[Dark Lord Seth]

I wonder, with todays CPUs becoming more and more powerful, won't the actual internal architecture and the standard data transmission system (copper or gold or whatever those conduits are made of) end up outdated and not being able to cope with the CPU's speed? Maybe this applies to other pieces of hardware as well? HDs not being able to feed procs the data they require fast enough or RAM suffering from aforementioned problem...

How do they solve these kind of issues anyways, especially in extremely large computer arrays like this one mentioned here but also in supercomputers or maybe even in our home PCs which are getting faster and faster as well every few months...

Re:CPU vs data transmission speeds.

[Qrlx]

Maybe you haven't noticed, but bus speeds have increased since you bought that Pentium 75 system. Though not as much as cpu speed, because that's historically been the focus of the, uh, personal computer. Who cares about optimizing network transactions on a PC? They were built to get away from mainframes, remember? Well, that was true 20 years ago and the paradigm has stuck for longer than it should have.

Even so, Consumer hard drives can now claim ATA-133 speeds, that's probably an order of magnitude faster than the 1.2 GB drives from five years ago. And SerialATA is coming. On the server side, I think U320 SCSI is out now. SCSI started at 5, now it's at 320. THat's like 64 times faster.

RAM has kept up, too. The first DIMMS were 66MHz, now you can get effectively 400MHZ DDR, or faster than that if you want soon-to-be-out-of-business RAMBUS.

Heck they invented the AGP port so we could play games, and that's at 4X now, with 8X on the horizon and some really bigtime advances in GPU power in just the past two years.

None of these have seen the speed increases of the CPU, but they are moving along at a nice clip. The PCI bus is maybe the weakest link here, but it's gotten better.

I think there's a lot of room for growth left in the current physical materials. I keep hearing 15 years until we hit the quantum barrier in CPUs, if we keep up with Moore's Law. There was a great article not so long ago about hard drives, and how they are basically doubling in areal storage density every year. In ten years, you can get a 120 Terabyte drive. Only one problem: What the hell would you put on it to fill it up?

Kinda like the predicament they find with broadband. There's nothing else to do with all that bandwidth than download mp3s and pr0n and warez. Oops.

Re:CPU vs data transmission speeds.

[eyepeepackets]

As the other reply says, plus:

Magnetic RAM is coming soon (MRAM) and holographic memory storage too. Granted, bus speed is still a pain, but if you put enough RAM in the machine and use RAM disks, you can get some serious transfer speeds.

What I want is multiple CPUs per CPU. Yes, I know that sounds strange. Maybe those FPGA thingys will get faster and cheaper soon.

Re:CPU vs data transmission speeds.

[_LFTL_]

In ten years, you can get a 120 Terabyte drive. Only one problem: What the hell would you put on it to fill it up? Kinda like the predicament they find with broadband. There's nothing else to do with all that bandwidth than download mp3s and pr0n and warez. Oops.

I began pondering exactly how much "pr0n" 120 Terabytes would be. From the bit of encoding I've done you can get a pretty good movie down to about 512 megs (rounding to simplify my atrocious arithmetic). So that's about 4 hours per gig or 4048 hours pers terabyte. So 120 terabytes comes out to around 480000 hours or 56 years worth of pr0n.

Just in case you were wondering.

Re:CPU vs data transmission speeds.

[zeno_2]

400Mhz DDR also doesn't exist yet, you are thinking of 333Mhz DDR. And though RIMMS have a higher clock speed, they use a narrower channel (4-bits?). You sound like some OCing game phreak who gets information from tomshardware.com.

Go ahead and check pricewatch.com, you can buy 433Mhz DDR memory there. The new Nforce2 motherboards from Nvidia are going to support this faster ram.

Re:CPU vs data transmission speeds.

[psamuels]

What I want is multiple CPUs per CPU. Yes, I know that sounds strange.

Done, see the IBM Power4 (basically a 64-bit PowerPC with some extensions, but not peer-compatible with the G3/G4/G5 line from Mot/Apple) which I believe has 2 or 4 logical CPUs per die. The little boys are moving this way too - ever since the Pentium or so, Intel and competitors have been putting multiple pipelines and execution units in a single CPU, to be scheduled as needed by a component known as the "instruction scheduler", which takes responsibility for making sure any parallelism has no side effects - that it behaves as though completely serialised, only faster. The Intel Xenon^WXeon does one better with a feature they call "hyperthreading", whereby the instruction scheduler becomes an actual multi-CPU scheduler, portraying to the OS two logical CPUs per physical CPU, in order to make better use of the redundant execution units.

Re:CPU vs data transmission speeds.

[ianaverage]

A good place to read up on multiprocessor systems (that means both in a single box as well as those connected through a network) would be in Computer Organization and Design by Hennessy and Patterson (chapter 9). You can buy it here.

It may be expensive...but it is a great book for learning about the basics of architecture. Pretty much all schools use this book in their intro to architecture courses. It's got all kinds of info about some of the bottlenecks and how they are being dealt with.

Re:CPU vs data transmission speeds.

[Saeger]

I keep hearing 15 years until we hit the quantum barrier in CPUs, if we keep up with Moore's Law.

I wonder if any of those predictions ever take the 3rd dimension into account? Or did they just assume circuits would be flat forever, instead of "growing" them from the bottom up. Parallelism never seems to get much credit for pushing the barrier either...

Even then, a super-dense cube/sphere cluster faces the light limit... but then we have "spooky" electron-wave-computing to look forward to, right.

--

Re:CPU vs data transmission speeds.

[Qrlx]

Hey, if you have any extras I could use them in my PowerBase 180.

I'm not an idiot, but I play one on Slashdot.

Re:CPU vs data transmission speeds.

[CoAX]

"In ten years, you can get a 120 Terabyte drive. Only one problem: What the hell would you put on it to fill it up?"

Well what did you say when you bought this 1.2GB hard drive 5 years ago ? Wasn't it a bit like "What the heck am I gonna do with all this space" ?
Hard drive space is increasing because we need it. Well this part is like the old chicken-or-egg-first question...

I don't know about that...

[Erpo]

How about XPs modded into MPs?

Hmmm

[ill_conditioned]

$5 bucks says they just want be able to play Doom III at full detail ;)

2qb == 64b ?

[Kz]

How do you count qubits?

I'm pretty sure that there's no direct equivalence formula between qubits and bits...

Re:2qb == 64b ?

[ArsonPerBuilding]

Actually, iirc 2 qbits is the equivilent to 4 bits, as qbits can be 1 and 0 at the same time. Two regular bits = 2(bits)^1(#of states a bit can be); however with qbits = 2(bits)^2(#states).

Re:2qb == 64b ?

[crywolf]

And Noah said, "God...what's a qubit?"

Re:2qb == 64b ?

[Fyndlorn]

There isn't...

Just think of it in terms of hilbert spaces (or just plain vector spaces). A qubit spans a 2 dimentional hilbert space. A (normalized) state on that space could be written

|S>=a1|0>+a2|1>

just think of |> as a vector, where a1 and a2 are ANY complex numbers such that |a1|^2+|a2|^2=1

for two qubits then you just have a 4 state space

|S>=a1|00>+a2|01>+...

for more info check out:
http://search.barnesandnoble.com/textbooks/b ooksea rch/isbnInquiry.asp?userid=66NT518KIO&isbn=0521635 039

Re:2qb == 64b ?

[sharkey]

"Am I on Candid Camera?"

Who gives a monkey's chuff?

[Beatlebum]

>> They should use that in the FotR ad campaign... 'Rendered using the most powerful processing site in the southern hemisphere'

So that morons like Taco can point this out to their long-suffering girlfriends?

Who gives a fuck. Seriously dude, get a hold of youself and try not to be a weiner all your life.

Re:Who gives a monkey's chuff?

[wadetemp]

But... but... but I...

Oh yeah, you're right.

Re:Who gives a monkey's chuff?

[Flakeloaf]

Still no cure for cancer, but man do them hobbits move smoooothly! Look at the hair on his face! Kinda brings a tear to your eye don't it Uncle Bob?

Huh? Oh, you're crying because your morphine drip doesn't numb the pain. Never mind then.

Re:Who gives a monkey's chuff?

[A.Soze]

A weiner? The guy runs Slashdot, News For Nerds, for crying out loud!
And besides, she's not a long suffering girlfriend. She's a long-suffering Fiancee .

Re:Who gives a monkey's chuff?

[Dr. Smooth]

This is the funniest goddamn post I've ever read on Slashdot! Way to go, Beatlebum!

Re:Who gives a monkey's chuff?

[Sabalon]

Just cause he runs /. doesn't mean he's not a weiner. Besides...I thought they got married, moving her from girlfriend to fiancee to a finance :)

Cost?

[Quixote]

The cost of the 476 machines is pegged at between $3M and $4M. Assuming $3.5M (midpoint), it works out to $7352 per machine; assuming NZDs, that comes to about USD 3564 per machine. Since no HDD is mentioned, they most probably do no have any.

Assuming all the assumptions above were correct, how does the cost compare to something comparable stateside? Of course, I'm ignoring the "100Gbps" network(!) and the Foundry switches, but I don't think they'll add more than a couple of hundred bucks per machine _at most_.

Re:Cost?

[Anonymous Coward]

Between 3 and 4M could include housing, space, support of various types, and whatever they payed for the logic of the switches. Further, the figure was a guess by outside sources.

I'd say we don't have much to really go on. Esp. when the article says:

"Weta has been quiet on its use of technology after a deal with IBM this year was misreported around the world at around US$10 million. Sources now suggest it was more like a tenth of that price. "

Others have tried a price game and were not very precise :)

Re:Cost?

[KewlPC]

Of course they'll have hard disks. It makes no sense not to. Having a RAM disk would be stupid, because you don't pay through the nose for dual XEON CPUs (waaay more expensive that normal P4 CPUs) and 4GB of memory only to try and save $150 by not throwing in a hard disk. And I'm sure that those huge battle scenes need every last bit of RAM the machine has.

And remember, these aren't your normal desktop PCs. Certain parts would be more expensive because they have to use parts specifically designed for use in 1U systems.

Obligatory jokes

[(void*)]

• Is it the most powerful render farm in all of Middle Earth?
• Is this the Matrix of Middle Earth? I've always wondered about that Agent Guy.
• Imagine a beowulf cluster of these ...

Ad campaign

[breon.halling]

They should use that in the FotR ad campaign... 'Rendered using the most powerful processing site in the southern hemisphere'

Pshaw! That'll only appeal to geeks! Oh, wait a minute...

Re:Ad campaign

[Alric]

For the record, I appreciated the dry humour of your post, and I would mod it up if I could.

Peace.

Rules for flaming based on spelling/grammar

[hayden]

Make damn sure you don't make the same mistakes.

...without a front-page type or two?

"typo" maybe?

Is it that much to ask ...

"Is that too much to ask ..." or possibly "Is it too much to ask ..." depending on what you wanted to do with the rest of the sentence.

... of professionalism slashdot.org presents on itself.

Slashdot and professionalim in the same sentence has to be some sort of error.

You wouldn't submit a resume` that has grammatical errors on it, would you?

Surely you mean "in it".

My point? Enough with the bitching about the spelling/grammar. Most of people here aren't any better and of the remainder most don't care.

Re:Rules for flaming based on spelling/grammar

[WIAKywbfatw]

My point? Enough with the bitching about the spelling/grammar. Most of people here aren't any better and of the remainder most don't care.

Surely you meant one of the following:

1. Most of people here aren't any better and, of the remainder, most don't care.

2. Most of people here aren't any better, and most of the remainder don't care.

Hey, even grammar nazis need grammar nazis.

Re:Rules for flaming based on spelling/grammar

[arvindn]

You forgot the most important rule:

When pointing out incorrect grammar, you must write "What you say?!" :-)

Re:Rules for flaming based on spelling/grammar

[itsnotme]

... of professionalism slashdot.org presents on itself.

Slashdot and professionalim in the same sentence has to be some sort of error.

No no no.. thats just called an oxymoron :-)

Re:Rules for flaming based on spelling/grammar

[maxume]

No, it is fine as it is. A comma could be inserted after remainder, but there is certainly no need for one after and.

with that much power...

[kishkumen]

I bet they get killer frame-rates!!

Re:with that much power...

[Oculus Habent]

With the raw graphics processing power of the PlayStation 2 and the availability of PS2/Linux, I wonder if they have any plan to add 'em in...

That Threw me too...

[josquint]

but i figured out.. Fellowship of the Ring

Re:That Threw me too...

[psamuels]

but i figured out.. Fellowship of the Ring

So you're saying these machines are so fast they are rendering the movie in time for me to have seen it several months ago? Xenon processors must use faster-than-light conduits of some sort. (:

I think it more likely that these machines are being used for The Two Towers, and possibly Return of the King, though who knows - they might be used a little in perfecting the extra 30 minutes of FotR that haven't been released yet.

Re:That Threw me too...

[daeley]

Dude, you know it's actually Fellowship of the Ring II: The II Towers, right? ;)

Re:That Threw me too...

[daeley]

Note the emoticon. :)

Re:That Threw me too...

[brunson]

No, it's The Lord of the Rings: The Two Towers.

Bang for the buck

[janolder]

I wonder if these guys are actually getting the most bang for the buck. Sure, they are buying the fastest machines, but I sure wonder if a cluster of 300 Pentium 4 2.0 GHz or even Athlon 1900+ wouldn't be faster. According to mwave, the Athlon MP 1900+ currently sells for $192, while the P4 Xeon 2.2 sells for $304. Everything else being the same, that's $100 per box saved.

Assuming a base platform cost (without processor) of $400 for MoBo, memory etc., the P4 Xeon would have to be 17% faster than the Athlon to justify the premium. According to the benchmarks on Tom's Hardware, Intel would have a hard time attaining that.

Jan

Re:Bang for the buck

[RedWizzard]

Assuming a base platform cost (without processor) of $400 for MoBo, memory etc., the P4 Xeon would have to be 17% faster than the Athlon to justify the premium. According to the benchmarks on Tom's Hardware, Intel would have a hard time attaining that. You may be right but those benchmarks don't support your case much because they don't include any P4 Xeons.

Re:Bang for the buck

[janolder]

But the Xeon is very similar to the standard P4, with the exception of perhaps cache. I don't think that'll make that much of a difference in a raytracing application.

Re:Bang for the buck

[sirsnork]

What you're forgetting is that it isn't a question of money, it's a question of space, as is any farm of this size. You have to have the space to hold 22 racks plus everything else needed. Why buy Athlonsor P4's if you have to buy 2 more racks to get the same power and have to find somewhere to put those extra 2 racks?

Re:Bang for the buck

[psamuels]

I wonder if these guys are actually getting the most bang for the buck. Sure, they are buying the fastest machines, but I sure wonder if a cluster of 300 Pentium 4 2.0 GHz or even Athlon 1900+ wouldn't be faster.

I agree with you, but to play Devil's Advocate, there are sometimes reasons you want a fast CPU, not just a fast cluster. Our SGI sales guy often tries to make this point, for the obvious reasons, but it's true.

If you are rendering out a large number of frames, you want the most possible aggregate CPU power, because rendering is extremely parallelisable (each frame stands alone). So 50 Athlons is better than 40 Xeons. But if you are just rendering out a 5- or 10-frame test sequence, and the wall is not already overloaded - then you want the 40 Xeons instead, since each one can take a frame and you'll get your result back faster.

There is also the issue of network bandwidth. In some cases you can benefit quite a bit by having fast boxes with as many CPUs per box as possible. This is because there is a non-trivial network burden in sending out the job to be rendered, along with all its textures, images, etc. This can be mitigated by multicasting and caching - but I don't know to what extent Renderman does this - but I know if you don't design it right, it can really slow down your jobs. (We evaluated one render distribution system that relied on Windows SMB file sharing for its I/O. Sending a 200-MB job to each of 10 render crunchers pretty much killed it.)

Re:Bang for the buck

[robosmurf]

According to the article, each server has 4GB of RAM. Considering the model detail, they may well need this.

Memory may be cheap at the moment, but the base cost for the platform (including ram, motherboard, case, PSU etc.) is going to be WAY more than $400.

Given this cost, you might as well put the fastest processor you can get into it.

I wanna be...

[Edward Teach]

on THEIR SETI@home team!

Re:I wanna be...

[RedWizzard]

I wanna be on THEIR SETI@home team!

You mean this one. It doesn't seem to have been active since late '99, probably about when they started heavy work on FotR.

/. effect

[user32.ExitWindowsEx]

So, would this sort of a server farm be /.-effect-proof?

And please, please, please....

[orthogonal]

Donate any down-time to Folding@home.

Hmmm

[baldass_newbie]

I wonder what kind of monitor you'd get for that setup?

In the Southern Hemisphere

[judd]

"[superlative] in the southern hemisphere" is the standard appellation for anything that New Zealanders (or Australians) are proud of, but isn't actually that huge.

Eg: "New Zealand has the most DSL connections per head of population in the southern hemisphere", or "Australia boasts more camel-related accidents than any other country in the Southern Hemisphere".

Not for the movie....

[12ahead]

They used some insider knowledge to get the hardware specs for Doom IV and acted on some more insider dealer connections. Eat that Bush!

Interesting...

[mrmag00]

From the article:
The system allows artists to render textures, shading and resolution of scenes in an iterative process. The faster they can do that the better the pictures.

Now theres some interesting editor commentary. Since when does drawing somthing faster make it better? It might get it out a month earlier, but really... better pictures?

Re:Interesting...

[Mac Degger]

That's due to the 'old' addage "computer art is never finnished, only abandoned". So the less time it takes for the frames to render, the more time can be spent on improving the scenes (a polygon here, a better shader there can make all the difference).
And because they work to a deadline (they have a release date and a whole slew of marketing crap lined up to culminate on the release date), anything which shortens the project tasks on the end of the schedule will leave more time for the tasks before it.

It's so simple, you could've worked it out too :)

Re:Interesting...

[Eccles]

Since when does drawing somthing faster make it better? It might get it out a month earlier, but really... better pictures?

Yes, because they talk about an iterative process. As in, try it, see how it looks, improve it, try it again, repeat as necessary until it's the best you can make it.

Re:Interesting...

[CommieOverlord]

Probably because movies are also called "Motion Pictures" (hence the MP in the MPAA). People will often shorten motion picture to just picture.

Way kewl

[McFish]

Finally there's machine that could run WinXP with decent speed (well... atleast like Linux on p90), hmn.. now if only someone would donate it to me.

Make more movies?

[Milinar]

Maybe, maybe not. It's my impression that studios like this put tremendous amounts of capital into individual projects. They may very well not do another movie after the third LotR. Case in point: digital domain hired over 1000(!) animators to work on titanic - just imagine the amount of hardware they got. I could be wrong, but they haven't done a project nearly like that since.

Plus, with moore's law, those machines they bought won't be worth the electric bill in a few years.
-Milinar

Re:Make more movies?

[K8Fan]

Cameron was the most visible co-owner of Digital Domain, but he was actually a junior partner. WETA is, as far as I know, owned by Peter Jackson. He has a slate of films ready to roll. He doesn't have the dependence on "stars" like Arnie that Cameron has. He's on the opposite side of the world from Hollywood, and has produced a very profitable film. He has more freedom to make any film he likes than any other film-maker in years.

Peter, who started working on effects in his mother's kitchen will be making use of this new toy for quite some time.

And for another "wise" Xenon joke...

[vanza]

Talk about vaporware!

Everybody drool along with me...

[carambola5]

It is networked together with 100Gbps ethernet and Foundry networking switches.

*sigh* My puny Netgear 100Mbps switch is feeling quite inadequate right now.

what graphics? opengl?

[horster]

do these render farms use any graphics chips or are they done entirely in cpu?
the reason I ask is that linux does not have any high quality open source opengl that supports the latest graphics boards. nvidia is probably the best for opengl support but not opensource.

Re:what graphics? opengl?

[psamuels]

do these render farms use any graphics chips or are they done entirely in cpu?

Just the CPU. You want good floating point support [which is why Titanic used 500 dual-Alpha boxes], and memory bandwidth, and of course lots of Hz are always nice.

Theoretically a renderer could use a GPU for a coprocessor, but I believe render software is so complex that any GPU on the market today would be too specialised to be of much use. Hardware acceleration works for games because the game developer can tailor the rendering requirements / algorithms to the capabilities of the hardware (as abstracted by OpenGL and Direct3D, or via vendor extensions to same). Render software, OTOH, is at the mercy of what the modeler / animator / compositor wants, and they are not willing to settle for "whatever the hardware can do the fastest".

I wonder...

[2Bits]

... what happens to these fine machines when they are retired, or when the studio deems them too slow?

I sure can use one of these, gee, 4GB of RAM, that's more than the entire HD on my current machine.

Ok, don't tell me to go buy a new one. My machine, as old as it is, it running Linux just fine, thank you. Has been serving me for almost 5 years, and 3 or 3 more years, than I'll consider... hehe.

Yeah but...

[Jeffv323]

can it play GTA3 at more than 15 fps?

Imagine...

[swf]

a single one of these!!!!

In your face!

[nihilogos]

The previous "largest server farm in the Southern Hemisphere" was in Tonga where 7 486s could render a scene from Tribes 2 in less than 17 minutes.

So suck on that Tonga. And you never had the first dawn of the new millenium either.

Re:In your face!

[FunkyChild]

Or perhaps the Australian Partnership for Advanced Computing's AlphaServer cluster, ranked as the 42nd most powerful in the world...

Re:In your face!

[Alsee]

42nd most powerful in the world

The Southern Hemisphere - they've got half the planet yet they break out the Champaign when they break into the top-50 list in anything :)

-

Upgrading farms? Somebody call Blizzard...

[WIAKywbfatw]

Gee, that's one unit upgrade that Blizzard obviously forgot to include in Warcraft III.

A plough here, a grain store there, and voila, +50% to your food output. I'm surprised that nobody's thought of it before...

Obligatory quotes...

[Jester99]

Scotty: "I just can't do it captain! I don't have the power!"

"It's not the size of the render farm, it's how you use it."

And of course, let's all imagine a Beowulf cluster of... oh. wait. Right.

(Obligatory. Didn't say it was funny) :)

Umm, I think you might be confused

[angelkey]

Umm, graphic (or video) cards don't actually do any rendering. It's always the cpu. The only thing you need a high-end video card for is (pre)visualization when you are modelling. No sir, it's just that roomful of noble gas doing the work there.

Bottlenecks

[Oculus Habent]

There's always a bottleneck somewhere. It's been the drives, the bus, the expansion slots, the network, the ram...

Our biggest issue right now (in my mind, anyway) is physical media. Sure, ATA 133 is burstable to 133, but who actually thinks they'll get 133 for any length of time. If you Cause Win98 to hang at the End Task screen, the buffer on the drive might fill up and you could get maybe a half-second of 133.

The only way to get great speeds out of media is RAID striping or other such technologies.

Don't know if the cluster they have set up uses much (decentralized) storage, but the network has got to be huge.

Comment removed

[account_deleted]

Comment removed based on user account deletion

100Gbps ethernet

[dhammabum]

Accoring to the article, It is networked together with 100Gbps ethernet and Foundry networking switches. 100Mbit perhaps?

I looked on the Foundry website, 'only' 10Gbit.

I hate those exponential powers!

Dell PowerEdge 2650?

[Cedric]

Hmm, are these perhaps the new Dell PowerEdge 2650s? We just got one for our lab (dual Xeon 2.4 Ghz, 4GB DDR RAM). Mehopes that they know how loud these machines get, since one of them litterally sounds like a jet engine and is the loudest computer I have ever heard. Just search groups.google.com for "PowerEdge 2650 Loud Fan" to see what I mean.

nak

Re:Dell PowerEdge 2650?

[ScoobyDoo-heh]

They are clones would you believe, assembled in Christchurch a small village in New Zealand made up predominantly of farmers and sheep.

Re:Dell PowerEdge 2650?

[phoebus1553]

Your search - PowerEdge 2650 Loud Fan - did not match any documents

Re:Dell PowerEdge 2650?

[sirsnork]

Oi you.. settle down... ;) They are clones as you say, and they are noisy as the parent suggests, but they only get really bad when you have several hundred running at once ;)

Re:Dell PowerEdge 2650?

[Random Data]

Hmm, are these perhaps the new Dell PowerEdge 2650s? ... Just search groups.google.com for "PowerEdge 2650 Loud Fan"
Go to Dell's support site and download the A04 firmware for the Embedded remote access device. Use the 3rd set of instructions, the ones where you use a TFTP server (the other ones don't work). Adjust the alarm thresholds, and voila - fans spinning at half speed, Server ticking over nicely, and I can walk past the server room without thinking I've got tinnitus. Kind of a cute server once they shut up!

Great place to work

[Crosis]

I live near where Weta is situated, so once I graduate at the end of the year in Software Engineering (Bachelor of Engineering) I'll be trying there!!!

Re:Karma info loss

[SwedishChef]

I actually emailed them about this and they replied saying only that the change was "necessary" and that the karma is still there, just that no one can see it.

Yes, yes... we know it's off-topic but since no one sees the karma any more, who cares?

wow...

[M@T]

I've always wanted to use Blender's "Render daemon" button...

Seriously though, does anyone know what kind of modelling and render tools these guys are using ?

Re:And for another "wise" Xenon joke...

[the way, what're you]

What a gas!

how do render farms work

[brarrr]

I'm an extremely technical person, but in the world of materials engineering and such. I read /. for computer news and have for 2.5 years now. However, I'm only now starting to do any programming just out of sheer interest. So I don't know squat about this.

Do the render farms work simply as individual nodes rendering individual frames as doled out by some server, or do they work collectively. As in: are they done serially or in parallel? I don't mean this part as a joke, but is the beowulf cluster concept meant to be a single fast computer made of many?

Dumb questions brought on by enough misunderstanding.

Re:how do render farms work

[sirsnork]

The all work in parallel

Re:how do render farms work

[KewlPC]

They don't ALL work on the same frame at once. But it can be set up so that more than one machine works on the same frame: each renders a part of the same frame, then they are automatically pieced together by Alfred (the distributed rendering software that comes with Photorealistic RenderMan).

Re:how do render farms work

[once_had_a_puppy]

Alfred, while made by pixar comes seperate to Renderman (along with another hefty price tag) and basically tries to manage the queue of tasks hitting the renderwall. So while cpus on the wall do parts of an image, Alfred waits until these are done then tells another application that it can begin to assemble it all together. With Alfred you can theoretically use it to manage any programm and look after the interactions between any applications as well.. as long as its command line BTW

Re:how do render farms work

[KewlPC]

Oops. My bad. BMRT (Renderman-compliant global illumination renderer) comes with an app to do some basic distributed rendering, and that's what I (incorrectly) assumed Alfred was.

Oasis

[terry_dyne]

And after all
You're my renderwall....

Thank you Chicago -- Goodnight!

Re:wow...

[Anonymous Coward]

A blend of Maya, Softimage, Houdini, proprietary code, and Photorealistic Renderman

Hear about the plan to open source Xeon?

[Artifex]

Yah! It was gonna be called Freon!

Strangely, the idea got a very chilly reception, though everyone complained when it eventually got banned.

Re:Hear about the plan to open source Xeon?

[Techno_Jesus]

...And the CPU after that is going to be called the PEON!

*smack* don't be a moron.

-tj

Re:Take your own advice...

[hayden]

Professionalism methinks?

Damn it! I swear I copy and pasted that bit for that very reason. Must have X's/Slashcode/cosmic rays fault. :)

a cheap Mac Dual G4 1 Ghz is FASTER.

[Anonymous Coward]

a cheap Mac Dual G4 1 Ghz is FASTER.

Its $2799 and comes with a 300 dollar DVD-r burner as part of the price.

It gets over TWICE as many RC5 keys per second than the fastest dual AMD MBs... and per dollar, the XEON is way slower than a Mac at RC5.

Macs have a huge L3 cache and AMDs have no l3 cache so that might be one reason macs are twice as fast, plus a cold page of memory can be simultaneously write and read faster on a mac than a pc typically. That helps for some benchmarks perhaps.

but if you go to TOP500.org they maintain a ranked FRESH list of all the top 500 render/gfop cpu farms.

xeons are rare in the list and Powerpc boards dominate it. check out the list yourself.

Admittedly a better list would be megabyte per gigaflop... a conttest each fall determines that and typically dual Pentium 3 boards with three netwrok cards each win that award.... not this overpriced xeon garbage.

I like xoen for one thing... it has PCI-X now and has for over a year and no AMD has PCI-X shipping yet. Check Pricewatch.com yourself.

PCI-X will ship on macs soon and tahts all I care about.

Re:a cheap Mac Dual G4 1 Ghz is FASTER.

[array_one]

ummm....that's great and all, but there arent any Renderman compliant renderers which run on a Mac.

Re:a cheap Mac Dual G4 1 Ghz is FASTER.

[once_had_a_puppy]

ok well.. no.. but renderman used to be on mac about 8 years ago i think. then it shifted to intel and mips only. However, now that Maya is on osX and Apple has aquired Nothing Real (they create Shake, compositing package) and steve jobs' associations with Pixar, i wouldnt be surprised if we see a re-introduction of prman on the macintosh.

Re:a cheap Mac Dual G4 1 Ghz is FASTER.

[IamSorrow]

Not sure what your talking about here www.TOP500.com does not contain a single TRUE PowerPC CPU, the POWER3's used by IBM are not PowerPC Cpu's but the next Generation of PowerPC Cpu's , the conform to the specifications of the PowerPC Architecture but, you will not be able to take on othe these and place them in your Mac G4 As for the Dual Mac G4 at 1Ghz, it is actually 2 CPU's at 500MHz PLUS the L3 cache is not all that great, it is external, backside configuration L3 cache, up to 2MB of it. As for Intel and AMD on the www.TOP500.org list ther are a number of them "The first PC Cluster (#35 wth 825 GF/s) is based on AMD Athlons and installed at the IWR at the University of Heidelberg in Germany. " Plus the list goes on to explain "A total of 42 Intel based and 7 AMD based PC cluster are in the TOP500. 31 of these Intel based cluster are IBM Netfinity systems delivered by IBM. A substantial part of these are installed at industrial customers especially in the oil-industry....." Check the list out yourself at http://www.top500.org/lists/2002/06/trends.html

Someone has to say it

[Cyberop5]

Somebody has to say it:
Can you imagine a beowulf cluster of these?

the obvious

[DemiKnute]

In ten years, you can get a 120 Terabyte drive. Only one problem: What the hell would you put on it to fill it up?

MS Windows XP 8. Duh.

tremendous

[phriedom]

I wouldn't call $4 million NZ (or even US) to be a tremendous amount of capital, for a project like this. If they never use it for another project, they will still have gotten their money out of it. Sure, its a lot of money to me, but I bet they spent more than that on film stock.

But I think the other guy is right and Peter Jackson will make good use of this equipment and these people in the future.

Porting Software

[m_evanchik]

Everytime I read an article like this, it ticks me off.

If they can get this sort of application running on a Linux system, why can't dreamweaver and Adobe port their products to Linux.

Hell and damnation.

I mean it can't be that hard.

I guess the reason is because noone would buy the ports.

Is Linux ultimately only useful to the custom solution and server crowd. Will the professional and consumer desktop ever be tamed?

Re:Porting Software

[Dynedain]

Adobe made photoshop 3.1 for UNIX.....my university still has it if you are running an x-server and telnet in.

so....maybee they will do it again....granted they are one of the biggest supporters of the BSA and might be afraid of the 'hacker' community

Re:Porting Software

[m_evanchik]

But noone would require them to realease the source.

admittedly, they would have headaches porting binaries for the various distros.

Maybe this is the thinking behind United Linux: make it easier to distribute binaries, not source that requires compiling and gives up intellectual property.

Advertising pitch

[captainmoo]

They should use that in the FotR ad campaign... 'Rendered using the most powerful processing site in the southern hemisphere'

mm hmm, that would definitely sell all... the.... people who were going to see it anyway (geeks) =)

Slashdot Speeling stryks uhgin

[whizzmo]

Shouldn't the link be:

220 2.2GHz dual Xeon machines

not

220 2.2GHz dual Xenon machines ?


Not that I'd expect any sort of technical accuracy from this site. It's not like it's the most visited geek site on the 'net or anything...

Re:obviously

[KewlPC]

Except, AFAIK, you can't get Photorealistic RenderMan or Shake for FreeBSD. You could run the Linux emulation drivers under FreeBSD and then run PRMan or Shake, but if you're going to all the trouble, why not just use Linux?

Slashdot hypocrisy

[jbf]

RIAA/MPAA: bad
Geek MPAA movies (eg LOTR): good
Linux: good
Using Linux to further the MPAA: good

</karmaburn>

beowulf cluster?

[tapiwa]

imagine a beowulf cluster of these!!

sorry, couldn't resist

With So Much Processing Power...

[stixman]

...Maybe they can force southern-hemisphere toilets to flush counter-clockwise!!!

Expensive CPU? Not really.

[Chas]

The 2.2Ghz are $280. The P4 2.2 is $225. The CPU's aren't are obscenely priced as they used to be. What's obscenely priced in those systems are the motherboard and more to the point, the RAM. 4GB of RAM in a single system is disgustingly expensive.

• PC2100 DDR 1GByte sticks are running $319 (Costs more than the CPU!)
• PC800 RDRAM 1GB modules are running approximately 5x that ($1533 and can only find it from one vendor).

Granted, they may be using a motherboard with more than 4 DIMM/RIMM slots....

But even still. The prices don't skew THAT much for DDR (though they skew a lot more highly for RDRAM).

• PC2100 512MB: $100
• PC800 512MB: $155

It makes me cringe...

[Viceice]

... the thought of the most powerful processing site in the southern hemisphere is located in a country whose poeple think a PII(2) machine is soemthing to yell about.

Oh the shame...

Re:wow...

[Joff_NZ]

They use Maya for modelling, and renderman for rendering.

Re:Software they use...

[once_had_a_puppy]

yeh.. i love getting to work reading the email notifying everyone that overnight 400 processors and 4Tb of space has been added to the network... and if that will cause anyone any problems to contact support immediately...

LMAO

but youre right.. sure it might be great to get 200 CPUs working on your job, but thats 200 seperate machines trying to read/write from the same disk, to/from the same files, at the same time as fast as possible.. network performance anyone?

More large sites in New Zealand

[Curl E]

Massey university just announced that it is going to build a 128 node beowulf cluster (no imagination necessary!). Auckland University have recently got an IBM Regatta class machine.

Just a (quite impressive) stone's throw away from Weta is NIWA's Cray T3E
bash-2.03$ uname -a
sn6908 kupe 2.0.5.51 unicosmk CRAY T3E

I love running that uname :-)

Priorities

[PMuse]

Shouldn't we be disappointed that "the most powerful processing site in the Southern Hemisphere" is doing nothing more important than entertainment? Surely there is some real problem we could be solving with our collective resources!

Oh well, see you at the theatre on opening night -- I'll be at the 12:05 a.m. show.

Re:wow...

[once_had_a_puppy]

er.. not entirely true if you read the article and the one in cinescape you will see that all the crowd rendering is done by an in house renderer called Grunt

Re:twit

[once_had_a_puppy]

i think youve missed his/her ever so slight dig at XP.. ie. it would take a dual Xeon 2.2GHz w/ 4Gb RAM to run winXP as good as a P90 running linux.. sheesh. twit indeed.

Obligatory simpsons joke

[TheFranz]

mmmhhhh xenon

Imagine...

[natefanaro]

I bet they could find aliens in a day if they ran seti on all of those machines.

Finally ...

[nrowe]

And not before time. Before this purchase all of New Zealand's computing needs were met using a time shared Commodore 64. (I'm a Kiwi, I "can" make jokes like this.)

Garbage collector

[Anonymous Custard]

If anyone from the company is looking on /. trying to get some rid of their old almost-super computers to make way for the new super computers, I can probably manage to take a few off your hands.

Bart: 256? Oh and I'm stuck with this useless 252 :kicks it into an open fire:
Gamestation 252: Don't destroy me! I can still make you happy! To the maaaax!

Cool! I just bonded 10,000 10Mbps cards!

[Jogar the Barbarian]

Good thing I got them on sale!

Money isn't a problem, obviously...

[tcc]

Because if it would/could have been, they would probably have gone for a dual AMD system.

You pay a lot more per XEON CPU, you pay a bit more for RAM (and the bit more adds up pretty quickly with 200 machines with 4GB), you pay a LOT more for the motherboard. I've had do to a renderfarm with budget restrictions, I got twice as much machines for the same price if that intel-based setup (and almost twice as much power).

Stability? not any unusual issues that I wouldn't have got also with Intel-based stuff. I bought TYAN TIGER MPs, with dual athlon XP, and the hardware is top notch. The only issue I could see is if everything is heavily optimized for SSE2 and money isn't a problem, then it would make sense to grab P4 XEONs, but that's the only case I'd see (aside from marketting or direct rebates from intel for free exposure, etc etc) that could make someone take such a decision.

My 0.02 cents.