×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Top 500 Supercomputer List Released

Hemos posted more than 9 years ago | from the ibm-moves-ahead dept.

HP 167

sundling writes "The heavily anticipated Top 500 Supercomputer list has been released. There is a Sevenfold increase in AMD Opteron processors on the list. Two sections of an IBM prototype took spots in the top 10 and the famous Apple cluster didn't make the list, because it was out of service for hardware upgrades. When complete, the new IBM cluster is sure to take the top spot from the Earth Simulator."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

167 comments

Yeah! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9482991)

This post was brought to you by f.i.r.s.t.p.o.s.t., the program to frist post automatically. On your screen soon.

first post! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9482995)

fp!!

Why the fuss about Earth Simulator? (5, Funny)

Moblaster (521614) | more than 9 years ago | (#9483006)

IBM's new supercomputer will calculate "42" before the Japanese. America can feel good again.

Re:Why the fuss about Earth Simulator? (-1, Offtopic)

swiftstream (782211) | more than 9 years ago | (#9483088)

On the other hand, I bet the average time for a Japanese kid to calculate 42 (as in, 6 x 7) is much lower than an American kid...

Re:Why the fuss about Earth Simulator? (1)

ch-chuck (9622) | more than 9 years ago | (#9483136)

I have a theory that Deep Thought had a word size of 42 bits..... thus the answer to the great question, the meaning of everything is 42, just like humans anthropomorphize 'god' as an elderly grandparent with long white beard, etc.

Re:Why the fuss about Earth Simulator? (0, Offtopic)

The Original Yama (454111) | more than 9 years ago | (#9483214)

humans anthropomorphize 'god' as an elderly grandparent with long white beard, etc.
Don't you mean "Christians anthropomorphise 'god'..."?

Re:Why the fuss about Earth Simulator? (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9483301)

I can't stand it when Christians assume that everyone is (or should be) like themselves. Americans are well known for this too. It's just plain bigoted.

Re:Why the fuss about Earth Simulator? (1)

PD (9577) | more than 9 years ago | (#9483949)

Don't you mean Romans anthropomorphise god? The image that was described fits Jupiter to a tee, and was borrowed by others.

Or maybe it's the Greeks describing Zeus...

Jesus Christ! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9483557)

Enough with the Hitchhiker quotes already. They're getting as old as Monty Python quotes.

Get some new material, guys. Cripes, you'll be doing Laugh-In material next.

ECFA WANTS DEAD DOGS - AND A SUPERCOMPUTER (-1, Troll)

Anonymous Coward | more than 9 years ago | (#9483011)

This message brought to you by the National Association for Humane Action for Dogs and the Euthenasia for Canus Familourous Association. Gadgets For The Elimination Of Dogs is announcing a BRAND NEW product designed to exterminate canine pests of all sizes. Our economical K9Zap product retails for just $49.95 and takes only 2 seconds for a 60 lb dog. Our $5 bakers chocolate will kill up to 500 lbs of dog per package!

Gadgets For The Elimination Of Dogs is a division of ECFA (Euthenasia for Canus Familourous Association). The GFTEOD/ECFA would like you to do one thing - KILL A DOG. By KILLING A DOG, you will ELIMINATE one USELESSLY RESPIRATING animal from this planet. Are you TIRED of having your TAXES increased? Humane Societies cost our country over $100 million annually. By eliminating DOGS, this money can EDUCATE OUR KIDS. OVERPOPULATION of DOGS is RAPANT in this country. Take a stand! Help rid this INFESTATION. KILL A DOG TODAY!!!!

Have you ever stepped in DOG DOO-DOO [k9treat.com]

Are you MAD? [apa.org]

Do you KILL DOGS? [friendsofdogs.net]

Are you a MAD DOG KILLER? [k911emergencies.com]

If you answered "YES" to any of the above questions the ECFA (Euthenasia for Canus Familourous Association) is for you! Why change your sexual lifestyle or change your skin color to join an EVIL ORGANIZATION when you can simply INCREASE OUR SUPPLY OF O2! Did you know that DOGS turn BENEFICIAL O2 into CO2 simply to gain their energy to bark, drool, and howl? They ACTUALLY BOND their carbon TO OUR OXYGEN SUPPLY!!! One dog can waste 2 moles of O2 PER HOUR! This country has MANY UNWANTED, ABANDONED DOGS that WE ARE PAYING MONEY TO KEEP ALIVE. We are FEEDING them our food supply while making the homeless STARVE! By using a Dog Killing Gadget, a dog can be turned into beneficial food, helping us all. We let children go hungry yet feed our **UNWANTED** dogs like royalty.

Do you own a dog? Are you tired of its mess? Then get it euthanized. Euthanasia is a painless way for a dog to... terminate. However, it can be too expensive to buy these drugs for the LARGE NUMBER of DOGS in the HUMANE SOCIETIES. It is thus proposed that these dogs be turned into food for the homeless.

WANT TO SUPPORT THE ECFA? Simply form picket lines around your nearest humane society or gain a FIRST POST on /. to join our club. If you have MOD POINTS and would like to support the ECFA, moderate this post UP.

==This post brought to you by proud dog killer PickaBu on EFNET.

THE GNAA WILL RIP OUT YOUR HEART (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9483042)

On behalf of hfis, proud member of the GNAA.

Oh dear (4, Funny)

Killjoy_NL (719667) | more than 9 years ago | (#9483018)

Does nobody see what is about to happen?
Those computers will read that list and know which computers to connect to, to take over the world!!

Doesn't anyone read comics anymore ??
May $DEITY have mercy on us all.

Not comics... the Forbin Project (2, Funny)

Faust7 (314817) | more than 9 years ago | (#9483095)

Does nobody see what is about to happen?
Those computers will read that list and know which computers to connect to, to take over the world!!

WARN

THERE IS ANOTHER SYSTEM

Guess.. (-1, Redundant)

Anonymous Coward | more than 9 years ago | (#9483021)

They need to host their site on one of 500 listed.

Someone's gotta say it... (-1, Redundant)

akadruid (606405) | more than 9 years ago | (#9483028)

Looks like their webserver didn't make the top 500 list...

Either that or there is an enterprising student thinking 'hmm, I know how I can get a higher score at this SET@home game'...

Jesus (-1, Redundant)

Moblaster (521614) | more than 9 years ago | (#9483033)

Imagine trying to close the pop-up windows on that thing. They got Opera for that?

Re:Jesus (1, Insightful)

Anonymous Coward | more than 9 years ago | (#9483191)

Supercomputers are big calculators. If there is a GUI, you run it on your own computers.

And, before you ask, supercomputers generally won't make your games run faster. The game would have to be completely rewritten to take advantage of the architecture -- and, even if there is graphics hardware installed, most HPC architectures aren't designed to deliver a high framerate.

I GOT GREASY LOONIX IN MY POOP SHUTE!!!1111````!~1 (0, Troll)

Greased_Yoda (724757) | more than 9 years ago | (#9483034)

Props to all my short and greasy anus-dwelling jedi niggas!

OMFG WELCOM BACK TO TEH SLASHDOT WEBLOG!!!`1 (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9483090)

doom3 (-1, Redundant)

Braingoo (771241) | more than 9 years ago | (#9483035)

But will they play doom3?

Re:doom3 (-1)

Anonymous Coward | more than 9 years ago | (#9483138)

Will all people like you finally curl up into a ball and die, please?

Imagine a... (3, Funny)

garethwi (118563) | more than 9 years ago | (#9483036)

...oh forget it.

Re:Imagine a... (0)

Jacer (574383) | more than 9 years ago | (#9483089)

I hate you, and I just wanted you to know with that comment you've made my short list of foes.

Re:Imagine a... (-1)

Anonymous Coward | more than 9 years ago | (#9483160)

A wise choice, sir. I will do the same.

Re:Imagine a... (-1)

Anonymous Coward | more than 9 years ago | (#9483202)

Your short list?? You have exactly one entry and it's that guy.

IBM's Blue Gene (5, Interesting)

zal (553) | more than 9 years ago | (#9483038)

Last Thursday there was a little HPC Event by IBM at my University. And apart from the usual Balde Center for Scale Out Computing PR Blurb there also was a 1 Hour Presentation by one of IBM's Senior Strategy Analysts. What i found most interesting how they basically use embedded Processors for Blue Gene due to Cooling and Power Consumption Issues. He talked about Thermal Design, from the Basic Components right to where you compute Heat Dissipation for the whole room so you know where to put the very heat sensitive myrinet/infiniband components.

Re:IBM's Blue Gene (-1)

Anonymous Coward | more than 9 years ago | (#9483101)

Please don't Capitalize every Other word.

Re:IBM's Blue Gene (0, Offtopic)

zal (553) | more than 9 years ago | (#9483455)

Well, first of im not a native speaker, so im allowed some freedom with capitalization. And Second , i can't even get capitalization right in my native Language, so whatever.

Re:IBM's Blue Gene (5, Informative)

flaming-opus (8186) | more than 9 years ago | (#9483824)

Did they mention why myrinet and infiniband are heat sensitive? I've used myrinet before, and did not encounter any problems with it, though I was not using 1U dual-CPU systems. (just a bad idea in general) A myrinet card includes a pretty high-clocked ASIC that runs warm for a network card, but is nothing compared to most graphics cards these days.

Blue Gene is an amazingly simple, and crafty design, with efficiency at its heart. I'm not sure that it will be as successful as the IBM marketing machine claims it will, but it's exciting none-the-less.

The trend in CPUs, over the last ten years or so, has been to maximally fill long, wide super-scalar pipelines. The Power4 has half a dozen execution units and a 15 stage pipeline, running at 1.7 ghz. To keep that full, one has to have exceptional branch prediction, huge caches, and superb compilers, and tons of memory bandwidth.

The Blue Gene approach is to have fewer, shallower, lower-clocked pipelines, but lots of CPUs. Their peak speed is a quarter of the top CPU designs, but their real speed is half of the big guns. Since they are using today's chip technology to implement yesterday's chip designs, they use little power, and are very inexpensive. Since IBM has cleverly integrated all the communications networks and memory controllers, you only need three components in the system: CPUs, RAM chips, and passive circuit boards - plastic and copper. (Yeah, I'm sure there is other stuff, but not much)

The design is not revolutionary, it's a fairly intuitive evolution of the Paragon, or the T3E. This sort of system may not be perfect for every task, but will excell at the sorts of tasks that already work well on big clusters. That, and it will likely be very cost effective.

3...2...1... /. (-1, Redundant)

Nakkel (748351) | more than 9 years ago | (#9483040)

Its safe to say that the site isnt hosted on any of those computers. Its already succumbing under the /. effect...

One thing is for sure. (-1, Redundant)

Supradog (583554) | more than 9 years ago | (#9483041)

None of the top 500 is hosting top500.org.

slooooow.

(yeah yeah, computing power, not backbone)

What I find interesting... (4, Insightful)

Noryungi (70322) | more than 9 years ago | (#9483046)

Is that Disney is #57 in the top500, while Weta has the #77 and #80 spots... impressive showing by the entertainment companies.

On the other hand, PDI (Pacific Data Images -- Shrek), Pixar and ILM do not appear in the list, which is also very interesting.

Re:What I find interesting... (2, Insightful)

gadget junkie (618542) | more than 9 years ago | (#9483085)

... I guess that's because rendering is inherently scaleable, i.e. there is no advantage in building one big, bad ubermachine. Far simpler to parcel out frames between any and odd number of renderfarms, many of which you may not even own.

It is a "make or buy" situation. Given an efficient payment system, I do not see why they should not render using some program similar to Folding@home.

Re:What I find interesting... (1)

lboxman (587913) | more than 9 years ago | (#9483232)

Because the movie has to be done on time, and it is difficult to guarentee that enough CPU time wil be available from a folding@home-type distributed network. Users may turn their PCs off, get bored with it and decide to give/sell their unused cycles to a different project, etc.

Re:What I find interesting... (3, Interesting)

afidel (530433) | more than 9 years ago | (#9483299)

Actually the biggest reason is that the scene data is gigabytes in size and the machines need to be maxed on the RAM they can hold. My friend had a single texture on his senior digital film project that was larger than most systems ram (570MB IIRC).

Re:What I find interesting... (5, Insightful)

flaming-opus (8186) | more than 9 years ago | (#9483512)

I did some contract work at ILM several years ago, and know why this is. They don't use one big machine, but rather a bunch of medium sized clusters. This is for a very good reason. Weta has, thus far, worked on one big movie at a time, where all of their resources are dedicated to a single data set. ILM is constantly working on half a dozen moveis all at once.

In essence, they lease some amount of resources to a particular movie studio for some number of months. At the time they were doing this with row upon row of 32 processor SGIs, but they are probably using something else these days. Thus no spot on the top500 list. However, since they are in the business of making movies, I bet they don't really care.

Not all that interesting. (0)

Anonymous Coward | more than 9 years ago | (#9483713)

Perhaps they .. didn't submit to the Top500 list.

Sevenfold Increase in Opterons (2, Funny)

Moblaster (521614) | more than 9 years ago | (#9483049)

That's the old trick about multiplying by zero, right?

Re:Sevenfold Increase in Opterons (0)

Anonymous Coward | more than 9 years ago | (#9483142)

Sevenfold litteraly means "to fold seven times" or 2 to the power of 7, which is 128. Alas, the list only increased by 30, which is less than a fivefold increase. I hope that the AMD processors weren't used in the calculation of this figure, otherwise, I'n not sure we could call it a "super computer".

How do they measure? (5, Funny)

-noefordeg- (697342) | more than 9 years ago | (#9483051)

So how do they measure?

The link didn't work right now so I'll make a guess...

Test must at least include Q3, UT-2004 and 3DMark03, but since these are pretty powerful computers I guess they also use some sort of advanced custom built MineSweeper with like 10.000x10.000 grid playing field or something wild crazy stuff like that.
Maybe 400+ pages Word documents?
Final test is probably Halo for pc. Any fps score above 20 will result in a spot > 100 on the list.

Re:How do they measure? (0)

Anonymous Coward | more than 9 years ago | (#9483080)

"The ranking relies on computer owners or makers submitting details of their machines and is based on the results of a standard benchmark called Linpack. Machines are ranked by the maximum number of floating operations per second (flops) achieved during the test."

Re:How do they measure? (2, Funny)

G-funk (22712) | more than 9 years ago | (#9483091)

Above 20fps? In pc halo? Man what are you smoking, apart from the magic smoke? It's not like they're all linked up into some giant uber-cluster!

Re:How do they measure? (0)

irokie (697424) | more than 9 years ago | (#9483120)

nah... none of that wussy ass junk...

they're testing Longhorn on them (see here [slashdot.org]).

Re:How do they measure? (1, Interesting)

flaming-opus (8186) | more than 9 years ago | (#9483439)

They measure with linpack, which only measures processor computational performance, but ignores memory, interconnect, and I/O performance.

This is why the US government uses HPC challenge benchmark, in which Linpack is only one measure among eight.

Re:How do they measure? (-1, Flamebait)

Anonymous Coward | more than 9 years ago | (#9484116)

Well I guess that makes my G5 truly a supercomputer, because it can run halo at 28 fps.

Google cluster? (3, Interesting)

millwall (622730) | more than 9 years ago | (#9483054)

Google cluter not in here? What do you reckon the performance/size of such cluster could be?

Re:Google cluster? (3, Interesting)

nutshell42 (557890) | more than 9 years ago | (#9483140)

I'm just guessing here so sue me

Google has an impressive cluster but it's optimized for storage and parallel page access.

I don't think that you could use google's cluster to compute 42 without distributing the work by hand over the different servers because it wasn't built to do calculations but to answer page requests distributed over the different units and to be able to access the most complete mirror of today's web

Re:Google cluster? (5, Interesting)

pete-wilko (628329) | more than 9 years ago | (#9483181)

Having heard a lecture from Jack Dongarra about HPC and the top 500, he mentioned that google declines to participate, as they wern't inclined to reveal their setup, or run the benchmarks for the top 500 which would mean putting their machines to other uses for the duration of the benchmark. If I rememeber though I think he said that at a guess if they did participate (based on the various 'guesstimates' out there of google's setup) that they'd easily make the top 10 if not pushing number 1. This is also leaving aside arguments over the role that the system is trying to fulfill (i.e. easily distributed work, like a search engine, vs work that can't be broken up easily like an earth simulator).

Re:Google cluster? (1)

freeduke (786783) | more than 9 years ago | (#9483542)

Many other clusters/grids computers can't be there. Defense clusters are amongst the most powerfull, but people are really reluctant to tell the other what their computing power is made of as it comes to defense...

In research, there are huge grids that cannot be benchmarked, because those are co-financed, and facing the difficulties to determine who would get the credit for the whole grid, the best is to avoid it.

And the final reason could be that now that the manufacturers are leading a war on this list, the figures are often allmost meaningless.

Where are the times where your homemade research bi-Athlon cluster could enter this list?

Google facts and figures (3, Interesting)

freeduke (786783) | more than 9 years ago | (#9483724)

I found this on the Folding at Home site. It seems that they are running FAH on spare time and when you have a look at the statistics of team 446 [stanford.edu], you see that they are the first team, that they had 23721 CPUs active during the last 50 days...

that tells more about "the beast". So far, I just can tell that it is made of linux clusters, containing about 12500 nodes, because in case of clusters you are facing bi processors systems 98% of the time.

Here is the track, if someone wants to hunt the beast.

Virus takes out Apple cluster (-1)

Anonymous Coward | more than 9 years ago | (#9483079)

It's called AIDS.

These links work: (4, Informative)

BReflection (736785) | more than 9 years ago | (#9483082)

main page: http://freecache.org/http://www.top500.org/

click view lists: http://freecache.org/http://www.top500.org/lists/2 004/06/

the list: http://freecache.org/http://www.top500.org/list/20 04/06/

Apple!!!!! (-1, Flamebait)

Anonymous Coward | more than 9 years ago | (#9483086)

jesus CHRIST...you mean a desktop Apple G5 didn't make the list?

"heavily anticipated"? (2)

Fourier (60719) | more than 9 years ago | (#9483087)

Heavily anticipated by whom? I understand that the Superbowl is heavily anticipated. The upcoming US election is heavily anticipated. To a lesser degree, today's SpaceShipOne launch is heavily anticipated. But honestly, are there any people gathering around the water cooler exchanging rumors of who has the edge in cluster network latency this year? (Supercomputer administrators don't count.)

Somebody needs a little perspective...

Re:"heavily anticipated"? (0)

Anonymous Coward | more than 9 years ago | (#9483250)

Yes. People who work in HPC centers around the world are quite interested. I don't see why anyone else should care -- but since I'm peripherally involved in scientific computing (as a sysadmin at VT), I find it quite interesting too.

Even better, the people who want to give us research money read those rankings -- so a high ranking means more research money and some good press. It's kind of like football -- except that benefits those of us who are at this university for research, learning, and teaching. :-)

P.S. I don't see why anyone gets excited about football. I'd much rather watch a Supercomputer Bowl than a Superbowl! But, hey, a lot of people enjoy football, so it's all good.

Re:"heavily anticipated"? (5, Insightful)

TimeZone (658837) | more than 9 years ago | (#9483390)

You probably don't understand that a lot of people are employed in the area. I worked on technology that went into the #6 machine, and yeah, the top500 lists mean a lot to us. I've been waiting a long time for something I worked on to end up in the top 10.

TZ

WWDC Power (1, Interesting)

artlu (265391) | more than 9 years ago | (#9483104)

Maybe we can get everyone at the WWDC to use XGrid [apple.com] and break into the #1 slot for a brief second. Damn, i want Apple to take that spot.

GroupShares Inc [groupshares.com] - A Free Online Stock Trading Community

Re:WWDC Power (2, Interesting)

Talez (468021) | more than 9 years ago | (#9483173)

Do it!

Assuming an average 1GHz per person, 4 FLOPS per cycle (assuming you could get Altivec working flat strap), 70,000 people turn up that could work out to be... ummm.... 280 teraflops.

You'd have yourself a Universe Simulator with that amount of power!

Predictions (-1, Offtopic)

Estanislao Martnez (203477) | more than 9 years ago | (#9483107)

1. Somebody's going to write an "Imagine a Beowulf cluster of these!" comment. This will not really get modded up much

2. Somebody's going to make an utterly offtopic and mildly racist joke about the dumb Indian IT workers who speak really bad English and take jobs away from smart geeks. This will of course shoot right up to (+5, Funny).

Re:Predictions (-1)

Anonymous Coward | more than 9 years ago | (#9483225)

Someone already made an "Imagine a ... Oh Forget it!" comment which is t +5.

There is not one lame comment about "the dumb Indian IT worker who .... geeks" (I'm one of those, but spaek English quiet wail)

Re:Predictions (0)

cdyson37 (584699) | more than 9 years ago | (#9483237)

Number 1 beat you to it (albeit slightly varied). Not seen number 2 yet.

I'm still waiting for IN SOVIET RUSSIA BEOWULF CLUSTERS IMAGINE YOU, but I won't stoop to posting that.

Linux clusters still rule (5, Informative)

Sunspire (784352) | more than 9 years ago | (#9483108)

At least 5 of the top 10 systems are running Linux, starting at number two with Thunder at the Lawrence Livermore National Laboratory [intel.com]. The others are IBM BlueGene/L clusters at places #4 and #8 [linuxdevices.com], Tungsten at NCSA at #5 [uiuc.edu], MPP2 at Pacific Northwest National Laboratory at #9 [quadrics.com], and probably also the Dawning 4000A at the Shanghai Supercomputer Center as #10, though I'm not 100% sure about this last one.

Re:Linux clusters still rule (1, Informative)

Anonymous Coward | more than 9 years ago | (#9483258)

just about 1 out of 64 chips runs a full powerpc version of linux (lightly modified), that will be the node that handles input/output for that group of nodes. the others run a small custom and very stripped down kernel, i don't remember the name, i attended a presentation at my university here in italy.
on a side note the cluster that will control bluegene (yes, to control the big beast they are planning to use a cluster of machines, for example they will use db2 to store informations about the 64 thousands nodes. think about it, a cluster to control a HUGE cluster...) will be made of linux workstations.
pretty impressive...

Re:Linux clusters still rule (2, Interesting)

flaming-opus (8186) | more than 9 years ago | (#9483579)

well, in a supercomputer OS, you really only have two choices. You can create a microkernel OS that runs on al the computation nodes, and does system calls to services nodes.

you cluster together a bunch of monolithic kernels. At 8000 processors you aren't going to be able to use 1 monolithic kernel, so the distinction between a medium scalable OS like linux and a large scalable OS like solaris/irix is a bit of a moot point. 1000 OS images instead of 250? It's a nuisance either way.

most powerful clusters? (1)

millahtime (710421) | more than 9 years ago | (#9483113)

Is there a list of most powerful clusters? If so, does /. make that list?

Re:most powerful clusters? (1)

gl4ss (559668) | more than 9 years ago | (#9483143)

this is a list of the most powerful clusters.

in all practicality it's impossible to make computer that isn't a cluster of some sort that would make it to the list.

Re:most powerful clusters? (1)

hendridm (302246) | more than 9 years ago | (#9483678)

How about a cluster of a million monkeys (slashbots?), if given enough time randomly banging on keyboards, could reproduce Trollkore's complete works?

I hope they're not using... (1, Funny)

Armchair Dissident (557503) | more than 9 years ago | (#9483125)

"The Thunder system, based on 4,096 Intel Corp. Itanium 2 processors, at LLNL recorded a maximum performance of 20T flops"

I hope they're not using Linux. That's a LOT of SCO licenses...

My machine (4, Funny)

swapsn (701280) | more than 9 years ago | (#9483127)


I see my machine has not made it into the list. Ah well. Maybe next year...

Re:My machine (0)

Anonymous Coward | more than 9 years ago | (#9483226)

You forgot to click "submit my 3dmark score on the net" after running it.

Supercomputer running the website. (1, Redundant)

serviscope_minor (664417) | more than 9 years ago | (#9483129)

Pitty they don't have one of the top500 running the website. It seems to be going rather slowly at the moment...

Apple Xserve cluster is IBM too (4, Interesting)

YouHaveSnail (202852) | more than 9 years ago | (#9483133)

It's worth pointint out that if you're going to consider a given supercomputer to be "AMD" or "Intel" based on where the processors come from, then Virginia Tech's cluster of Apple Xserves is an "IBM" machine.

That's not to take anything away from Apple. Both Xserve and the G5 towers that came before them are a great design, reliable, run a great OS, yada yada yada. But the chips are IBM.

Re:Apple Xserve cluster is IBM too (2, Informative)

Anonymous Coward | more than 9 years ago | (#9483891)

The PowerPC G5 is the product of a long-standing partnership between Apple and IBM, two companies committed to innovation and customer-driven solutions. In 1991, they co-created a PowerPC architecture that could support both 32-bit and 64-bit instructions. Leveraging this design, Apple went on to bring 32-bit RISC processing to desktop and portable computers, while IBM focused on developing 64-bit processors for enterprise servers.The new PowerPC G5 represents a convergence of these efforts: Its design is based on the PowerPC instruction set, as well as the POWER Architecture that drives IBM's top-of-the-line enterprise servers. The PowerPC G5 is fabricated in IBM's new $3 billion, state-of-the-art facility in East Fishkill, New York.To get electronics so small requires miniaturization breakthroughs, and IBM's dedication to scientific research has made these advances possible.With industry-leading build, assembly, and test technology, IBM uses a 90-nanometer process to produce the PowerPC G5. More than 58 million silicon-on-insulator (SOI) transistors and eight layers of copper interconnects enable this new processor to deliver tremendous performance.

Re:Apple Xserve cluster is IBM too (0, Flamebait)

Kuad (529006) | more than 9 years ago | (#9483966)

Virginia Tech's cluster isn't on the list, you idiot. They swapped the G5 towers out for XServes because they have ECC memory (which made the original cluster useless), and they haven't published a Linpack test since then.

+ 65 for IBM (5, Interesting)

freeduke (786783) | more than 9 years ago | (#9483135)

I have seen that there are 65 more IBM supercomputers in june than in october (jump from 159 to 224). I thried to figure out which computer those were, because it is an impressive gap: + 65 out of 500 in 6 month? Marketing gap?

In October, HP was impressive, because they filled the bottom of the list with Itanium based superdome: they ranked those all on the same bench figures, that means that those computers were not benchmarked by the customers but by HP. That was a good oportunity for IBM: each time they could put one of their computers on the list, they were sure to throw an HP one out of it, so increase the gap by a factor of 2 (+1 for IBM, -1 for HP) with their main rival.

So I am now wondering if this top500 list still means anything in term of performances and computing power, or is just a promoting tool, where manufacturers can conduct a war on market shares.

hmmm (-1, Troll)

Anonymous Coward | more than 9 years ago | (#9483157)

1. practice clicking

2. get a real fast computer so your clicks are "faster", maybe post an "ask slashdot" about how to silence your mouse so
you don't have to hear the clicks.

3. OMG imagine a beowulf clust...

4. get job at IBM to use their prototype

5. take a break.... play DOOM III on longhorn with the other top 5 super computer guys and laugh at all the n00bs who can't play. Possibly overclock and argue with other guys over who's processor is best and how with cry to mum with a crushed core.

6. use ultra fast clicking ability to get first post on slashdot

7. make comment about FRIST PISS, FROM TEH GNNA WIT TEH HOT GRITS OF PORTMAN, misleading link to a goatse.cx-like picture.

8. make subsequent post about first one and your super computer in the 1,2,3,?, profit style, using each step to rehash old cliches and have a rage about cliches THEN post from another account and say "I for one welcome our new cliche hating overlords" so you can karma whore.

9. Blame it all on microsoft, run an RPM distro, then gentoo cause it's 3j33t, then realise linux is full of n00bs and become a snobby BSD guy, then realise you are too old for it all and go to apple then look in the mirror and realise you are running a commercial OS and are way away from your hacker roots and start using linux again as a "old mentor" type and maybe trying and "unite da clans" (braveheart)... fail and look like an aging hippy as you wave a sign with a hand-drawn penguin on it against laws which have been greased by lobby money.

9. lose hope

10. Re-start trolling as an intellectual troll (not with GNAA) and use the power of anonymity to show weaknesses in cliches of sites like slashdot.

11. make up a back-story, lie about your age, technical prowess and history playing DOOM III on longhorn in a super computer lab at IBM

12. ????

13. FUCK OFF AND DIE ALL YOU STINKING KARMA WHORES, come up with some new material for GODS sake. Moderators; there is a phrase that goes "don't feed the trolls", well feed THIS troll as a reminder to all that stupid beowulf jokes etc. etc. from logged-in people to karma whore are crap and they never exhibit the creativity that should be required to get +5 in anything.

14. When I was little I used to wonder why my parents were against me swearing, because I had heard them swear on occasion. Then I realised why; because if you do it all the time it devalues it for when you REALLY need it. +5 insightful or funny doesn't need to be a civilisation changing event. But some of the crap cliche no-effort karma whoring that goes on is just a disgrace, and everyone is responsible because everyone mods. Trolls like GNAA use this slack moderation to "harvest" (as they put it) karma. Their objective is to harvest karma for their accounts while adding no "value" to slashdot. Now, while I don't love slashdot, and have no reason to encourage people to make money for it by making it a better place, you could mod down the cliched dicks and save me having to read them.

14. YHBT YHL FOAD N00Bs

thank you, I'll be here all week, try the veal

Re:hmmm (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#9483178)

I for one welcome our new cliche hating overlords.

P.S. It's me, the troll, just doing this so nobody else can. Just like self-derogatory joke can help immunise one about a real flaw, this immunises me against possibly the lamest comeback ever. I am strong and powerful and have a wizards hat -- don't mess with me you low IQ power cliche-trolls.

Re:hmmm (-1)

Anonymous Coward | more than 9 years ago | (#9483228)

*steals hat*

ha-ha!

I, for one, AM a HAT-STEALING overlord!

Shrinkage? (-1)

Anonymous Coward | more than 9 years ago | (#9483193)

my, my, that Big Mac turned into a Jr Burger pretty fast...

Re:Shrinkage? (1)

cyfer2000 (548592) | more than 9 years ago | (#9483540)

No, they are under construction, that means the big Mac will provide a large frech fry for free when it comes back.

Re:Shrinkage? (0)

Anonymous Coward | more than 9 years ago | (#9483896)

oh I thought "under construction" was an ex-RDF expression for "didn't perform as expected under scrutiny"

Benchmarking and being open (0, Redundant)

p0 (740290) | more than 9 years ago | (#9483198)

This makes me wonder why Google is not on this list.

Unemployment Rate Goes Down (2, Funny)

Moblaster (521614) | more than 9 years ago | (#9483227)

In other news, Bush administration officials have created 1.2 million new jobs by hiring unemployed Americans to close pop-ups windows for Lawrence Livermore National Laboratory, whose new supercomputer will be used to study nuclear bombs, the weather, and the dynamics of carpal tunnel syndrome.

Purchase IBM vs SGI vs HP (0)

Anonymous Coward | more than 9 years ago | (#9483286)

I'm in need of some informed opinions for an impending purchase. This thread might be just the ticket.

Given a choice of a p690 (32 processors) and offerings of either 32 or 64 processors from SGI (altix) and HP, which would you choose everything else being roughly equivalent?

mirror site (1, Informative)

Anonymous Coward | more than 9 years ago | (#9483318)

Use the Mirror [top500.org]

Don't bother mentioning Intel (1)

mcbevin (450303) | more than 9 years ago | (#9483335)

Before everyone starts congratulating AMD's success and talking about the superiority of the Opteron and Intel's imminent demise etc etc, I thought it might be worth mentioning that AMD isn't the only company improving on the list:

A look at the hardware shows Intel Corp. making big gains on its competitors with a total of 287 machines are based on Intel chips, up from 119 this time last year.

Which of these run W2k3 for HPC? (0)

Anonymous Coward | more than 9 years ago | (#9483407)

...and which run linux? I'd be interested in seeing some benchmarking and stability comparisons.

Can anyone provide a link to this info please?

Important points of note (5, Interesting)

patrik (55312) | more than 9 years ago | (#9483621)

1) The VT cluster will probably never beat the EarthSim. Why? Because the interconnects (fancy network connections) are so specialized on EarthSim that it will tromp any off the shelf system. Furthermore everything about the EarthSim computers are built to be clustered as they are. VT uses infiniband which is faster and lower latency than Myranet or the other common cluster interconnects, which is part of the reason why it kicks so much butt, but the systems are still pretty much off the shelf and will never be able to beat EarthSim. Of course VT does for millions upon millions less and much more cost effectively, so even if it's not #1, in many ways it is the best.
2) Google's cluster is (probably) a much more distributed system, it would probably take a severe beating in trying to do the LinPack benchmarks that they use to rank the top500. The algorithm requires a lot of data passing, it probably doesn't excel at low latency or even high bandwidth (>16Gb/s) data passing. That's just an educated guess though, AFAIK that information is pretty well secreted. In raw processing power under one roof Google probably has it made, but since most problems (not all, read: *@home) in science and math require lots of data passing between nodes Google will probably get trounced in the top500.

Patrik

Sheesh (4, Funny)

HarveyBirdman (627248) | more than 9 years ago | (#9483646)

the famous Apple cluster didn't make the list, because it was out of service for hardware upgrades

:-\

In other news, Car & Driver released their list of top ten coolest cars. The new Ford GT was not included because Bob had it in the garage for an oil change.

breakthrough? (0)

Anonymous Coward | more than 9 years ago | (#9483943)

i wonder how many TFlops they'll make when they're back.

Re:Sheesh (2, Interesting)

falcon5768 (629591) | more than 9 years ago | (#9484004)

Thats a legit thing. Its actually off the list because Apple still hasnt sent over all of the xserves it was supposed to, and VT being stupid as fuck, sold off their entire computer cluster.

China took more than 10 positions (1)

cyfer2000 (548592) | more than 9 years ago | (#9483690)

And the top one is #10. Russia took 2 positions. Japan took 30+ positions. Germany took 30+ positions. United Kingdom took 30+ positions. France took 10+ positions. Well, Skynet still have a longway to go to take control of Russia.
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...