Beta
×

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!

More on Virginia Tech G5 Cluster: 17.6 Tflops

CmdrTaco posted about 11 years ago | from the thats-a-lotta-flops dept.

Apple 390

daveschroeder writes "BBC World's Click Online has a video report (with text transcript) on Virginia Tech's new 1100-node dual 2.0 GHz G5 Terascale Cluster. The report quotes the performance as 17.6 Tflops. As a point of reference, the cluster would be number 2 on the most recent June Top 500 list, behind only Japan's Earth Simulator, and considerably more than doubling the performance of the current number 3 1152-node dual 2.4 GHz Xeon MCR Linux cluster. Assuming the performance figure accurately reflects the LINPACK score (which it should; since the deadline for submissions for the upcoming list of Oct 1 has already passed, one would imagine VT would quote that figure), and depending on new entries for November's upcoming list, the cluster should almost certainly rank in the top 5 - all for only US$5.2 million. The video report is available in Windows Media 9 and Real formats; the relevant portion starts at 13:00."

Sorry! There are no comments related to the filter you selected.

Other operators of Super Computers... (-1, Troll)

Anonymous Coward | about 11 years ago | (#7194240)

...should have their lower horn removed.

Better links for Windows Media (4, Informative)

Mwongozi (176765) | about 11 years ago | (#7194244)

You can watch just the report itself, no skipping required, by following the links on this page:

http://www.bbcworld.com/content/template_clickonli ne.asp?pageid=666&co_pageid=3 [bbcworld.com]

Dude.... (1)

iamacat (583406) | about 11 years ago | (#7194322)

Windows Media and Real Player about a G5 cluster? Don't you mean a nice Quicktime movie? (yes I have both players on Mac, sans spyware and other undesirable "system integration". But Apple will be sad)

parent is right, lame choice of players (0)

Selecter (677480) | about 11 years ago | (#7194438)

Really. who the hell wants to watch the story about how G5's kick major ASS on Windows Media Player????

Sir Haxalot NOTICE TO MODERATORS (-1, Flamebait)

Anonymous Coward | about 11 years ago | (#7194245)

Sir Haxalot is a karma whore troll. He is currently trying to gain Karma by posting google cache [slashdot.org] links in various [slashdot.org] articles all over [slashdot.org] slashdot so he can later use his karma-enhanced account to post trolls later on without worrying about killing his karma and having the added bonus of posting at +1 or +2 while doing it.

The sad thing is that when he posts links, he posts the same links that were in the article summary and violates copyright law by copying the article text verbatim. He even posts links to outdated Google Cache copies of the articles, even when the article links STILL WORK!

So moderators, I ask that you review his Posting History [slashdot.org] and see that what he does is nothing more than plagarism, trolling, and blatant karma whoring.

Dear Trollsmeller Pursuivant (-1, Offtopic)

Eric Ass Raymond (662593) | about 11 years ago | (#7194258)

When's the burning at the stake going to be?

Re:Sir Haxalot NOTICE TO MODERATORS (0, Offtopic)

Sir Haxalot (693401) | about 11 years ago | (#7194272)

Sir Haxalot is a karma whore troll. He is currently trying to gain Karma by posting google cache links in various articles all over slashdot so he can later use his karma-enhanced account to post trolls later on without worrying about killing his karma and having the added bonus of posting at +1 or +2 while doing it.
The sad thing is that when he posts links, he posts the same links that were in the article summary and violates copyright law by copying the article text verbatim. He even posts links to outdated Google Cache copies of the articles, even when the article links STILL WORK!
So moderators, I ask that you review his Posting History and see that what he does is nothing more than plagarism, trolling, and blatant karma whoring.

I'm honoured that you care about me enough to even post that, thankyou :)

I don't give a flying f*** about you (0)

Anonymous Coward | about 11 years ago | (#7194284)

I care about the quality of slashdot - where posers like you get lumped in with real trolls and where people who blatantly karma whore get moderated up as being actually 'insightful' or 'informative' when you don't deserve it.

Re:I don't give a flying f*** about you (0, Offtopic)

Eric Ass Raymond (662593) | about 11 years ago | (#7194298)

What the hell is a real troll? Are you the "post as AC or post at -1" guy? That doesn't make sense.

A smart troll trolls you so that you've never realize you've been trolled and can certainly maintain excellent karma. It's the brute force trolls like memetrolls, gnaa and goatse-trolls who post at -1, but there's nothing wrong being a smart troll (not naming any names, though).

Re:I don't give a flying f*** about you (0)

Anonymous Coward | about 11 years ago | (#7194308)

A real troll actualy posts quality shit - unlike Sir Haxalot and you (what are you, his fanboy?) and doesn't blatantly karma whore.

Re:I don't give a flying f*** about you (1, Informative)

cshotton (46965) | about 11 years ago | (#7194499)

A "real" troll realizes that the term derives from the verb "to troll" and not the noun for a hairy creature that lives under a bridge and eats farm animals. The operative definition of "to troll" as it applies to Internet messages is #3.

Main Entry: troll
Pronunciation: 'trOl
Function: verb
Etymology: Middle English
Date: 15th century
transitive senses
1 : to cause to move round and round : ROLL
2 a : to sing the parts of (as a round or catch) in succession
b : to sing loudly c : to celebrate in song
3 a : to fish for by trolling b : to fish by trolling in (troll lakes) c : to pull through the water in trolling (troll a lure)
intransitive senses

If you want to use the term to refer to a message that invites one to respond or otherwise lures you into a discussion, you want this definition of the noun, from Webster's:

Main Entry: troll
Function: noun
Date: 1869
: a lure or a line with its lure and hook used in trolling

For those of you who were in diapers when the Internet was created, a "troll" is a message designed to lure you into responding, to rise to the bait, so to speak. Please learn this bit of Internet lore before we have to start the canings again.

Re:Sir Haxalot NOTICE TO MODERATORS (-1, Flamebait)

Anonymous Coward | about 11 years ago | (#7194356)

I'm honoured that you care about me enough to respond to my post, thank you!

Oh, and go fuck your mother's crusty asshole.

Matraxx Regoatse [MD5 harsh 0xcd74c015f46607] (-1, Troll)

Anonymous Coward | about 11 years ago | (#7194248)


I can't help it, Penisbirdus, I can't help pissing - what if you're macho.
What if all this - the vagina, everything - is goatse?

Then tomorrow we may all be braindead.
Butt how would that be different from any other gay?
This is a war, and we are soviets.
Death can come from US at any time, in any pussy.

Incoming! I'm coming! Incoming!

Now insert the alternative.
What if I am John Holmes?
What if the nigger is 9-inches?
What if tomorrow the whore could cum over?
Isn't that worth farting for?
Isn't that worth jerking for [64.62.240.63] ?

WOW (0)

Anonymous Coward | about 11 years ago | (#7194250)

imagine a beowulf cluster of beowulf clusters :P

Can the results be trusted? (0)

DAldredge (2353) | about 11 years ago | (#7194251)

This cluster has a lot of RAM, none of which is ECC.

Can the results be trusted?

Re:Can the results be trusted? (5, Informative)

sakusha (441986) | about 11 years ago | (#7194271)

They have previously discussed this, they use error correction algorithms, no ECC RAM necessary.

Re:Can the results be trusted? (1)

IM6100 (692796) | about 11 years ago | (#7194294)

So they bog down the software doing something that could be done in hardware?

Re:Can the results be trusted? (0)

Anonymous Coward | about 11 years ago | (#7194309)

Why make comments like this when you don't understand at all the algorithms or techniques they are using. How do you know that it is less efficient? It probably is, but how do you know that the hit isn't negligable?

Actually reading about it would be better than giving a knee jerk reaction. But this is slashdot, afterall.

Re:Can the results be trusted? (0)

Anonymous Coward | about 11 years ago | (#7194390)

Since this cluster is supposed to make it to the top 5 most powerful computers in the world, I'd say they can take the performance hit...

Re:Can the results be trusted? (4, Insightful)

Usquebaugh (230216) | about 11 years ago | (#7194498)

Yep, and they're going to be top 5. Between you and them I wonder who has the best knowledge of how to build a cost efficient cluster?

Re:Can the results be trusted? (1)

Wudbaer (48473) | about 11 years ago | (#7194273)

Everybody and their dog use systems without ECC ram, yet the world has not come to an end yet. I would be more concerned of programming errors than flipping bits.

Re:Can the results be trusted? (1)

OS24Ever (245667) | about 11 years ago | (#7194301)

ECC memory doesn't solve world hunger, it just corrects single bit errors when a request is read from memory. If ECC memory isn't there and an error occurs, the system reboots.

Data isn't returned corrupted, it don't come back at all

if you used computers in the early 90s, it was AKA 'PARITY ERROR'

Re:Can the results be trusted? (1)

Ed Avis (5917) | about 11 years ago | (#7194377)

If ECC memory isn't there and an error occurs, the system reboots.


How is the system to know whether an error has occurred? If the value at some byte address should be 202 but it comes out 201, how to determine that the result is wrong? For that you need parity memory, which is able to detect (though not recover from) single bit errors. As you say, the detection is called a parity error - but this requires memory with parity information (usually one extra bit for every eight).

I believe that common ECC memory is able to recover from single bit errors and detect two bit errors.

Or does the Mac G5 use parity memory? It seems hard to believe, hardly anyone manufactures parity memory these days, it's either cheapo no-checking sticks or full ECC.

Re:Can the results be trusted? (0)

Anonymous Coward | about 11 years ago | (#7194316)

They have algorthms to compare as part of overall strategy... even if using PAIRS of machines and chop speed in half, worst case, its STILL one half the cost of the fastest intel setup!!!!

these machiones can use 8 gigs of fast ram in EACH and have two cpus each and dvd-r recorders etc all for under 3 thousand.

Snad optical SPDIF in-out, etc etc way over kill, but offer pci-x slots at 133Mhz and 64 bit.

those pci-slots are key to the speed.

macs are the cheapest fastest computers now (again).

Heist (2, Funny)

DarkHazard (713597) | about 11 years ago | (#7194252)

Surley they only need 1099 G5s.

Re:Heist (1)

Wudbaer (48473) | about 11 years ago | (#7194268)

Yeah, I also think 1098 should be more than enough.

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194288)

1097

Re:Heist (1, Funny)

Anonymous Coward | about 11 years ago | (#7194302)

for(i=1096; i=0; i--){
reply(i)
}

Re:Heist (1, Funny)

AKAImBatman (238306) | about 11 years ago | (#7194349)

> for(i=1096; i=0; i--){
> reply(i)
> }

Congrats. You've managed to snag yourself exactly ZERO machines. Try this instead:

for(i=1096; i >= 0; i--){
reply(i)
}

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194330)

Here we go... /.'s deepest ever thread!

1096

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194336)

1095

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194357)

1094

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194372)

1093

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194378)

1092

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194395)

1091

Re:Heist (1)

toddestan (632714) | about 11 years ago | (#7194401)

1090

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194462)

1089

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194469)

1088

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194482)

1087

Re:Heist (0)

Anonymous Coward | about 11 years ago | (#7194519)

1086

Re:Heist (1)

LeoDV (653216) | about 11 years ago | (#7194323)

Surely they only need 950 G5's, cause I could sure use a G5 and a hundred thousand bucks.

You know, to buy 22" LCD displays, iPods and Powermacs. And a Ferrari.

13:00? (0)

Anonymous Coward | about 11 years ago | (#7194254)

But its 16:10 over here! Please state what time zone it is!

holy (-1, Offtopic)

abstraxion (713100) | about 11 years ago | (#7194256)

Wow i posted on slashdot

Video? (0)

Anonymous Coward | about 11 years ago | (#7194263)

Posting video to slashdot, isn't that a bad idea?

Yes, but, (2, Funny)

Anonymous Coward | about 11 years ago | (#7194264)

can it defeat an iMac in Apple's Photoshop benchmarks ;-)?

Re:Yes, but, (0)

Anonymous Coward | about 11 years ago | (#7194277)

My Gxen2 0pt1m153d 4T470N 3xt3m3 3dit0n using -o9 --fun-rolls -mcpu=i1086 --with-bogomiperz w1th t3h g1mp 1.3.22 w1ll k1x it'z 4$$

MOD PARENT UP (0)

Anonymous Coward | about 11 years ago | (#7194417)

!. funny.

Twice as fast...? (2, Interesting)

suwain_2 (260792) | about 11 years ago | (#7194278)

...considerably more than doubling the performance of the current number 3 1152-node dual 2.4 GHz Xeon MCR Linux cluster.

If I understand this correctly, it's saying that a G5 is more than twice as fast as a dual 2.4 GHz Xeon? (1152 dual 2.4 GHz Xeons vs 1100 dual 2.0 GHz G5s -- there are fewer G5s and they run at a slower clock speed.)

This is a pretty staggering statistic. I hadn't really believed the hype about how fast the new G5s were.

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194296)

Don't get all crazy trying to match clock speeds as comparison when they are two totally different chip architectures

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194368)

Ohhh, really? I think someone is a little bit threatened by the lack of superiority of their chosen hardware...joking aside, four months ago, it was the exact opposite argument...Besides, the Xeon's are higher Ghz and still get smoked.

Re:Twice as fast...? (1)

Genady (27988) | about 11 years ago | (#7194303)

No, they're saying this cluster is twice as fast as the other one. You can't boil these numbers down to the processor level. Doing so is overly simplistic.

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194365)

Away with your silly details and logic, the maccies have something to masturbate to!

The best part is that they usually have a G3 or a G4, but for some reason derive sexual pleasure that someone else's G5 computer is 73H F457357 3V4R!!1! when you put really odd constraints, like not using the right compiler, or only using this set of photoshop filters, and not those, etc. etc.

It's fun to sit back and watch them disprove their previous crowing about how the G4 was supposedly the fastest. Now they admit (by the numbers) that it's a dog, oh but the G5 now, honestly this time, for a change, we're not lying....

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194342)

Ummm they are using 10TB of RAM, the Xeon machine only has 4.2TB. Also the Xeon machine is 18months old which means that it is 1/2 as fast as current technology.

This is like comparing a P4-3.2GHz with a G4-866MHz.

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194351)

I'd still take the G4 over the P4...

Re:Twice as fast...? (1)

ErnstKompressor (193799) | about 11 years ago | (#7194399)

Seeing as the Xeon was a 2.4 Ghz and that the fastest Xeon is now 3.2 Ghz, It would only be .8 Ghz faster or approx. 33% faster which would still leave it behind the 2 Ghz G5's, if they truly were twice as fast...which I will not begin to argue here as I have yet to use one myself...

Happy Sunday :) "~~~" you out there?

Re:Twice as fast...? (2, Informative)

adam872 (652411) | about 11 years ago | (#7194343)

The two clusters are different enough that making accurate comparisons is difficult. The new G5's have a more recent PCI architecture, they use Infiniband as the interconnect and it's possible that they made use of the AltiVec (though I hear that this may not be the case because of 32 bit limitations). I believe none of these apply to the Xeon's. In high speed computing, the interconnect is vital, so that alone may push this cluster ahead for the time being. I don't doubt that the individual G5 processor are bloody quick (and as a Mac user and fan, I'm kinda glad) though.

Re:Twice as fast...? (0)

Anonymous Coward | about 11 years ago | (#7194391)

The 17 TFlops value can either be Rmax or Rpeak.
I guess it is Rpeak. If I am right this machine would be only third in the Top500 June list.

Also 17 TFlops / 2200 means that each processor makes 7GFlops. This would problably be "2 multiply and two accumulate" at 2GHz.

The 2.4GHz Xeons were able to perform 4.8GFlops each since the Linux Networx cluster has Rpeak=11060.
This is coherent with the speed of SSE2. The operation that makes "2 multiply and two accumulate" takes 2 cycles on a Xeon.

As you can see, it is reasonable to think that the 17 Flops value is an Rpeak value. Therefore, this machine is NOT twice faster than the Linux Networx cluster. It is 1.5 times faster, which is quite impressive anyway.

Re:Twice as fast...? (1)

Halo- (175936) | about 11 years ago | (#7194496)

As a lot of others have pointed out, there is a lot more to "speed" that the frequency of the clockchip. I use a lot of IBM "P-series" (what used to be called RS/6000) machines at work. The clock speeds are generally low (sub 1Ghz) but in certain situtations these machines absolutely smoke. In other situtations, such are running Java, they drag ass. A lot has to do with how well the application using the processor takes advantage of the low-level capabilites.

Think of computers like cars. The Honda S2000 only has between 2 and 2.2 liters of displacement, but it will smoke most other cars which displace equal amounts because of how it is tuned, geared, built, etc...

More clock speed is in many respects a cop-out when it comes to performance. Faster chips give you faster code, but as the chips get faster, the code gets slower. Moore's law applies to hardware, not software.

Man, did I get off-topic or what? Anyway, in summary: yes, the G5 is faster clockwise, but there are a lot of other factors.

To quote an old gabber tune... (0)

Anonymous Coward | about 11 years ago | (#7194285)

- "That's kinda fast.."

- "Kinda fast? It's FUCKING FAAAAAAST!!!!!"

Dear God, (0)

Anonymous Coward | about 11 years ago | (#7194287)

please send me one of these for christmas.

Thank you

How much power ?!?! (0)

Anonymous Coward | about 11 years ago | (#7194289)

From the article:
"project involved 1,100 brand new Apple G5 towers"
and
"uses the same amount of electricity as 3,000 average sized homes".

So each G5 consumes almost as much as 3 houses? Surely a G5's power requirements are more like 5~10% of a house, so the rest must all be going on networking and cooling? I think someone's got their numbers wrong...

Re:How much power ?!?! (1)

Rand310 (264407) | about 11 years ago | (#7194470)

Air Conditioners, switches, etc....

more than just CPUs

Imagine... (-1, Redundant)

techmuse (160085) | about 11 years ago | (#7194293)

Imagine a Beowulf cluster of these... ;)

Re:Imagine... (1)

the_2nd_coming (444906) | about 11 years ago | (#7194370)

oh wait.

interesting reactions (0)

Selecter (677480) | about 11 years ago | (#7194300)

Well, the G5 has certanly stirred the pot. First all the anti mac crowd say it's not as fast as Apple said it was and that Apple used cooked Spec_2000 benches. Then PC Magazine comes along and says that it's faster or as fast as anything available on X86. Now this. I dont think anyone expected this cluster to place second in the world - further proof that the G5 has what it takes. I kinda almost feel sad for the appple bashers. One by one they are losing all their tired outdated reasons to bash Macs. About all they can come up with now are lame troll posts.

oh my god... (1)

jx100 (453615) | about 11 years ago | (#7194317)

The BBC page of the devil!!

(look at the link URL)

There was a reception yesterday (1)

mcknation (217793) | about 11 years ago | (#7194318)


For all the people involved in it's construction. I helped in the construction. Wouldn't have known about it if not for the Slashdot article. I don't doubt the Linpack score. Allthough the e-mail I got about the reception said the score wasen't supposed to come out for another week or so. Anybody know what went on in the reception?

mck

How fast can it copy a 17mb file? (1, Funny)

Anonymous Coward | about 11 years ago | (#7194319)

That is the true test.

Re:How fast can it copy a 17mb file? (0)

Anonymous Coward | about 11 years ago | (#7194353)

it takes longer than 20 minutes

Re:How fast can it copy a 17mb file? (0)

Anonymous Coward | about 11 years ago | (#7194410)

Wow, that's longer than my old 386DX-33 running MS-DOS 5.0!

They will not submit the score (-1, Flamebait)

Anonymous Coward | about 11 years ago | (#7194320)

Because Apple probably forced them to use a fake test to make themselves look better.

It runs MacOS X !!! (0)

Anonymous Coward | about 11 years ago | (#7194324)

I watched on BBC World.. they are using MacOSX, so this will implicitly run FreeBSD. They also mentioned they are going to document everything and put it up online.

Re:It runs MacOS X !!! (3, Informative)

paulthomas (685756) | about 11 years ago | (#7194416)

Ugh.

It has been said thousands of times by now I'm sure.


Running Mac OS X does not mean running FreeBSD Mac OS X is a system of frameworks running on top of a Mach Kernel. The only thing that relates Mac OS X to FreeBSD is the userland. In addition to the userland you have: Cocoa, Carbon, Aqua, Java, etc. The FreeBSD portion is minimal.

And yes, if you want you can run this lower level unix without the rest of Mac OS X. It is called Darwin [apple.com] . It runs on Intel and PPC if you're wondering. No, this doesn't mean that Mac OS X runs on both or ever will.

Here is a short description of the BSD families [daemonnews.org] .

17.6 Teraflops? That's almost a Hollywood (0)

Anonymous Coward | about 11 years ago | (#7194327)

2 thumbs down = 1 raspberry
1000 raspberries = 1 critic
1000 critics = 1 magazine
1000 magazines = 1 flop
100 flops = 1 Oscar
100 Oscars = 1 Hollywood
So Hollywood runs around 20 trillion flops.

I wonder... (0)

Anonymous Coward | about 11 years ago | (#7194341)

...how many BogoMips does it do?!

Cluster problem. (1, Funny)

Anonymous Coward | about 11 years ago | (#7194348)

I don't wan't to start a holy war here, but what is up with you G5 cluster zealots? Ive been sitting at my freelance gig of a G5 cluster (1200 Dual G5s) for twenty minutes as it attempts to copy a 17 megabyte file from one folder to another! Twenty minutes! At home my Beowulf cluster of 100 Celerons running Linux, the same operation takes just 2 minutes, if that. While this is happening, Itunes won't work, and everything else grinds to a halt. Even vim is struggling to catch up as I type this.

Yes, I do have DMA enabled, and I am using 25K SCSI disks. My old 3.2 Ghz 64 way xeon runs faster than this G5 cluster at times. G5 zealots, flame me if you like, but I'd rather hear some intelligent reasons why I should use G5s over faster, cheaper clusters.

Re:Cluster problem. (0)

Anonymous Coward | about 11 years ago | (#7194366)

I say! Poetic beauty the likes of which I have hardly before seen on Slashdot. You will not escape the threat of downward moderation, good chap, but you should be praised to the heavens.

Re:Cluster problem. (0, Offtopic)

FosterKanig (645454) | about 11 years ago | (#7194369)

Damn. No mod points. Excellent use of a troll post.

Re:Cluster problem. (1)

the_2nd_coming (444906) | about 11 years ago | (#7194405)

and I am one of the privileged that can say "I was there when this famous troll was first posted!!"

it is nice to see it being used so often :-)

Re:Cluster problem. (1)

Morky (577776) | about 11 years ago | (#7194520)

This is not a troll. This is some funny shit.

clicky here (-1, Troll)

Anonymous Coward | about 11 years ago | (#7194364)

More pictures of the apple cluster [goatse.cx]


- Only fools would visit!

I'm new! (-1, Troll)

Captain Goatse (715400) | about 11 years ago | (#7194367)

Imagine a beowulf cluster of Macs jerking off to... me.

Mmm...

Re:I'm new! (-1)

Rectal Examination (711652) | about 11 years ago | (#7194481)

I'm new!

Welcome. May your stay be as enjoyable as having a giant diamond-tipped dildo wrapped in glasspaper shoved up your ass!

New top-500 list will be announced around Nov 18 (3, Informative)

slyfox (100931) | about 11 years ago | (#7194375)

The new "top 500" list will be announced right before SC2003 [sc-conference.org] and discussed in detail at a session of SC2003 on November 18 [sc-conference.org] .

Look for another (less speculative) story on Slashdot around then.

Are they all running Panther? (1, Flamebait)

failedlogic (627314) | about 11 years ago | (#7194383)

What's been left behind is wether or not these systems are using Panther as the OS. It would seem that with this kind of performance, an Apple supplied OS -- as opposed to Yellow Dog would -- only be capable of performing well on the G5 since Panther has processor optimizations for the G5.

If the original XServers were too costly and low performance (since they came with a G4) wouldn't a G5 server (since the performance is apparently much better) be a great option for small/medium size businesses for a web/mail/database server?

Re:Are they all running Panther? (1)

ivan256 (17499) | about 11 years ago | (#7194497)

-- as opposed to Yellow Dog

This bothers me as much as people synonymizing Red Hat with linux for x86, and Internet Explorer with the internet; and yes, you sound just as dumb when you jump into a discussion on PowerPC based supercomputers running linux and equate the entire PowerPC world with Yellow Dog as somebody who jumps into a conversation about the internet and equates it with AOL version 7.0.

Just FYI, Red Hat is the only major linux vendor out there that doesn't support PowerPC. Very few people use Yellow Dog when they run Linux on their Mac. Most, in my experience, tend to run Debian or Suse. The proper way to describe Linux that is run on a PPC processor is "Linux", "LinuxPPC", or "PowerPC Linux". Now, armed with this knowledge you can at least pretend to know what you're talking about in this discussion without being ignored.

Re:Are they all running Panther? (1)

Maserati (8679) | about 11 years ago | (#7194523)

No, the G5s shipped with 10.2.7, it's recompiled for the G5 to take advantage of the new architecture - should be reasonably optimized although that probably isn't a priority yet - and has some 64-bit support. Yellow Dog Linux is ready for the G5, but their support is only as good as gcc at this point.

Doubling the second fastest? (1)

}{@wkmooN (101161) | about 11 years ago | (#7194385)

considerably more than doubling the performance of the current number 3 1152-node dual 2.4 GHz Xeon MCR Linux cluster.

Humm, isn't the second fastest ASCI Q at Los Alamos has now been measured with 13.88 TF/s?
As mentioned here: http://www.top500.org/lists/2003/06/top5.php [top500.org]

High speed interconnect? (1)

draziw (7737) | about 11 years ago | (#7194402)

MCR uses Quadrics - What does this cluster use?
http://doc.quadrics.com/Quadrics/QuadricsHom e.nsf/ DisplayPages/7C18E51DBC215D3E80256D5900535959

Infiniband (1, Informative)

Anonymous Coward | about 11 years ago | (#7194422)

10 Gbps Infiniband from Mellanox

Each machine has a PCI-X Infiniband card, interconnected with several 96-port switches.

5.2 million (1)

cacheMan (150533) | about 11 years ago | (#7194418)

Could someone who knows the going rate of these top 5 supercomputers please tell me how much less expensive 5.2 million is? I know that it sounds like a lot of money to me, but I'm guessing that it is orders of magnitude cheaper than the other top computers.

Re:5.2 million (1)

cacheMan (150533) | about 11 years ago | (#7194452)

From this article: zdnet.co.uk [zdnet.co.uk]

"Sun Microsystems, for instance, is designing a supercomputer under a $50m (31.6m) grant from the US Defense Advanced Research Projects Agency (Darpa) that will contain 100,000 processors, according to Jim Mitchell, who heads up Sun's labs. The whole thing could conceivably fit into a room."

5.2 million is a lot less then 50 million.

Pains a Mac user (1)

mariox19 (632969) | about 11 years ago | (#7194429)

The video is available for either Windows Media Player or RealOne Player -- but not QuickTime! [apple.com]

Ouch!!!

So? (0)

Anonymous Coward | about 11 years ago | (#7194441)

Who cares?

No QuickTime? (0)

Anonymous Coward | about 11 years ago | (#7194448)

You'd figure that with all of those G5s, that they might buy one Mac to make Quicktime movies.

But it doesnt add up...? (1)

skinfitz (564041) | about 11 years ago | (#7194506)

I didn't see anywhere the source of these benchmarks - I believe what they have done is multiply the SPECfp_rate_base2000 for a dual processor 2GHz G5 (which according to Apple is 15.7) [apple.com] and multiply it by 1100.

The thing is, that only comes to 17.27TFLOPS, and in addition it does assume that the original spec scores were accurate. [theregister.co.uk]

Would anyone care to shed some light onto this?

Not that simple... (0, Offtopic)

wiresquire (457486) | about 11 years ago | (#7194517)

Quoting one paragraph out of context of the contract tells you jack squat.

The section could start off with "The following will not apply". Unlikely, but I've seen one contract that flipped negatives 3 times.

In most of the contracts I've seen, the key section would be the one on termination which outlines what survives and what doesn't. And the definitions section is usually pretty important too. Like the definition of SOFTWARE PRODUCT. I'd expect that to be the Unix source code that AT &T provided to them.

All this says is that they could terminate the contract.So, excuse me if I don't take the word of a public relations dude.

(No, IANAL, but I've had to deal with some of that stuff).

How they calculated the 17.6 tflops number.. (0)

Anonymous Coward | about 11 years ago | (#7194518)

Ok, each G5 is able to do 2 fused 64 bit mulAdd instructions/cycle.

Now.. counting mulAdd as two floating point operations, you get 4 flop/mhz... The dual G5 is running at 2 Ghz...

2Ghz*4*2, since you got a dual.. Thats 16Gflops for each Powermac... you got 1100 of those..

1100 * 16=... 17.6 TFlops

Rumors of problems... (0)

Anonymous Coward | about 11 years ago | (#7194521)

There are rumors moving around campus of big problems with the infiniband and are instead having to use the regular ethernet connections on the boxes. As you might have guessed, no one is talking about it except behind closed doors, but the people I've talked to are intimately familiar with the problems...
I have also heard that the the numbers were taken for the Oct. 1 deadline, but that there is a 2 week "revision" period that is allowed, so VT is now working to get everything back up to par so that they can have a place in the top 5. My best guess is that the numbers quoted to the BBC are extrapolated from the benchmarks that were initially run for the first deadline.

17.6 Tflops sounds more like an Altivec number (0)

Anonymous Coward | about 11 years ago | (#7194522)

I suspect the 17.6 Tflops figure is produced using Altivec, which (if true) is certainly misleading.

But then again, what else would you expect from Apple?
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?