PDA

View Full Version : Virginia Tech Cluster Moving to Xserve G5s


MacRumors
Jan 15, 2004, 04:07 PM
ThinkSecret provides (http://www.thinksecret.com/news/virginiatech2.html) some confirmation on earlier rumors (http://www.macrumors.com/pages/2004/01/20040112042242.shtml) that Virginia Tech will be migrating from PowerMac G5s to Xserve G5s in their recently assembled Supercomputer cluster.

MacRumors has also received multiple confirmations of the planned upgrade, but varying reports as to the fate of the original PowerMacs used in the cluster. According to ThinkSecret, Apple will be providing a one-to-one tradein for the PowerMacs with Xserves.

As one reader (suzerain) noted, Srinidhi Varadarajan had stated (http://www.tombridge.com/rta/2003/10/tencon_keynote__1.html) in October that "We are planning on moving to ECC systems in the future", suggesting that the upgrade has been planned for some time. Apple's recently released Xserve G5s support ECC memory, while the PowerMac G5s do not.

notjustjay
Jan 15, 2004, 04:14 PM
Does this mean we're going to suddenly see an onslaught of refurbished G5's on the Apple store? :)

jouster
Jan 15, 2004, 04:15 PM
Understandable. I guess this was part of the original deal: hurry them out so they get ranked and boost Apple, then build the *real* cluster.

nagromme
Jan 15, 2004, 04:18 PM
This is probably how Apple "worked with them" to give them a deal. Instead of volume pricing, they paid full price with a trade-in plan. Makes sense all around.

It may be sad to see Big Mac 1 go, but "Big Mac 2" will have real estate to keep growing!

Meanwhile, it's good PR for Apple that VT was forced to use desktops: they're the big sellers, and people like the idea that their tower is the same one used in a famous supercluster.

And now Apple will have a proven LARGE-SCALE Xserve G5 installation. Very comforting to future buyers.

(Personally I'd have waited for a G6 or higher GHz... but that probably wasn't the deal.)

Omad0n
Jan 15, 2004, 04:20 PM
Sorry I don't know much about how these things work. Is the main advantage to doing this a space and heating issue? Or is there something that makes a Xserve faster in this then a normal dual G5 would be?

waterbug
Jan 15, 2004, 04:22 PM
Does this mean we're going to suddenly see an onslaught of refurbished G5's on the Apple store
Maybe a few, but remember that Apple sold over 200,000 PMG5's last quarter. Having another 1,000 isn't going to change things much.

acj
Jan 15, 2004, 04:24 PM
That was a short lived supercomputer

notjustjay
Jan 15, 2004, 04:24 PM
True. But those 1,100 PM's aren't going to be resold as new (one would think)... and while I haven't really flipped through all of the refurbished gear on sale at Apple.com, I would expect that adding 1,100 used dual G5's is going to be at least somewhat significant.

Wish I could afford one of them, in any case.

slowtreme
Jan 15, 2004, 04:30 PM
1100 refurb G5s for sale, I could get in on that deal.

johnnyjibbs
Jan 15, 2004, 04:41 PM
Didn't they build a whole new building and heatflow system especifically for the G5s? Wouldn't that have been one huge waste if they were just going to swap to the smaller and more compact Xserves?

phillymjs
Jan 15, 2004, 04:42 PM
...if they sold the old machines on eBay. Engrave a number somewhere, slap a Certificate of Authenticity in the box, and sell the G5s as "a piece of computing history, a fully-functional component of the third-fastest supercomputer in the world! Only 1100 available!"

I'm sure there are some Mac fanatics who'd pony up the bucks to own one. :)

~Philly

andyduncan
Jan 15, 2004, 04:42 PM
Originally posted by Omad0n
Sorry I don't know much about how these things work. Is the main advantage to doing this a space and heating issue? Or is there something that makes a Xserve faster in this then a normal dual G5 would be?

The lack of error correcting code ram is a big issue depending on what you're doing. Varadarajan mentions offhandedly in the article that "They may have to run things twice for a bit." This is to make sure they got the right answer.

So for benchmarks, where they already know what the answer should be, they probably aren't getting much improvement (we've yet to see if the Xserves are faster than the desktops for other reasons) but for some (many?) types of real-world use ECC is a huge benefit.

arn
Jan 15, 2004, 04:47 PM
Originally posted by johnnyjibbs
Didn't they build a whole new building and heatflow system especifically for the G5s? Wouldn't that have been one huge waste if they were just going to swap to the smaller and more compact Xserves?

according to the article, the xserves will swap in fine.

arn

nmcphers
Jan 15, 2004, 04:47 PM
I gave this story a negaive review. I hate when a story title states something as facts. Then goes ahead and quote "rumor" sites as legitimate news source.

iriejedi
Jan 15, 2004, 05:04 PM
Now I know why my BRAND NEW G5 had VT Rules! carved into the side. They should put them in student labs and chuck out 1100 window's machines!!!!!!! Donate those Wintel boxes to charity for a nice tax write off!

Kidding.. but while a cheaper referb would be nice - I still think a new dual 3 gig would be better... ok 2.8 gig... oh okay 2.4 gig... oh all right... a new dual 2.05 gig the real upgrade next week. 50 more mhz per processor. Cross your fingers!


Seriously though, What is EEC memory and why is it not part of the G5 Powermac?

T.Rex
Jan 15, 2004, 05:05 PM
What a tremendous waste of time. They spend countless days and sleepless nights to get this thing together, spend weeks if not months to finally get it running at top efficiency, just to tear it all down and start again? I would be pretty angry if I were one of the students who volunteered their time to assemble this thing when the administration knew full well it was only going to be around for a few months for the sole purpose of getting them on the supercomputer list this year simply to satisfy their own ego's.

Foxer
Jan 15, 2004, 05:06 PM
Originally posted by nmcphers
I gave this story a negaive review. I hate when a story title states something as facts. Then goes ahead and quote "rumor" sites as legitimate news source.

The site, as you can read at the top of your page, is called MacRumors.com - FYI.

geerlingguy
Jan 15, 2004, 05:07 PM
Originally posted by johnnyjibbs
Didn't they build a whole new building and heatflow system especifically for the G5s? Wouldn't that have been one huge waste if they were just going to swap to the smaller and more compact Xserves?

If they already had knowledge of the trade-in, I am sure they designed the building with adaptability for the Xserves. Plus, if you look at the video on Apple's website, it looks like the racks are open on both front and back, and the InifiniBand routers have space above for two or three more routers, so you could have 42 Xserves per rack instead of the 12 G5s and still have enough Infiniband interconnects...

What I think is most awesome about this rumor (if true - :rolleyes: ) is the option of VT to just buy an extra 10, 20, 100, or 500 in a heartbeat to increase speed by whatever factor they want. Also, when the faster G5s are announced, they can just stick 'em in the rack and all will be fine! :D

El Tritoma
Jan 15, 2004, 05:11 PM
Originally posted by T.Rex
What a tremendous waste of time. They spend countless days and sleepless nights to get this thing together, spend weeks if not months to finally get it running at top efficiency, just to tear it all down and start again? I would be pretty angry if I were one of the students who volunteered their time to assemble this thing when the administration knew full well it was only going to be around for a few months for the sole purpose of getting them on the supercomputer list this year simply to satisfy their own ego's.

I'll bet you are an English major with a writing assignment in which you must attempt to use irony and sarcasm. At least I hope you are.

oliverlubin
Jan 15, 2004, 05:13 PM
think about it like this maybe.

apple's rumored to be revamping the entire line soon...with some people guessing the base line is 2.0ghz.

what are the chances they use these machines for "parts" to make those new low-end machines. while this isnt the same chip as the 90nm G5 that's in the xServe, it could be the chip that apple decides to use in the low end system to save cost.

single 2.0 using 130nm G5 and NON-EEC memory
dual 2.2 and 2.4 using 90nm G5s and EEC memory for the 2 higher end machines.

would justify higher costs of higher-end machines and allow apple to re-use these "old" parts.

id say this idea is unlikely but i guess it's a thought. and someone already pointed out, apple shipped over 200k machines this quarter, so 1100 really is a drop in the bucket now that the dual 2.0 is in full production and quick availability.

T.Rex
Jan 15, 2004, 05:34 PM
Originally posted by El Tritoma
I'll bet you are an English major with a writing assignment in which you must attempt to use irony and sarcasm. At least I hope you are.

Actually, I try to refrain from using sarcasm as I find it is lost on all but those who equal your obviously superior intellect.

Sabbath
Jan 15, 2004, 05:35 PM
I dont think Apple could use these used units to make up ones, surely they would be forced to state them as at least partly refurbished for legal reasons. It would make more sense if they already had some places to take them, ie maybe a few eductaion, government or business orders.

On another hand if we're expecting a powermac update soon, how will these extra rev. A products affect this. I expect it means we will definitely not see a dual low end, as that would lower the price of these products too much. Apple could likely sell them as refurbs at a price above the new base model if its a single 2GHz. I hope it doesnt mean they restrict the low end G5 too much, although common sense would say theres only 1,100 of these so too much importance shouldnt be assigned to them. Especially after the amount of good publicity they have generated for Apple.

One final option give me 1 :D or 10!

johnnowak
Jan 15, 2004, 05:37 PM
I hope they inscribe some special Virginia Tech logo on the side and sell them as special editions!

"Your very own supercomputer."

MMmmm.

Rincewind42
Jan 15, 2004, 05:47 PM
Originally posted by T.Rex
What a tremendous waste of time. They spend countless days and sleepless nights to get this thing together, spend weeks if not months to finally get it running at top efficiency, just to tear it all down and start again? I would be pretty angry if I were one of the students who volunteered their time to assemble this thing when the administration knew full well it was only going to be around for a few months for the sole purpose of getting them on the supercomputer list this year simply to satisfy their own ego's.

I wouldn't call it a waste of time by any measure. If they hadn't built the cluster for the Oct deadline, then they wouldn't be able to get funding for it for at least 6 months. And if they hadn't built the cluster at all, then they wouldn't have the experience and software to support the cluster now. So while the physical labor may become wasted, such labor tends to be wasted in the long term anyway (just think of how much is destroyed/rebuilt in any city over the centuries).

And if I was a student at VT I would like at this as a chance to get more free pizza :D

Rincewind42
Jan 15, 2004, 05:50 PM
Originally posted by johnnyjibbs
Didn't they build a whole new building and heatflow system especifically for the G5s? Wouldn't that have been one huge waste if they were just going to swap to the smaller and more compact Xserves?

They did build up a certain amount of heatflow for the PowerMacs, however they same technology would still be needed for Xserves, because while each unit produces less heat, there are a LOT more units per unit area with Xserves than with PowerMacs, so the cooling system would actually need to be more powerful (although over a smaller area) for the Xserves. Although overall the power usage would be less.

MacEyeDoc
Jan 15, 2004, 05:54 PM
if VT (and Apple) know that 2.6 or 3.0's won't be in the Xserves anytime soon. Why would you exchange all those boxes for ones of the same speed 4 months after you set it up? Better to wait another 6 months, and get the 3.0's (Steve-o did say summer 2004, didn't he?), and still have time to place #2 in the next supercomputer rankings next fall.

Of course summer on Apple time is more like late September, early October . . .

Maybe ECC memory is a big deal at that level. And they will have lots of extra room to add more Xserves.

Who wants pizza?

Counterfit
Jan 15, 2004, 05:55 PM
Originally posted by oliverlubin
dual 2.2 and 2.4 using 90nm G5s and EEC memory for the 2 higher end machines. We're not going to be seeing ECC (Error Checking Code) RAM in a desktop G5, or any Mac for that matter, Simply because it's slower than non-ECC RAM.

ginoledesma
Jan 15, 2004, 06:09 PM
REFURB! REFURB! REFURB!... There, I got it off my chest. :D

Come to think of it, 1100 units isn't too many in light of the 200,000+ units Apple pushed last quarter, but it will probably fill up Refurb stocks for quite some time. And if they DO slap on a "certification" of some sort on the G5 casing (perhaps laser engraving ala iPods), they'd make someone happy. "This unit was part of the legendary Big Mac that made the Top 3 SuperComputers."

If they do a straight 1-to-1 swapping of PowerMac G5s to Xserves, there'd be quite a LOT of vacant (physical) space in their cluster. The dimensions of each PowerMac G5 is, based on specs, 20.1"x8.1"x18.7x" (51.1cm x 20.6cm x 47.5 cm), and each Xserve is about 1.73"x17.6"x28" (4.4 cm x 44.7 cm x 71.1 cm). Now, basing on just the pictures available on the net (since I can't find the dimensions of the racks they used), the Xserves are slightly deeper by about 10" (28" vs. 18.7"), so there'll be about something almost as long as a ruler protudring from the back of the racks. But, using the existing rack setup, they'd be able to stack at most a dozen Xserve in each of the 3-node pack. Assuming each rack contains 4x3 rows, that would be 48 Xserves in each rack compared to the 12 PowerMac G5s in reach rack! That's 4x more power in one rack! :D And furthering these assumptions, at 1100 PowerMac G5 units, they'd be using about ~92 racks (1100 units / 12 units/rack rounded up). Using Xserves, they'd be using only ~43 of the 92 racks they have. Perhaps they'd be jumping to a 2200-node cluster soon? :D

Of course, these are all "max" assumptions. They may as well put in PCs there or relocate the racks elsewhere (though that'd mean more vacant space in their cluster), or most likely spread out the Xserves for easier maintenance.

Since they'll be moving to Xserves, each of those G5s are _fully loaded_. I doubt that they'll be keeping all of the parts used, except perhaps for the Mellanox interconnects. Each node has 4GB of RAM (4x1GB) and 160GB of SATA Storage. Selling a PowerMac G5 with that even at refurb is overkill for most, so they might be breaking them down into smaller, more manageable chunks.

Of course, another likely scenario is to sell these cheaper to another institution that wants to build a supercomputing facility. At least they've been guaranteed to work.

vitaboy
Jan 15, 2004, 06:10 PM
Not only slower, but much, much more expensive. For consumer or even for most workstation applications, there really isn't a need for EEC memory.

ginoledesma
Jan 15, 2004, 06:14 PM
In addition to a cooling system, perhaps they need a solution to lessen the noise generated by the Xserves? One Xserve alone screams by itself. What more of an orchestra of 1100 screamers? :eek:

IndyGopher
Jan 15, 2004, 06:16 PM
Originally posted by El Tritoma
I'll bet you are an English major with a writing assignment in which you must attempt to use irony and sarcasm. At least I hope you are.

No, if he were an English major, he would have known that plurals don't use apostrophes. (re: "ego's")

rdowns
Jan 15, 2004, 06:20 PM
Originally posted by Sabbath
I dont think Apple could use these used units to make up ones, surely they would be forced to state them as at least partly refurbished for legal reasons. It would make more sense if they already had some places to take them, ie maybe a few eductaion, government or business orders.

On another hand if we're expecting a powermac update soon, how will these extra rev. A products affect this. I expect it means we will definitely not see a dual low end, as that would lower the price of these products too much. Apple could likely sell them as refurbs at a price above the new base model if its a single 2GHz. I hope it doesnt mean they restrict the low end G5 too much, although common sense would say theres only 1,100 of these so too much importance shouldnt be assigned to them. Especially after the amount of good publicity they have generated for Apple.

One final option give me 1 :D or 10!

Give me a break. Do you really believe Apple having 1,100 machines to sell as refurbs would affect what speed bumped configurations they would release? Apple is known for head up it's ass marketing but even this is beyond them.

iomar
Jan 15, 2004, 06:21 PM
That is nice of Apple! I hope Apple is not charging them for it.

isus
Jan 15, 2004, 06:31 PM
atat did an article about this... they did the math, and i think they said that switching to xserve's would save them a lot of space... the xserve's take up 33% or something?

i can't find that article right now, but...

Macmaniac
Jan 15, 2004, 06:38 PM
I'd buy a refurb G5 from VTech! Especially if there was engraving! Price em at $2500 and that would be sweet!!!

hexor
Jan 15, 2004, 07:16 PM
Originally posted by vitaboy
Not only slower, but much, much more expensive. For consumer or even for most workstation applications, there really isn't a need for EEC memory.

I just looked up 1Gb 400Mhz PC 3200 ECC $428.. not too bad.. Are there any stats to show how much more reliable using ECC would be? Maybe it would be worth it...

AidenShaw
Jan 15, 2004, 07:24 PM
Originally posted by vitaboy
Not only slower, but much, much more expensive. For consumer or even for most workstation applications, there really isn't a need for EEC memory.


Check a site like http://www.crucial.com/store/listmodule.asp?module=DDR+PC3200&Attrib=Package&cat=RAM, you'll see about a 20% extra tax for ECC.

Only $40 per gig to have the peace-of-mind that you won't have random crashes or corruptions....

As to performance, most reports say 1% to 2% performance difference with ECC (see http://www.computer-memory-upgrade-stick.com/ecc-vs-non-ecc.htm for more info).

ZildjianKX
Jan 15, 2004, 07:46 PM
Setting up the intitial G5 cluster seems like a huge waste of time now. Obviously it didn't have ECC memory before, which surprised me that they would even use DP 2.0 G5s then. Now it all just seems like a big Apple publicity stunt.

legion
Jan 15, 2004, 07:58 PM
Originally posted by Counterfit
We're not going to be seeing ECC (Error Checking Code) RAM in a desktop G5, or any Mac for that matter, Simply because it's slower than non-ECC RAM.

close... ECC is Error Correcting Code.

Rex44
Jan 15, 2004, 08:17 PM
Given the notoriety the Virginia Tech project has received, maybe Apple could sell the old G5s on eBay for 1100 small fortunes?

nagromme
Jan 15, 2004, 08:17 PM
Big Mac 1 was not a waste. VT had two deadlines (one for funding, one for the prestige of the Top 500 list) that were not their own doing. The deadlines are a shame, maybe, but not in VT's control. They had VERY good reasons for finding WHATEVER was best to meet those deadlines. It was PowerMac G5s. If, in the process, they negotiated for something more compact (and ECC) down the road, then that too makes sense. They can judge for themselves if the re-install is worth the benefits or not. Looks like it's worth it.

Think how much bigger the cluster could grow now, in the same installation with the same cooling? 12 PowerMacs in a rack... or 42+ Xserves. That's 2/7 the space!

That means VT will now have room in the same racks for at least 3 and a half Big Macs... probably more.

So... why wait for higher GHz? VT can ADD faster Xserves any time, and keep the old ones too!

El Tritoma
Jan 15, 2004, 09:15 PM
In the real world, unfortunately, very few things have the chance to be done right the first time. This is especially true when you are after funding. The NSF, NASA, and other government funding sources are probably right now making decisions about next year's budget. VT would have lost much more than a few months of work. They would have, effectively, lost about one and a half years if they had waited. The primary goal had to be that they needed to impress some people, and it didn't matter that it wasn't the perfect solution. It was a solution, it was good enough to probably get enough money and attention that they could then continue what they want/need to do. I would be amazed if VT was not thinking about the servers last year. It did not take much imagination to realize that G5s would make it into the servers as soon as possible. Apple, first though, had to do something about the pent-up demand for desktop machines. They could not afford to ignore this. It was not a waste of time. Apple and VT, last summer, had to have formulated a more satisfactory solution than jamming a bunch of desktop machines into a room to build a supercomputer. Just think about that! No reasonable person could have thought they weren't going to redo things. I doubt very much if the VT students think they were wasting their time. They are engineers! They are smart young people. Surely they could figure out that this was only a temporary solution. Besides, wouldn't you just love to be in college at VT and have a chance to put together a world-class supercomputer, and get free pizza and soda!? It would be something to always remember and brag about! It was not a waste of time. Everyone went into it with their eyes wide open knowing what would happen when G5s were put into servers.

ClimbingTheLog
Jan 15, 2004, 09:23 PM
Originally posted by T.Rex
What a tremendous waste of time. They spend countless days and sleepless nights to get this thing together, spend weeks if not months to finally get it running at top efficiency, just to tear it all down and start again? I would be pretty angry if I were one of the students who volunteered their time to assemble this thing when the administration knew full well it was only going to be around for a few months for the sole purpose of getting them on the supercomputer list this year simply to satisfy their own ego's.

They'll probably have a few work-study students install the new units, a few at a time. I bet two students could easily do 3 an hour, a couple hours a day, over a few months; no need for another army. The cluster can keep on humming all the while.

ClimbingTheLog
Jan 15, 2004, 09:27 PM
Originally posted by MacEyeDoc
Maybe ECC memory is a big deal at that level.

Yeah, the cluster shoudl be twice as fast for real work. I bet they didn't do it for the benchmarks, but in real usage they need to run jobs twice, to make sure there weren't memory errors.

With ECC you need only run it once. Maybe throw in 1/100 duplicates for good measure, but not every work unit.

i_wolf
Jan 15, 2004, 09:28 PM
The G5 powermac doesn't need ECC ram. This ram is only required usually for servers or clusters. Usually it carries much higher latency than standard ram meaning that it is slightly slower than standard ram. However in server and cluster environments it provides higher reliablility of data. For workstation apps like Maya, photoshop, Final Cut Pro etc... it would not benefit the G5 in any way at all.. if anything these apps would run slightly slower... because of the added latency incumbant with ECC ram.
However a cluster like virginia tech would benefit because presently part of their cluster is made up of software error checking to make up for the lack of ECC memory. This would slow the current set up down slightly ... i have no idea what difference it woudl make but it would slow it down some what. With the introduction of XServe's with ECC memory they could scrap the software ECC and could potentially gain a speed up since doing a software error check can be compute expensive. Just ot reiterate again though, for the Powermac there is no need to do error checking if anything having ECC memory would hampter its memory latency, it is mainly for server and cluster apps.

Phobophobia
Jan 15, 2004, 10:09 PM
Originally posted by T.Rex
What a tremendous waste of time. They spend countless days and sleepless nights...

Countless days? Are you still in first grade or something?

woodsey
Jan 15, 2004, 11:41 PM
I think they should leave in the PM G5s while they install the XServes so they will temporarily have the 2nd fastest supercomputer on earth!

fabsgwu
Jan 16, 2004, 12:41 AM
Originally posted by woodsey
I think they should leave in the PM G5s while they install the XServes so they will temporarily have the 2nd fastest supercomputer on earth!

Or trade them all in and double or triple the cluster with the space-saving XServes.

But I do agree that it is a publicity stunt or at least smart marketing for Apple--it puts the 4 month old news back at the top... Also, I'm sure the people who volunteered to set up the original G5s wanted to be there--it wasn't a waste of their time (some people in this forum should take a pill).

prb
Jan 16, 2004, 03:10 AM
(What a schmuck - I originally posted this to the wrong thread... Sorry)

To me, the most surprising thing about this is that Apple pitch the G5 desktops as viable servers without ECC memory. They won't get far in the corporate server market that way.

I've had the misfortune to administer servers without ECC in the past, and when memory cards start failing it can do some serious damage to the files (and the backups of them!) before you really notice.

As for the VT cluster, ECC is a really big deal... I currently work in an environment with about 200 Sun servers with between 600 and 800G of memory between them (all ECC) and on average we see a few log messages per month where the ECC has corrected a one-bit error and we have maybe half a dozen memory cards per year fail... Usually they degrade before they fail and we pick that up from the ECC corrections and swap 'em.

Assuming Apple non-ECC memory is about as reliable as Sun ECC memory (which seems fair), and scaling that up to the VT cluster of 2200G, they would be seeing a several memory errors every week but with no indication of where they were occuring... Hence the need to run jobs twice and check the results.

Final point: People assume they are going to rip the whole cluster apart and rebuild it. Very unlikely, I'd have thought: They're smart guys and it's a fault tolerant cluster so I'd imagine they'd do a phased replacement, say a cabinet at a time.... Take the G5's in that cab out of the cluster and swap for Xserves, unit test them, then re-introduce them to the cluster. Not much more performance degradation than a single G5 failing in service and having to be replaced.

Pete.

prb
Jan 16, 2004, 03:22 AM
Originally posted by i_wolf
The G5 powermac doesn't need ECC ram. This ram is only required usually for servers or clusters.

Absolute tosh.

Memory errors happen. A lot of the time they're harmless (who's going to notice 1 bit error in a huge photoshop image, especially if it only occurs once or twice a year?). But when memory starts failing, it can do a lot more damage to your files before you notice if there's no ECC.

The performance overheard of ECC is minimal, so it comes down to the question: Do you want to be sure your computer is giving you the right answers?

I know I do.

Pete.

krimson
Jan 16, 2004, 08:57 AM
Originally posted by AidenShaw
Check a site like http://www.crucial.com/store/listmodule.asp?module=DDR+PC3200&Attrib=Package&cat=RAM, you'll see about a 20% extra tax for ECC.

Only $40 per gig to have the peace-of-mind that you won't have random crashes or corruptions....

As to performance, most reports say 1% to 2% performance difference with ECC (see http://www.computer-memory-upgrade-stick.com/ecc-vs-non-ecc.htm for more info).

$40/Gig??

XForge
Jan 16, 2004, 10:52 AM
Originally posted by T.Rex
What a tremendous waste of time. They spend countless days and sleepless nights to get this thing together, spend weeks if not months to finally get it running at top efficiency, just to tear it all down and start again? I would be pretty angry if I were one of the students who volunteered their time to assemble this thing when the administration knew full well it was only going to be around for a few months for the sole purpose of getting them on the supercomputer list this year simply to satisfy their own ego's.

Ever build a hotrod? = )

T.Rex
Jan 16, 2004, 10:58 AM
Originally posted by Phobophobia
Countless days? Are you still in first grade or something?

What the devil are you talking about?

Geez people, I'm sorry I had a dissenting opinion about this. I forgot how everybody has to agree on everything in this forum or be ridiculed. I post one message how I think it was silly they did all that work just to have to do it all again and people jump down my throat.

And I thought PC users were intolerant.

Good riddance to you bunch.

wdlove
Jan 16, 2004, 11:33 AM
Originally posted by notjustjay
Does this mean we're going to suddenly see an onslaught of refurbished G5's on the Apple store? :)

This is great news for Apple, another big sale. Just hope that it will encourage many other schools to do the same. That the "pilgrimages" will result in sales.

Gee now may be my chance to ge a G5. :cool:

ZephyrAardvark
Jan 16, 2004, 12:15 PM
This isn't a rumor, its a fact. The VT cluster is down right now so that they can do the equipment swap (installing the new G5 XServes). Why is this a "rumor"?

TMA
Jan 16, 2004, 01:43 PM
Originally posted by ZephyrAardvark
This isn't a rumor, its a fact. The VT cluster is down right now so that they can do the equipment swap (installing the new G5 XServes). Why is this a "rumor"?

Eh!? Do you have some proof to back that up? The majority (all?) of us here are classing it as a 'rumor' because we do not.

virividox
Jan 16, 2004, 01:53 PM
number 2 here we come

FuzzyBallz
Jan 16, 2004, 03:39 PM
How the hell does 1 college get so much money to buy bragging rights? Maybe all their alumnis are south american drug dealers, or simply Cheney and company...

Damn those lucky Virgin Tech bastards...

Counterfit
Jan 16, 2004, 05:00 PM
The total cost of the cluster was $5.2 million. That's nothing for a big school like VA Tech. Compare that to the $250 million spent on the #2 Super 'Puter, and $350 million on the Earth Simulator.

ZephyrAardvark
Jan 16, 2004, 07:07 PM
Originally posted by TMA
Eh!? Do you have some proof to back that up? The majority (all?) of us here are classing it as a 'rumor' because we do not.

??

Well, we had Srinidhi Varadarajan gave a talk recently at our lab describing how they were disassembling the old cluster to upgrade to the G5's Xserves. The VT cluster is down right now for the upgrade. I guess there isn't an official press release, but I guess you'll see eventually that this isn't really a rumor (its in progress right now).

Also, his talk indicated cooling system was designed with the expectation that they would be acquiring an Opteron-based cluster. The cooling capacity is a bit more than absolutely necessary for the desktop G5's, but its considerably more capacity than necessary for the much cooler-running 90nm parts in the new XServe's. However, it was worth it because the labor costs of installing any upgraded to the cooling and electrical system make the

isus
Jan 16, 2004, 10:39 PM
i wonder how fast it can do a seti unit... heh

Counterfit
Jan 16, 2004, 11:02 PM
Originally posted by Counterfit
The total cost of the cluster was $5.2 million. That's nothing for a big school like VA Tech. Compare that to the $250 million spent on the #2 Super 'Puter, and $350 million on the Earth Simulator. Sorry to quote myself, but I think I remember that most of the money came from a grant? Is that right?

NarKEd
Jan 17, 2004, 12:20 AM
as long as they dont decide at the last momen to change all their computers to G5 2.5ghz everything is fine.
imagine having to wait another time weeks and weeks for shipping

eazyway
Jan 17, 2004, 04:11 AM
Since the PowerMac G5 is at 8 terraflops and the Xserve at 9 gigaflops this implies an immediate 12.5% increase in computation power.

That would put the new system much closer to number two. Add in an extra 220 Xserves and you are oh so close to number 2.

niter
Jan 17, 2004, 07:07 PM
Hee hee. As a Tech student, I am very intersted in what happens to the G5s. I doubt we will see them at the surplus auction anytime soon, but they might appear around campus. Of course, since there is a lot of private investment in these computers, they may go somewhere else all together.

edit: I just read several of the posts knocking on Tech and the point of doing this whole project. I think it is very ignorant to say anything without knowing the whole picture. I have been at Tech for undergraduate and now graduate school, and I still am very limited in what I say to prevent sounding like a fool. The computer, even as is, where it is, has great use. I do know know how it was or if already open for research use, but I do know that several people I spoke to were very excited. For instance, several Biochemist/Molecular Biologists were very excited about access to such computing power. The Supercomputer was put together in the Corporate Research Center where there is both campus and private research.

Let's say that the computer has been totally useless so far...the PR is worth it. How many students who might not have heard of Tech have now applied. A hypothetical student could have went to the Tech webpage to look for the supercomputer information and while he/she was there, he/she found out more about the university and its programs. Also, sucessfully putting this computer together brings in more grant money for research.

There is a huge benefit of the computer for Tech and Blacksburg. I guess I am just a Hokie tried and true, but I really dislike hearing people knock on Tech.

i_wolf
Jan 17, 2004, 09:08 PM
Absolute tosh. Memory errors happen. A lot of the time they're harmless (who's going to notice 1 bit error in a huge photoshop image, especially if it only occurs once or twice a year?). But when memory starts failing, it can do a lot more damage to your files before you notice if there's no ECC. The performance overheard of ECC is minimal, so it comes down to the question: Do you want to be sure your computer is giving you the right answers? I know I do. Pete.

ABSOLUTE TOSH !!! lol.. thats funny! Never heard that insult before!

anyway. back on point! True true. memory errors happen, I am merely pointing out that desktop machines tend not to need ECC memory and if good quality memory is used tend not to see or have any memory problems. If you disagree with this , debate it with pretty much every manufacturer out there that ship desktop machines without ECC memory.

AMD Athlon MP boards originally shipped without ECC memory support for workstations. A lot of Intel Xeon mobo manufacturers support non ecc memory and do not support Ecc memory, IWILL, MSI etc.. Then there are manufacturers like Tyan etc.. who shipped more server orientated boards that supported ECC memory.
In a workstation setup it isn't needed. in a server, cluster definately. Maybe im lucky but I have an Athlon MP workstation thats sitting there nicely running FreeBSD with 2 gigs of non ECC memory. Hasn't been rebooted in well over a 7 months. Hasn't seen the slightest glitch with memory. And yes you can tell when memory starts to act up. Usually memory errors occur not because of age but because of heat. Heat in a workstation tends not to be as big as a problem as in a 1u node or cluster or server box where everything is crammed together. In a workstation box like G5 where there is good airflow i serious seriously doubt you are ever going to see any problems with memory. Just my two cents. Feel free to disagree with me and others about it but please do so in a polite way. My opinions are my opinions... not tosh! thanks very much!
Regards
i_wolf

P.S. my take from the beginning was that a cluster of the size of virginia tech needs ECC memory, but not for workstation use of FCP on a single PowerMac etc... I stand by this. This has also been debated over at Macnn, where most people agree that ECC is not needed in PowerMac.