Junk Super Computer Assimilates All

VonGuard writes "The ACCRC is the relatively famous computer recycling non-profit in Berkeley that builds clusters out of old hardware. Make Blog has an article about the Center's plans to build a cluster out of the equipment people bring to recycle at Make Faire later this month. The ACCRC geeks are now able to integrate PII's or better into the cluster, which will be powered by Vegetable Oil and run Parallel Knoppix."

Comments

Resistance is futile

[Anonymous Coward]

First borg post of nine.

Re:Resistance is futile

[thc69]

You missed a few. Everybody post one.

I'll do Seven Of Nine.

Take THAT out of context!

You must warn them all!

[Anonymous Coward]

Soylent Cluster is made from equipment people!

Soon they'll be breeding us like cattle!

Re:You must warn them all!

[MyLongNickName]

Soon they'll be breeding us like cattle!

Yeah... I'm not holding my breath. Quit trying to get our hopes up...

Re:You must warn them all!

[diablomonic]

only the Stud Bulls get to breed, and if you were going to be classed as one of those, I dont think youd be needing the help

veggie oil?

[Evoluder]

is it really cheaper than plain old power company? maybe it scales cheaper?

Re:veggie oil?

[Stevyn]

I doubt it. If you look at a typical utility bill you're talking pennies a kilowatt hour. And small systems don't scale as well as larger systems that can deliver power to an entire city. The only inefficiency is how the power plants burn coal to heat the boilers.

Re:veggie oil?

[blincoln]

If you look at a typical utility bill you're talking pennies a kilowatt hour.

I think their idea is to counteract the concept that for the same amount of power, they could be running much more powerful hardware. If the electricity comes from coal, they're wasting energy, but if it comes from biodiesel they're... uh... wasting energy in a way that sounds good to hippies?

Re:veggie oil?

[Anonymous Coward]

Veg oil brings the chicks a running!

Of course they all weight 250+ lbs and trample you to death in an attempt to find the damn french fries!

Re:veggie oil?

[Anonymous Coward]

Um... I don't know where you live, but in NYC it's far from pennies per kilowatt hour... more like $0.23...

Re:veggie oil?

[tux_deamon]

That's the beauty of the vegetable oil: it's free. In fact, restaurants pay to have the stuff hauled away.

Re:veggie oil?

[Anonymous Coward]

yeah, 23 pennies.

Re:veggie oil?

[Anonymous Coward]

If the electricity comes from coal, they're wasting energy, but if it comes from biodiesel they're... uh... wasting energy in a way that sounds good to hippies?

What sounds good to hippies is power which 1) generates less pollution (I don't know whether this is really the case, but it's surely the idea) and 2) reuses something which would otherwise be wasted (thrown out) and does... something with it.

Re:veggie oil?

[Anonymous Coward]

Or 3) is sustainable.

The big problem with coal and oil power is that they use a resource that effectively does not regenerate on a human scale. While there's nothing *really* wrong with digging up oil and burning it (except pollution, which you mentioned), it's kinda dumb to be dependent on it, because it *is* going to run out at some point. It doesn't take a geologist to do the math there.

Re:veggie oil?

[ComputerSlicer23]

Curious, I thought with an efficient enough fuel cell (run off natural gas) you could generate power in your home, avoid the inefficiency of losing power during the power line travel... (if I remember my physics, correctly, the power lost during transmission is proportional to i^2 where i is the current). I thought the process of transforming the energy to and from that state was fairly inefficient (but better then sending it down the power line without doing it. It's been a long time. I thought it was the sorta link you could end up using to take yourself off the power grid, or better yet sell the power back to the power company. The question becomes what is the efficiency of transportation of natural gas. I'm not sure.

It's like the fact that modern day farms are actually far less efficient then ones from 100 years ago, from an energy perspective. Used to be that farming was a net energy benefit.... Not true any more. If I remember correctly between all of the oil products used, and automation, something like 100 times the energy is put in, then is extracted from the food produced on it.

This guy sounds like a whack job, but I believe he's referencing some reasonable sources: Read here.

Kirby

Re:veggie oil?

[wertarbyte]

if I remember my physics, correctly, the power lost during transmission is proportional to i^2 where i is the current

That's why they use transformers to lower the current and increase the voltage.

Re:veggie oil?

[Eivind]

Curious, I thought with an efficient enough fuel cell (run off natural gas) you could generate power in your home, avoid the inefficiency of losing power during the power line travel...

Yes. But you'd add the inefficiency of having to transport the natural gas somehow. Which also costs energy. No, natural gas floating in pipes is *not* obviously that much more energy-efficient than electrons floating in wires, it depends on the details. (one thick pipe offers less friction than many small ones, higher voltage power-lines give lower losses)

if I remember my physics, correctly, the power lost during transmission is proportional to i^2 where i is the current.

Yeah. In absolute terms. But offcourse in this case your power transmitted is higher too, so your losses, measured as a percentage, doesn't go up that rapidly.

The oposite is also true though: If you up the voltage, then you can scale back the current needed for a certain power by the same amount, which leads to lower losses. Multiply your voltage by 10, and you can divide current by 10, and still transmit the same power. But at 1/10th the current, this means, by your formula, that the losses are now only 1/100th of what they where.

I thought the process of transforming the energy to and from that state was fairly inefficient (but better then sending it down the power line without doing it. It's been a long time.

Where'd you get that idea ? Large transformers achieve efficiencies in the 99.75% range, and even the small ugly wall-wart transformers that are mass-made at a buck a piece from the cheapest possible materials frequently manage to come in at 95%

It's like the fact that modern day farms are actually far less efficient then ones from 100 years ago, from an energy perspective.

Yes. But only from that perspective, which isn't the one we're trying to optimise for. Our current economical system optimises for production-efficiency. And a single person working on a farm produces probably 100 times more than a single person working on a farm did 100 years ago.

Energy isn't lacking. Not even *clean* energy is lacking, there's plenty of it to go around. The only reason it's not dominant is that currently non-clean energy is cheaper. It's perfectly possible to make clean energy enough to supply current and forseeable needs. But the thing is, with current tech it costs more. I don't know the numbers for US, but for example in Norway wind-power costs double of normal power (which is hydro with us, so also clean, but let's ignore that). In Germany there's a minimum prize given for home-produced energy of $0,50 or so, which is more than enough to make it a paying proposition (i.e. you make a *profit* by installing solar-cells on your roof), but which also happens to be like 4 times the price of conventional power.

A farm using only clean energy would still be a hell of a lot more efficient than the ones 100 years ago. But thing is: it'd be *less* (financially) efficient than the farms that burn oil. So that's what's happening.

But the scale is slowly tipping. The price of oil and gas has raised a lot, and ist likely to raise a lot more. The price of solar, wind, hydro, thermal and so on has all been falling steadily, and will continue to do so.

Re:veggie oil?

[maxume]

It feels gooder.

Re:veggie oil?

[DrSkwid]

s/restaurants/slow thinking restaurants/

supply:demand

That's the beauty of the ratio: it varies.

Re:veggie oil?

[hackstraw]

I think their idea is to counteract the concept that for the same amount of power, they could be running much more powerful hardware. If the electricity comes from coal, they're wasting energy, but if it comes from biodiesel they're... uh... wasting energy in a way that sounds good to hippies?

I'm a hippie. I don't know too much about biodiesel except from what I've heard and read. I'm not that terribly interested in it, but lets look at the differences in this wasted energy. Coal is pressed plants that takes a considerable amount of energy to dig up, and is essentially finite in quantity because it takes more than a few years for the earth to make it. Biodiesel is made from plants. Plants are completely renewable, and we can basically pick where they are grown. We have to go to the coal. Burning both coal and biodiesel creates emissions, sure. But new plants eat co2 and create oxygen. The coal plants have been dead for quite some time. Coal is dirty nasty stuff (kinda like a dirty hippie :) Mining it is not fun stuff for people. You breath unclean air, you're in the dark. Cave-ins, oxygen depletion, nasty stuff. Plants tend to like to grow in the sun, which people pay good money just to go somewhere and do nothing and lay in the sun.

Hydro electric power is pretty cool too. Wind is not as cool as it seems. Very variable and it disrupts weather patterns. Solar is OK, but not very efficient.

Hippie nonsense aside, I think that wasting energy via biodiesel and other direct plant to usable forms of energy is a damn good source of energy in my eye. Plus, you can't put coal in your gas tank. Coal's energy density and portability has not been used for mobile energy forms like cars, trains, and boats in a long time. And never in planes.

Re:veggie oil?

[PhoenixOne]

Make isn't about doing things easy. ;)

It's cool to cluster computers together, it's cooler to make that cluster out of the odds-and-ends of PC 'junk', and it's even cooler to run it off of an alternative power source. :)

Re:veggie oil?

[Anonymous Coward]

Plants are completely renewable

Bollocks. You're still taking energy out of the system when you burn them as vegetable oil, plus you have to add nutrients back to the soil somehow (preferably not in the form of some nasty chemical fertilizer).

All of these energy transform methods are negative sum (by definition), plants aren't any better than coal or oil in that respect. In fact, they're worse (or were worse, depending on how you feel about peak oil). The coal and oil are already there; we should use them since all we really have to do is burn them to extract energy [1].

The best things anyone can do further the cause of using energy here on Earth are

• Push nuclear energy, both fission and fusion. We need to make fission cleaner with respect to heat pollution. We need to dump the laws preventing the building of new reactors and refining fuels. We need to make sure that the public has access to the facts of these matters. Nuclear energy is the most basic form of energy there is, and it just happens to be cleaner than all the other methods [2].
• Don't let the oil/coal companies transition to being ``energy'' companies. They've polluted the atmosphere and had the laws of the land perverted to reach their goals (drilling sideways for oil? drilling on public land?). They monopolized energy and then used their monopoly as an excuse to gain extraordinary power in this country [3](because after all, they're the only company that _can_ drill here, right?). Vote with your wallet for a different set of energy suppliers.

[1] It's ridiculous how much some of these places are allowed to pollute. Instead of making companies pay credits for pollution, they should be forced to put out zero emmisions. If we had nuclear energy, the loss of efficiency wouldn't be a problem.

[2] When it's done right, nuclear energy is free of emmisions with known effects on the environment. What's going to break when the energy of every wave or every puff of wind is taken out of our weather patterns? Scientists can't predict weather patterns on the scale that we need in order to start taking massive amounts of energy out of the systems. It's criminally foolish to start putting up windmills and expect it to solve all of our problems.

[3] I'm proud to live in the United States of America.

Re:veggie oil?

[damiam]

Hydro electric power is pretty cool too. Wind is not as cool as it seems. Very variable and it disrupts weather patterns.

Wind disrupts weather patterns? Unless you're talking about curbing global warming, I've never seen a shred of evidence that wind turbines affect the weather. As for hydroelectric power, it's one of the environmentally worst types of renewable energy. Building dams destroys valuable farmland, floods priceless natural habitat, and screws up fish migration.

Hippie nonsense aside, I think that wasting energy via biodiesel and other direct plant to usable forms of energy is a damn good source of energy in my eye.

It's great in concept, and works on a small scale, but it's nothing to get excited about. It would take twice the land area of the entire US (assuming it was all usable farmland) to grow the soy to produce enough biodiesel to meet our heating and transportation needs. The same problem exists with ethanol and other plant-based fuels.

In the long run, the only sensible power source is solar. When you think about it, fossil fuels, wind, plants, and hydroelectric power are all indirect forms of solar energy. Man-made solar cells have the potential to be more efficient than any other form of solar energy, because they cut out the middleman. Currently that's not the case, but it's only a matter of time given sufficient research.

Re:veggie oil?

[Anonymous Coward]

Don't use misleading statistics.

Care to cite a source for that "twice the land area of the united states"? I thought that had been discredited?

It'd be misleading even if it were anywhere close to being true, for a number of reasons.

For one, soy actually isn't the most productive oil crop, in terms of land/oil results. (Plus it takes a lot of chemical inputs (herbicide/pesticide) - for that reason it has a lot of ag industry (Monsanto) push behind it currently. It's also currently among the cheaper, but that is another question, and also would not necessarily be true were a lot going to energy.)

Nor is there reason why we must have *all* "our heating and transportation" needs from *one* source. (It's not as if these are all met by one source now!)

Nor need we use virgin oil for all our biodeisel conversions, by any means. Pacific Biofuels in Hawaii diverts used cooking oil from restaurants instead of it going to landfills (or illegally into the sewer or ocean). Pacific Biofuels is a growing operation and is opening mainland subsidiaries.

The solution isn't to find one "magic button" to substitute at one shot for all our energy needs. The solution will be a lot of pieces, including many "small scale" pieces. If you think about it *most* of us are small-scale users. But it all adds up.

Biodiesel is one excellent piece. And it has carbon cycle / pollution benefits (should be used on school and city diesel buses for just that reason alone).

I'm less impressed by ethanol however, though I know less about it. Costs/benefits don't seem to be there yet. But it might have its place too. Along with, yes, solar, absolutely. (Why all public buildings don't have solar roofs in sunbelt states is absurd. Why there aren't aesthetically pleasing solar solutions... well, we are getting there, actually.)

But not all our eggs in one basket please.

Re:veggie oil?

[xnixman]

Wow, this is a horrible thread...I guess I'll join it...

1. Biodiesel = Diesel (more (NO2) or less (carbon dust))
2. Reused restuarant oil is not really going to work for more then a small percentage of the people. After that you need to make more oil from soy, or whatever so the reuse percentage goes way down. (I can see the ads now, oil kills us via terrorists...Biodiesel kills us with fried food)

Re:veggie oil?

[xnixman]

Nothing is sustainable across a long enough span of time.

If we were talking hydrogen, you'd be complaining about using up our water for fuel.

The trick is to adapt, and we will, we always do. Malthus was only wrong because things change.

When the usual price of energy creeps too high this will create a profit motive for additional research and development as well as making higher priced alternatives more attractive as the economics change. (And no, even at $3 a gallon our energy is still insanely cheap)

Panicing about something that will not happen for 100+ years is silly and counter productive, consider the changes over the last 100 years as evidence.

Re:veggie oil?

[xnixman]

>Plants are completely renewable, and we can basically pick where they are grown.

Not really true on any significant scale.

>But new plants eat co2 and create oxygen.

And burning plants release co2 and consume o2

>Mining it is not fun stuff for people. You breath unclean air, you're in the dark. Cave-ins, oxygen depletion, nasty stuff.

Depends on where you are mining it. Back east sure, but in the west we just kind of dust it off and load it onto trains.

>Plants tend to like to grow in the sun, which people pay good money just to go somewhere and do nothing and lay in the sun.

So, you are suggesting some sort of energy growing resort? Next vacation, come to Iowa and grow soy for biodiesel!

>Hydro electric power is pretty cool too.

Sure, if you are planning your next lake on someone else's land

>Hippie nonsense aside, I think that wasting energy via biodiesel and other direct plant to usable forms of energy is a damn good source of energy in my eye.

Why is it ok to waste biodiesel? Biodiesel is a decent alternative to diesel for some, but I don't see how wasting biodiesel is any more appropriate then any other wasting of energy..

>Plus, you can't put coal in your gas tank.

You could use coal gas...

Re:veggie oil?

[xnixman]

>They've polluted the atmosphere and had the laws of the land perverted to reach their goals (drilling sideways for oil? drilling on public land?).

What are you talking about?
1. The producers are not the most significant polluters, the consumers are.
2. Directional drilling is a great tool when you don't happen to want to drill straight down, what is your problem with that?
3. Utilizing the public lands for oil and mining is a completely appropriate use, it ALWAYS HAS BEEN. Trying to whine about this 200 years later is silly and revisionist. Moreover, it is not like they stop by for a picnic and decide to drop in a well. They pay the US government for the right to drill.

>They monopolized energy and then used their monopoly as an excuse to gain extraordinary power in this country [3](because after all, they're the only company that _can_ drill here, right?).

Who is "they", the dozens of oil companies that, in fact, make energy a perfect commodity? No, anyone with the money and a lease or ownership of mineral rights can drill oil. Are you in some other country? I know Saudi has a monopoly thing going, as does Mexico as I recall, but the US certainly does not.

>Vote with your wallet for a different set of energy suppliers.

Yea, because you don't want to trust the people who have been doing this successfully for 100 years and have a distribution network established.

Re:veggie oil?

[xnixman]

>>Hydro electric power is pretty cool too. Wind is not as cool as it seems. Very variable and it >>disrupts weather patterns.

>Wind disrupts weather patterns? Unless you're talking about curbing global warming, I've never seen >a shred of evidence that wind turbines affect the weather.

Using the same logic, trees would do the same thing. I propose a nationwide mobilization to cut down all of those pesky trees that are disrupting our weather.

There's probably also the worry that with all of these propellers going, we will slow the earth's rotation making the days longer causing the earth to warm up. :-)

Re:veggie oil?

[xnixman]

>The solution isn't to find one "magic button" to substitute at one shot for all our energy needs.
>The solution will be a lot of pieces, including many "small scale" pieces. If you think about it
>*most* of us are small-scale users. But it all adds up.

Yea, 'cus it will be alot more efficient when everyone's furnace and car run on different fuels!

>Biodiesel is one excellent piece. And it has carbon cycle / pollution benefits (should be used on
>school and city diesel buses for just that reason alone).

Good idea, because government money is free money right?

>(Why all public buildings don't have solar roofs in sunbelt states is absurd. Why there aren't
>aesthetically pleasing solar solutions... well, we are getting there, actually.)

Maybe because they are still excessively expensive and it is MUCH cheaper to just use power from the power company. Oh, I forgot, government money is free money...Sorry

I am glad to see that you are concerned about the aesthetics though. For a minute I thought there was an actual problem.

Re:veggie oil?

[Presidential]

If we were talking hydrogen, you'd be complaining about using up our water for fuel.

Well, not really. The process of combustion with hydrogen is...water.

http://www.hydrogennow.org/Facts/FAQs.htm#10 explains nicely.

Re:veggie oil?

[xnixman]

I was thinking more along the lines of splitting water for hydrogen for fusion which result in helium.

Re:veggie oil?

[Anonymous Coward]

WRONG!!! get a job hippie FAG!!!

Make Faire

[Barbarian]

Make Faire = Do Do

Bit redundant, do do you think?

Re:Make Faire

[Frazbin]

Hahahaha. You said doo doo!

Re:Make Faire

[Somegeek]

Make Faire = Do Do

Bit redundant, do do you think?

I dunno, let's see, convert to binary, look for redundant bits...

Re:Make Faire

[SavvyPlayer]

Oh, to Make/Faire Free/Libre. The joy, the responsibility, the translation.

Re:Make Faire

[not-admin]

Make Faire == 01001101011000010110101101100101001000000100011001 100001011010010111001001100101
(In ASCII)

I bet StorageMojo could compress this down to 4 bytes!

Re:Make Faire

[Anonymous Coward]

Nice signature, very original (at least to me).

learn from the flashmob supercomputer

[stevetures]

Hmm... they tried this piecemeal supercomputer at my university (university of san francisco). From what I understood, they accepted a lot of low-spec computers that actually caused more problems than they served to compute. http://www.flashmobcomputing.org/ Can anyone confirm on my specific point?

Re:learn from the flashmob supercomputer

[Darth_brooks]

The biggest problem you can run into with older machines is the lack of support for things that make building a cluster easy. The two biggest things I ran into were:

-Wake On LAN support is huge, so that rules out the old machines with the clicky power switch.
-Trying to do anything with less than 32 megs of RAM is a PITA.

On top of that older machines don't always have a NIC, so you're stuck scrounging for parts. Plus who knows what kind of cryptic Acer-Packard Bell-eMachines crap hardware you're going to get via donations (so building a boot image can be a pain), so you're opening youself up to tracking down odd bits of unsupported yet essential hardware drivers (PCI Controllers stand out.)

Clustering gets way easier when you can stick to at least the same general system brand (e.g. Dell) or even better, identical systems.

Re:learn from the flashmob supercomputer

[Anonymous Coward]

i worked at usf at the time. from my understanding of the project, they're hoping to create useful software for other universities to use to build cheap supercomputers. but the differences in hardware was a huge problem and they spend most of the day trying to fix the damn things. they should have asked every kid with an ibook to bring it in and hook em up with firewire... or maybe it was more the challenge they were after?

Re:learn from the flashmob supercomputer

[caffeinemessiah]

absolutely. we had a bunch of old P3s lying around with about 256mb each. i spent some time putting them into a cluster because the departmental servers were overloaded. turned out that it just wasn't useful. the overloaded dual-opteron server with 4 gigs of ram ran a set of intensive experiments faster than the p3s could crank out their stuff. from my gross, empirical estimates, 5 p3s w/256mb each == 1 overloaded dual-opteron server at fairly I/O intensive tasks. Don't even want to think about power/heat issues.

Re:learn from the flashmob supercomputer

[cheaphomemadeacid]

No i wouldn't run windows on that cluster either, however running linux usually eliminates the problem with drivers for old hardware. The boot stuff can still be a pain in the ass though :)

Re:learn from the flashmob supercomputer

[hackstraw]

Having an almost completely heterogeneous computer system is not something I would want to use or admin. I know a little about this stuff...

Re:learn from the flashmob supercomputer

[hackstraw]

5 p3s w/256mb each == 1 overloaded dual-opteron server at fairly I/O intensive tasks. Don't even want to think about power/heat issues.

Not to mention 5x+ the likelihood of a hardware failure because there are 5 of every part that can and will fail and that the machines are already old. Plus ease of use, and admin maintenance.

Re:learn from the flashmob supercomputer

[Darth_brooks]

On the contrary, linux tends to add to the old hardware / drivers problem. You run into stuff that was only intended to run on windows, and that very few people would have tried to boot linux on, so implimenting support was never a huge priority. They became machines that were (as far as linux was concerned) an evolutionary dead end.

Re:learn from the flashmob supercomputer

[cheaphomemadeacid]

were you thinking about anything specific?

Why give them to a million dollar university ?

[Anonymous Coward]

when you could donate your old PC to a worthwhile charity, that would help the local or even an African community a lot more than some CS students messing about with Knoppix

universities should be donating their old stuff to the poor, not playing with Knoppix and acheiving very little (except a large electricity bill)

Re:Why give them to a million dollar university ?

[Anonymous Coward]

They are a non-profit, not part of the university.

Re:Why give them to a million dollar university ?

[Anonymous Coward]

They aren't running up an electricity bill. RTFA. Hell, you didn't bother to even read the summary, did you?

Re:Why give them to a million dollar university ?

[why-did-I-wakeup]

They are doing something: learning. They are having fun and at the same time learning about parrallel computing. I'm jealous of them; I would love to have lots of old crap that I could set up and run some sort of parallel computing software. Not to mention this hardware is basically unusable so the poor african towns could possibly have more trouble setting the stuff up than they are worth. Especially if they have to put in a connection to the internet. That could be hundreds of thousands of US dollars to do if the village is far away from a city.

Re:Why give them to a million dollar university ?

[tux_deamon]

The ACCRC is a charity based in Berkeley, California. It is not affiliated with with the University of California at Berkeley.

Re:Why give them to a million dollar university ?

[omeomi]

I worked at a computer lab through college. There was a mountain of old computers and monitors stacked in the back of one of the lesser-used labs. I asked once why they didn't give them to charity, or sell them or something. It turned out that the paperwork to get rid of them was more of a pain than it was worth. So they just sat there taking up space...hooray for red tape.

Re:Why give them to a million dollar university ?

[Anonymous Coward]

have several P2/3 class machines: take them off my hands...

Re:Why give them to a million dollar university ?

[tlynch001]

About 5 years ago the guy in the computer lab showed me a pile of 20" Sun monitors that they couldn't just get rid of for the same red tape reasons. "I'm going for coffee, if you want one take it before I get back."

20" Monitors? Amazing at the time. So I lifted one...or tried to because apparently they have plutonium in them or something, it weighed 80 lbs it seemed. Got a cart, loaded it up, raced home, wife rolled her eyes...and then I realized you can't plug them into your Gateway PC without an adapter.

ummm...and that's the end of my story.

Re:Why give them to a million dollar university ?

[Anonymous Coward]

I know of an office of a certain company which during their last upgrade cycle found out that the paperwork to donate or give away their old-but-working systems was so high, that it was not worth the cost of the administrators' time to cut through all the red tape.

So instead they just put it all in a dumpster out behind the loading dock. Some of it was fairly nice gear, too -- not just hardware, but basically new in box software, manuals, everything. They couldn't actually landfill it, but they put it in the dumpster, and within a few weeks almost everything in there had been looted. People hauled off everything that wasn't tied down -- even the ancient crap: XT keyboards and mice, old pre-VGA displays, and manuals for esoteric mainframe software. It just walked off in the middle of the night.

I assume it all ended up on eBay eventually.

Anyway, I call this the "Lord of War" disposal method, because it reminds me of the scene in that particular movie where the main character disposes of a plane full of weapons by just throwing the doors open and letting the Africans take it, right down to the plane itself. That's pretty much what happened.

Re:Why give them to a million dollar university ?

[modecx]

Even worse than not being able to use them because of a measly adapter: Depending on how old the monitors were, they could have been (probably were) fixed frequency composite sync monitors (H and Vsync signals are combined), or sync-on-green (where the vsync signals are combined with green), and would be unable to take a VGA signal. I think newer Sun, SGI monitors can take VGA through a VGA->13W3 cable without anything special in between.

However, Back in The Day you either required a special fixed frequency video adapter, or an external dongle device to convert VGA to whatever signaling your monitor required, and both were expensive to the point where getting a free monitor just wasn't worth it, unless you already had the stuff it would work with. Bummer.

I've got a few such monitors laying around hooked to old computers through old PCI adapters just because they're connected to a couple servers and they're hardly ever turned on, and damnit, I just can't stand to get rid of them.

Re:Why give them to a million dollar university ?

[DrSkwid]

Yeah, what did people do with computers before the internet anyway ?

The Question Remaining

[neoshroom]

So, they have a network of recycled computers...
...being run by a generator using veggie oil...
...to render 3D images.

So the only question remaining is: What are they rendering?

My guess: PETA's new 3D logo.

__

Custom Research Paper

Re:The Question Remaining

[oskay]

I'm giving a tutorial in getting started in POV-Ray at the MakerFaire.

So the only question remaining is: Am I supposed to bring my own vegetable oil?

Re:The Question Remaining

[sremick]

The Matrix: Recycled

What I hated about that place...

[Anonymous Coward]

...was that they want money to take your stuff. If you don't mind a drive, Video Only will take monitors (and TV's) for FREE! And displays are the hardest things to get rid of.

As for PC's, there is a charity in Berkeley that takes donated PC's, refurbs. them and gives them to families that can't afford a computer.

The City of Albany (next door to Berkeley) had a day where you could take almost any kind of electronic device and dispose of it for free (no large applicances). They plan on doing this yearly during the summer - the program runs for a few weeks. If you have a friend who lives there (ID required) - ask them to help you take your stuff.

JUST DON'T PAY SOMEONE TO DO IT!!!!!

Re:What I hated about that place...

[Varmint01]

I hate to parrot the ACCRC website so blatantly, but if you aren't paying someone to take it, it's probably being shipped to China, stripped of its precious metals, and then dumped in a river.

All this electronic equipment that we love so much is made up of some very, very unpleasant substances. Dumping it in a landfill or shipping it to a country that doesn't care about its environment doesn't count as proper disposal.

Working equipment is fine to be donated to charities who can use or redistribute it, but hardware that's broken, and I mean really broken (fried motherboards, scratched hard drives, etc.) needs to be taken care of the right way. The mindset that these things should be taken care of for free is very dangerous. Proper recycling costs money, and what you pay the ACCRC is the true price for keeping this stuff out of landfills.

Re:What I hated about that place...

[VonGuard]

First of all, monitors are free now at the ACCRC, as long as you are a California resident.

This IS the place that fixes PC's and gives them to charities, non-profits, and underprivlidged individuals.

The ACCRC was the recycler that took all of the equipment for free at the Solano Street fair, the day in Albany to which this post refers. The Solano Street fair will probably host the ACCRC for free recycling again next this year. No one from Albany has called to set this up yet, however.

Oh, and the ACCRC will take anything you can lug to the Make Faire for free. No charge. The one caveat is that it has to be able to fit in the truck, and there may not be a lift gate. So, disassemble those Onyx's first, people!

Re:What I hated about that place...

[operagost]

If it costs more to recycle something than to store in a safe location where it will not pollute, then it is not worth recycling. In the end, you're expending more energy to recycle it than you are taking in. The ACCRC's passing it on to the donater (no good deed goes unpunished) is a cheap way of hiding that cost. Obviously, we don't want lead dumped in Chinese rivers ("we" obviously doesn't include the Chinese enslavers/bureaucrats) so if you can't have it recycled efficiently, then you might as well have it crushed under tons of dirt in a contained area. It's no wonder we can't get people out of the disposable mindset when the well-meaning are penalized.

Re:What I hated about that place...

[Anonymous Coward]

Where's that "contained area" you mention? Oh... Yeah... It doesn't exist.

Still -- I suppose it will bring about a new phase in human evolution, which isn't all a bad thing. The people with the genes to not be retarded after drinking from a lead-contaminated water table will, largely, be more able to provide for their offspring, right?

What a colossal...

[Harry Balls]

...waste of electricity.
State-of-the-art computers are probably about 15 times as fast as Pentium II-based computers, and consume maybe twice as much electricity.
Or take Pentium M-based computers, they consume less electricity than Pentium II-based computers and are probably about 10 times as fast.

Just my 2 cents.

Re:What a colossal...

[Darth_brooks]

Funny, New systems are coming with 350 and 400 watt Power supplies, but my old PII has a 250. Yep, curse those old inefficient machines!

It really depends on what they're doing with the machines. If they're running it as a diskless thin cluster then, yeah, newer chips draw less power. But each node is probably drawing less than a hundred watts (max) in the first place.

Re:What a colossal...

[Anonymous Coward]

Hmmm, electricity is being generated damn near for free, equipment is free (As opposed to modern computer parts, which amazingly enough cost $). So I call waste of bandwith ;-)

Re:What a colossal...

[Anonymous Coward]

I think the OP's point was : for 2x the power consumption (250 Watt -> 500 Watt), you get 10x the compute performance (300 MHz -> 3 GHz).

So, if your goal is to get the best performance / killowatt-hour, you're better off running fewer, newer, machines.

Re:What a colossal...

[Jeff DeMaagd]

I've found that PII/PIII based computers can be pretty efficient. I have a PIII 500MHz computer that measured to consume 40W total at the wall jack, so that's counting PSU inefficiency too. You are right that some of the latest computers can produce far more FLOPS per watt, but electricity is pretty cheap compared to the cost of a new computer. That 40W computer might consume $40 worth of electricity per year, it's hard to argue that spending money on new computers would be better from an electricity cost perspective such that it outweighs the computer cost. Administration costs might be different matter though, but if you are working from volunteers or students, that can be cheap too, and quite an educational experience.

Re:What a colossal...

[vondo]

Your $40 is about right. So, lets say I can get a Pentium M at 10x the CPU power and the same wattage. You'd spend $1200 over the course of three years (reasonable lifetime of a PC) on electricity. I'd spend $120. Plus, you have 10 old PCs that are going to break down and cause you problems. I have one new one that probably won't.

Running old computers as supercomputers makes no sense. I do have one, though, that I run as a home network server. They are great for that.

Re:What a colossal...

[Anonymous Coward]

increase in wattage is due to peripherals with higher demand, not cpu.

Re:What a colossal...

[tux_deamon]

I think the point is is that the equipment being used is old discarded hardware. New fast computers cost money. This organization is reusing this old hardware and keeping it out of a landfill.

Re:What a colossal...

[Anonymous Coward]

Pentium III is better than Pentium 4.

Re:What a colossal...

[h4rr4r]

WOW, Where do you get these 10 GHz (or since the gp said 500, 5 GHz) Pentium Ms? Yes, I know its not all about hertz, but It is not even possible, much less believable that a Pentium M is 10x more powerful than a PIII 1.13Ghz coppermine or even a lowly PIII 500Mhz(unless you mean for playing games, which is mostly due to the older video cards in those machines). For reference you may refer to this chart.

  65 CPUs from 100 MHz to 3066 MHz

Re:What a colossal...

[__aawavt7683]

Yes.. because, after all, vegetable oil is a horribly inappropriate solution for their recycled cluster. Sigh.

-DrkShadow

Re:What a colossal...

[thedletterman]

This was along the lines of my thought.. using old computers that consume tons of power to compute very little.. but showing your ecological awareness by using vegetable oil? Give me a few nuclear powered quad core opterons anyday. I'll show you the definition of progress. Lower power consumption, cleaner energy, and multiples high in productivity and computational gains.

Re:What a colossal...

[enthused i swear]

Yes, but that's the point. The one time cost of new hardware will eventually pay them back because they get more computations per amount of electricity.....

Re:What a colossal...

[keeboo]

State-of-the-art computers are probably about 15 times as fast as Pentium II-based computers, and consume maybe twice as much electricity.

Modern computers being 15 times faster than P-IIs?
I seriously doubt it. Take the slowest P-II ever, the P-II/266, as reference. 15x that means, what, a P4 at 4GHz?
Sorry, no way it is that faster. Maybe a P3 core at 4GHz, assuming overall improvements besides the clock speed.

Personally, I do think that a P3/866-1GHz is worth for such tasks.
You may say about being unworthy machines because of power consumption costs. Let's forget the fact the newer machines have much higher power requirements, and let's also forget that the 15x-thing is an exaggeration.
Did it ever occur to you that perhaps, running for (let's say) 1-2 years may be cheaper even considering the power costs?
Well, perhaps in the USA power is to expensive while the hardware is too cheap, but in other countries it might be the very opposite (like where I live, for example).

On the other hand, I've seen such clusters using 486s... Now that's a waste of energy (considering the processing power alone), and obviously created for entertainment/learning purposes.

Re:What a colossal...

[sremick]

You know, you're absolutely right. And I'm sure if you contact them, they'll be happy to tell you who to make your check out to so that they can buy these new "state of the art" computers. I'm afraid it'll cost a bit more than your 2 cents, however... as well as a lot more than they're currently paying for this hardware, which... while not ideal... is FREE.

Re:What a colossal...

[Elastri]

Electricity costs money too, and it keeps costing money even after the initial capital purchase (or lack-there-of). If you're building a cluster powerful enough to be comparable with even a couple low-mid end modern PCs you're not going to be running for too long before you hit the point where the power savings makes the modern PCs less expensive. A more thorough explanation can be found in these two posts from a beowulf mailing list:

http://www.beowulf.org/archive/2003-March/009658.h tml
http://www.beowulf.org/archive/2003-March/009662.h tml

Re:What a colossal...

[njh]

Except they still are paying for the electricity. Which was the original point.

Re:What a colossal...

[Anonymous Coward]

Modern computers being 15 times faster than P-IIs? I seriously doubt it. I seriously doubt it. Take the slowest P-II ever, the P-II/266, as reference. 15x that means, what, a P4 at 4GHz? Sorry, no way it is that faster. Maybe a P3 core at 4GHz, assuming overall improvements besides the clock speed.

So close.... But so fucking far from right. You sir, are a classic example of a slashtard. I mean you're the guy who makes some vaguely correct statement if it's considered with a qualifier that shows that you have no fucking clue what you're talking about.

I mean seriously, dude. Get. A. Fucking. Clue... "assuming overall improvements besides the clock speed." -- do you have ANY idea how significant those overall improvements are? I didn't think so. I'll start at the most basic one: bus speed. I mean seriously, dude -- the biggest overall improvement you could care to mention is that a P3 or P4 talks to everything a LOT faster than a P2 could. Have you got any idea at all what that means? Nah, didn't think so. Look up what a cache hit is, it might interest you. Then try to wrap your wee little brain around the fact that a cache hit is less expensive on modern systems. It might help you come to grips with the fact that the "megahertz myth" is just that. A myth.

That should have been enough -- but I'll continue anyways, working from the assumption that you are so fucking dumb you didn't see how that last tidbit was at least as significant as the new clockspeed. I hope you looked up cache hit like I suggested -- 'cause now I'm going to mention that the newer processors have (get this!) BIGGER CACHE! I mean like... Wow, dude... Not only is the processor faster.... Not only is the processor able to get data from memory faster but -- check this shit out, the processor can also AVOID CACHE HITS BY KEEPING MORE DATA AND CODE IN CACHE. Holy fucking shit! No way! No way!

And then, like, OMG PONIES! you are never going to believe this one, 'cause, like, check this shit out, bozo! Those new processors are doing, WOW, more per cycle than the old ones! I mean, wtf? An op that used to cost 16 clock cycles can now be done in two or three? Fuck, man, look at all those transistors on the chip! They're smaller and change state faster! I mean, shit, that's hawt! They can now have these little dedicated engines for what would have been expensive in cycles before but now they can do it faster! ROFLCOPTER!!!!11!!

Oh, and yeah -- that doesn't even mention how they deepened the pipeline (OMFG, you better look that up, fuckstain!) improved predictive branching (OMFG, you better look that up, fuckstain!) and improved the feasability of OOOE (OMFG, you better look that up, fuckstain!)

A modern system will outperform an older system with one-fifteenth the clockspeed by FAR MORE than fifteen times. Seriously.

In conclusion: You're a dumbass who should probably go to school before you try bluffing your way past people who know what they're talking about

Re:What a colossal...

[Random Destruction]

10 old PCs will only last you 3 years?
So thats 3.6 months per pc. I'm not sure what you're doing to them to get that kind of lifespan, but I doubt they were designed for it :P.
My mom just got rid of her pentium 200mmx that she's been using since it was top-of-the-line (actually it was a 133 at the start of its life). It passed its 3 year lifespan your 3.6 month afer-life estimate loooong ago. It still works great, except that its completely useless now.

Re:What a colossal...

[runderwo]

I'll start at the most basic one: bus speed. I mean seriously, dude -- the biggest overall improvement you could care to mention is that a P3 or P4 talks to everything a LOT faster than a P2 could.

Sure, but consumer PCI devices still run at 33MHz. The only thing you're getting here is main memory bandwidth.

Have you got any idea at all what that means? Nah, didn't think so. Look up what a cache hit is, it might interest you. Then try to wrap your wee little brain around the fact that a cache hit is less expensive on modern systems.

That's not a fact at all. That depends entirely on the latency of the cache, and it has nothing to do with the bus speed, since if the cache is hit, on any P6 or later CPU there is no associated bus traffic.

It might help you come to grips with the fact that the "megahertz myth" is just that. A myth.

Not when you are comparing processors with the same execution core. P2 and P4 may be incomparable, but P2 and Intel's new P3-core mobile chips can very well be compared in terms of MHZ. You can write a benchmark program that never once accesses main memory after loaded, to control for bus bandwidth.

I hope you looked up cache hit like I suggested -- 'cause now I'm going to mention that the newer processors have (get this!) BIGGER CACHE!

Not necessarily. Many CPUs still have a L2 cache smaller than the 1MB in my PPro system. And many newer CPUs still don't even have a 128KB L1 cache like my classic Athlon.

I mean like... Wow, dude... Not only is the processor faster.... Not only is the processor able to get data from memory faster but -- check this shit out, the processor can also AVOID CACHE HITS BY KEEPING MORE DATA AND CODE IN CACHE. Holy fucking shit! No way! No way!

Are you on something? How can you be so overconfident and yet so completely wrong at the same time? A larger cache, given the same set-associativity, will INCREASE the number of cache hits.

Those new processors are doing, WOW, more per cycle than the old ones! I mean, wtf? An op that used to cost 16 clock cycles can now be done in two or three?

Pipelining has given us this, but there is a tradeoff because a long stalled pipeline is just as effective as no pipeline at all. And hazards cause a pipeline to be flushed, negating any advantage. The P4 was a design with an incredibly long pipeline, and Intel seems to have largely given up on that strategy in favor of the P3 philosophy, a shorter pipeline with more execution units.

Fuck, man, look at all those transistors on the chip! They're smaller and change state faster!

They can, and this is in fact one benefit of newer hardware. You can take your new CPU, downclock it to match the performance of your old CPU, then the power consumption becomes negligible.

Oh, and yeah -- that doesn't even mention how they deepened the pipeline

A tradeoff

improved predictive branching

A tradeoff - trading power consumption for potential work-ahead

improved the feasability of OOOE

You'd best quantify this, since P2 was an extremely strong performing out-of-order processor. One of the first and still one of the best.

A modern system will outperform an older system with one-fifteenth the clockspeed by FAR MORE than fifteen times. Seriously.

Nah. You're full of shit. Run some benchmarks. Unless the "application" has a compact (wrt cache) and minimal memory usage, doesn't spend the majority of its time waiting for user input, and never hits the disk or uses external peripherals, the difference isn't as great as you'd like to believe it is.

Re:What a colossal...

[Enigma_Man]

They're only paying for the few chemicals needed to make biodiesel to fuel the generator that powers the cluster.

-Jesse

Re:What a colossal...

[njh]

The electricity they generate could be sold back to the grid at a profit, instead they are burning it running computers. Whether they make their own electricity or not, the value of the electricity is still something like 12c/kWh.

To make this clearer, lets say you discovered 100t of gold on your property. Maybe you make your house out of gold, maybe you make it out of bricks. If you sold the gold you could buy a lot of bricks. Which would you do?

Reminds me of days of yore....

[Anonymous Coward]

... the old Stone Soup Supercomputer was the first I can remember that used cast-off computers to generate (what passed for) Serious Horsepower. Tempus fugit, indeed.

Worth it?

[Galahad2]

I wonder if the power consumption of a low-end Pentium 2 is actually worth the computation capability it could contribute to a network. There's definitely a point at which it costs more to run a computer than you can get out of it -- where does that line fall?

Re:Worth it?

[bear_phillips]

A good point, but a better question is which is more power efficient: 1) running 4 old dontated computers or 2) building and manufacturing a new computer.

Re:Worth it?

[Kadin2048]

Doesn't matter, in this situation. The power they're using is free, if they really are going to use a vegetable-oil generator. (Assumedly they are getting the vegetable oil donated, so the cost of the energy in is zero.)

I suppose you could argue that this still contributes to global warming or carbon desequestration or something, but that's taking things a bit far. Plus the carbon in the vegetable oil is eventually going to be released anyway.

If you're getting the energy from a source like that, which is both free in terms of cost and in terms of fossil fuel consumption, then it really doesn't matter how inefficient the computers are. The total fossil fuel consumed to run the whole operation is 0W.

What would be a legitimate question is what's the opportunity cost of the time of everyone involved -- is it really worthwhile to put together a vegetable oil generator to run this thing, when instead they could use the same generator to power some building's air conditioner someplace and reduce fossil fuel consumption. That's a much tougher question, and difficult to factor out because the people giving their time and use of their equipment are volunteers and not a fungible good.

Re:Worth it?

[Anonymous Coward]

PII = 66 Mhz
PIII = 100Mhz
P4 = 133 Mhz

Re:Worth it?

[Procyon101]

There is still a line in a heterogeneous cluster. There comes a point where the overhead cost needed to negotiate a job to the lowest end machine for processing surpasses the cost of a higher end machine doing the job itself. At such a point, adding lower end machines actually slows the cluster down.

Re:Worth it?

[merlin_jim]

There's definitely a point at which it costs more to run a computer than you can get out of it -- where does that line fall?

I would guess just barely this side of solar-powered calculators...

energy is cheap. computation is not. It's that simple - look at the laws of thermodynamics... the universe hates free energy, that much is clear, but even more than free energy it hates organization, information, computation.

Making computation a much scarcer resource than free energy...

Re:Worth it?

[Anonymous Coward]

With some applications, sure, but with ray tracing 3d rendering you get very good scaling value as you add more nodes. Probably why thats what they're doing with it...

Familiar sight

[simpsone]

Hey, I know this place. Drive by there all the time. I always thought it was something run by the county. Never realized they were an independent non-profit. Based in a funky looking building right by the freeway.

Re:Familiar sight

[Anonymous Coward]

That place actually is great. I also knew a guy who went in there and they helped him recycle all his electronic items too, even though there was a small fee for some items, it definitely seemed like it was worth it. Very helpful folks too.

Yes, but...

[zpeterz63]

will it run Windows?

Re:Yes, but...

[Tanmi-Daiow]

maybe win98, because Vista would clog up about 1000+ of those old computers.

Re:Yes, but...

[chmod a x mojo]

i hope you are talking about XP at the latest..... that many new graphics cards would be expensive.

Fucking Hippies!

[Anonymous Coward]

You hippies drive me nuts. Your biodiesel powered POS cluster of crap equipment is no match for the number crunching computing power of my Escalade cluster of brand spanking new HP blade servers. Row after row of racks. Sure it dims the lights at the local nuclear reactor when I turn it on but, it's worth it!

Get off the information superhighway, you hippies!!! You're holding up progress!

Re:Fucking Hippies!

[Anonymous Coward]

Hey man, mellow out.
Why do you think it's called Berkeley Software Distribution?
We paved that superhighway you're talking about.
While the extreme right wing was having sex with animals.

Re:Fucking Hippies!

[1iar_parad0x]

I'm not saying Berkeley's contribution to the information superhighway is meaningless, but DARPA, Stanford, and XEROX (PARC) are hardly bastions of liberal hippieness!

Re:Frist "Beowulf Cluster" post!

[Tablizer]

I for one welcome our smelly rusty 386 clustered overlords. (sorry, couldn't resist. medication didn't work.)

Once it runs, then what?

[deadline]

Before everyone gets all "top500" over this idea, here is little cold water on the realities of cluster computing. Yes large number sof CPUs are great, but the software has to be there to use them. Plus, for anything other than rendering, a heterogeneous cluster is limited by its slowest node (for almost all applications)

It is the cluster equivalent of how many people you can stuff into phone booth. If you have nothing better to do, well why not I guess.

Re:Once it runs, then what?

[Anonymous Coward]

For some applications besides rendering these kinds of clusters ARE good. And rendering is important, people pay big money for machines that can render on a high level.

Re:Once it runs, then what?

[Cicero382]

> Plus, for anything other than rendering, a heterogeneous cluster is limited by its slowest node (for almost all applications) Err... No. A heterogeneous cluster treating all nodes the same way will have the same problem with rendering engines as well. But it doesn't have to be that way. Using techniques like stochastic petri net analysis (just Google it) can allow tuning the cluster on a node-by-node basis. It's not always worth it, but you can segment the cluster so that it's the slower processors that end up with wait states. As they say YMMV.

Re:Once it runs, then what?

[deadline]

Please list the applications you are referring to.

Re:Once it runs, then what?

[deadline]

Err.. I said "(for almost all applications) ". Please provide some applications that use this method. I'm not trying to troll, I have a genuine interest in heterogeneous clusters -- and how to use them efficiently for applications that currently run best on homogeneous systems.

Must be getting old...

[__aaclcg7560]

... powered by Vegetable Oil and run Parallel ...

I remembered when they used to be powered by vacuum tubes and ran one instruction at a time.

Re:Must be getting old...

[Anonymous Coward]

Well, unless they were burning the vacuum tubes to create electricity, what you just said does not make much sense. These are not magical "Oil computers", they use transistors like everything else. The use the oil for electricity.

Re:Must be getting old...

[operagost]

Vacuum tubes? Hmph! In my day, we had to pass instructions by shouting them one character at a time into the ear-trumpet of a half-deaf, illiterate programmer. He would then flip the bits by wetting his fingers and toes, then shorting out the leads because we didn't have the kind of money to buy niceties like wires and switches like you young dandies nowadays. Brats!

Re:Must be getting old...

[__aaclcg7560]

My mistake. It should've been "the black goo of dead dinosaurs". :P

Re:Must be getting old...

[Cicero382]

You were lucky! We could't afford a programmer. Our interface was totally deaf and was illegitimate as well as illiterate; in fact it was a mongoose, no a snail, no... And you try telling the young folks today that - they won't believe you, they won't!

MFLOPS/W

[Detritus]

What's the optimal CPU for MFLOPS per watt these days? At some point, an old system is just too slow to justify the power bill, when a cheap new system delivers much more performance at minimal cost.

Re:MFLOPS/W

[Frumious Wombat]

Probably Power5. However, to use desktop processors as the example: I have some benchmarks of a code I've run on machines from a DEC Alpha 21064 through a current G5 2.0.. The timings that matter here are jobs that took 107 seconds on a PII/400 now take 7. The speedup is about constant across the series, so we're looking at a 15x speed-up on my current code versus a PII/400. Since this particular package runs at about the same speed on comparable clock-rate Opterons/G5s, we can infer a probable 15x speedup (30x if they're using PII/266, with the slower bus), for less than twice the power. (250W vs 400W). OTOH, that 400W PS powers two processors, which claim to pull in the >40W range when under load.

In short, as long as you avoid Itanium-2 and certain late P4-Xeons, any modern machine will deliver a pretty acceptable flop/watt rating. This, regrettably, means that while their heart is in the right place, Berkeley's stunt, even if using biodesiel as fuel, would be more efficient if they scrapped the old computers, and used the money to buy a current Mac Mini or two to offer as compute servers. In my last job, even with the institution supplying power as 'overhead', certain machines no longer delivered enough performance to justify them occupying a plug and 9 sq ft of floor space, even if they did work fine. If I had been directly billed for what they consumed versus what they produced, they would have been dumpster-bound years earlier.

This doesn't mean that they shouldn't refurb the old machines, stick an OS and some user-land software on them, and hand them (or sell them cheaply) to potential users for desktop usage, but as a cluster, they're not likely to earn their keep.

Re:MFLOPS/W

[Anonymous Coward]

You are wrong. If your goal is to give away computers and you have to test them and the best method is to test them by a burn in process, what better method to test them than a cluster? A cluster like this will be more cost effective for rendering than any mac, or pair of macs, mini macs, big mac, or royals with cheese you care to name.

Re:MFLOPS/W

[Anonymous Coward]

I think the AMD Geode line is very good

Re:Frist "Beowulf Cluster" post!

[Anonymous Coward]

Frist Beowulf Cluster post

You, my friend, are a TOOL! I can't wait until HVIP (High Voltage over IP) is available. I would definitly vote to fry your ass... GRRRRRR!

Moore's law...

[f97tosc]

is a big problem for these kinds of projects.

When computing power grows exponentially, you need an exponential (in the age of the machines) number of old machines to do the work of one new one. And that is even before you consider all the losses to parallelism, the big electricity bill, and all the know-how needed to put them together!

But it is pretty cool.

Tor

Re:Moore's law...

[rminsk]

Moore's law has nothing to do with computing power. Moore's law is about the number of transistors on a chip.

Re:Moore's law...

[diablomonic]

Which is fairly linearly related to how many cores and therefore how much computing power you can fit on a chip..... :|

And hence...

[Null Perception]

The first borg cube was created. Resistance is futile. F34r the Pentium Pros.

Re:And hence...

[Anonymous Coward]

Sounds like they should keep this thing away from any Trapper Keepers.

Saw this years ago on 20/20 or 60min

[ScrewTivo]

It was amazing what they were doing way back then. Before discussing the practicality of this you have to remember that a lot of what they do is teaching people about computers and providing refurbished computers to the poor. So now they get to learn about building super computers, it doesn't make a difference if a new multi-core system can outperform it or not, it's the lesson that is important. And tossing in a bio-diesel generator is precious!

BTW, he was talking of building a supercomputer way back then. So the group has put some thought into this.

If this turns out that it actually has some horsepower I can't wait to hear how it is put to use. The guy who started this is way ahead of the curve. Turning garbage into a self powered supercomputer...kewl!!

Re:Saw this years ago on 20/20 or 60min

[Anonymous Coward]

Turning garbage into a self powered supercomputer

Where did they say it would run off the methane of its users?

*ducks*

I'm scared

[Anonymous Coward]

This IS Skynet

Experimentation

[ComputerJerk]

Personally, I think experimenting with computers is a good thing. Maybe it's not a feasible solution to a problem, but experimenting generates new ideas. I see a lot of people saying "Oh, give your burnt out computer to the poor.". Well, if you want to be so generous with the poor, give them a computer that's worth having. Personally, I think giving a computer to someone that's too poor to buy it themself is a waste of a good computer. If they can't afford to buy the computer, they probably can't afford to access the internet, they certainly can't afford to buy any software for it, essentially all they get out of it is the ability to have a very large free paperweight that allows them to play solitaire when they don't feel like working to buy a real computer. If you have a computer to donate, I think this would be the perfect type of program to donate it to, at least it will get used and people may even learn something from it.

Re:Experimentation

[DexterF]

I yell.
Currently I'm unemployed since IT in my parts is a snowball in hell.
However, I'd really like to have two more boxes for a file server and an app server plus a set of disks in the 10 or 20GB range to experiment with raid arrays.

Why I need all this? For myself? Entertainment? No, to keep up with the IT pace and evade becoming an obsolete dinosaur.

I'd *gladly* take two PII boxen and a couple of disks.

Back to the average Joe and your false assumptions:
-if somebody doesn't have work, it doesn't mean he doesn't want to work. Arrogance check.
-you can be very productive on a computer with a dial-up or even *without* the frigging internet. A decent book about coding, databases or whatever is interesting to you and a low end machine running xfce4 or so will do just fine.
No money spent on the OS, the puter, the internet and still one can be a magnitude higher in productivity, creativity, learning than any dork with his broadband hooked 2GB-4GHz-SLI-500GB Gaming Powerhouse Of Ego Boost +3.

Re:Experimentation

[ComputerJerk]

Well, if IT in your area is hell, then you need to quit bothering staying in the field and choose a field that you CAN become employed in or move. What do you need a file server for? So you can set up your own FTP site to share pirated software via your dial-up modem connection? The common household that might be donating their old computer to charity doesn't generally have a RAID compatible motherboard. Most likely, you've already reached this point of becoming an IT dinosaur if you don't know how to set up RAID arrays and such. The IT pace is far beyond that. You can go buy a couple PII boxes for almost nothing, check your local paper and quit whining because someone doesn't want to give it to you for free. **Back to the average Joe and your false assumptions: If someone doesn't have work, it DOES mean he doesn't want to work. Generally, he/she is unemployed because he/she refuses to take a job that isn't in their field. I personally would gladly take ANY legal job if it means feeding my wife and kids. If it's not my usual line of work then I'll do something to make money until I can get back into my field. That's not arrogance. That is providing for the family with the available means as opposed to being unable to provide for the family with means that are not available. Yes, one can be productive on a computer with a dial-up connection. One can also be productive on a computer with no connection. But what are you going to do that is productive? You still need money to purchase software (unless of course you're downloading pirated software which amounts to stealing). You don't need a computer to read a book about coding, databases or whatever interests you although it may help later for implementing what you're learning, you can write algs, code, and trace without a machine. If you can afford to buy these books, you can afford to drop 100 bucks per old outdated system. I've done my time in the spare bedroom with my 8 computer network testing this and experimenting with that, but guess what, I bought all those computers... and paid very little for most of them. People don't owe you anything for your ability to keep up with the IT field, so get off your ass and go to work (anywhere). [ Reply to This ]

Re:Experimentation

[DexterF]

You've dropped below my Stupdity Tolerance Barrier in only two lines of response - if one wants to call this braindead heap of wordtrash a "response" at all.

I gather you seem a fitting recipient for penis enlargement spam - let me know if I can redirect it to you, otherwise please never ever talk to me again before you are at least 16.

Re:Experimentation

[Random Destruction]

The world sure seems simple from up there eh?
How is "if you can afford x, then obviously you can afford y" ever a valid argument (while x If you can afford a ($30) book then you can obviously afford (one or more) $100 computer(s)?
Right now I could spend $30. I couldn't spend $100, and that makes sense, because 100 > 30.. or perhaps I'm just too stupid comprehend money like you...

Though to the grandparent, if you are helpful enough to people with computers, they will generally give their old ones to you. I get them pretty often, and generally redonate them to others who want simple boxen.

Waste of energy?

[Savage-Rabbit]

I think the OP's point was : for 2x the power consumption (250 Watt -> 500 Watt), you get 10x the compute performance (300 MHz -> 3 GHz).

So, if your goal is to get the best performance / killowatt-hour, you're better off running fewer, newer, machines.

Actually the OP advocated using '...State-of-the-art computers...'. That's fine if you can afford them, these guys may be using old inefficient hardware but they are getting it for free and if they are running the whole mess on bio diesel the electricity is also practically free since Biodiesel can be made from used vegetable oil which can be had for free at any fast food resturant. I am not going to judge the usefulness of this cluster from a compter science standpoint. However, judging from TFA, with free hardware, free software, free energy other than the purchase and running costs of the generator and the treatment costs for the fuel which into the bargain is environmentally friendly, you'll have a hard time beating this setup for cost efficiency. If we assume the work on the project is done by voulenteers the only other major cost factor would be the cost of housing this setup.

Re:Frist "Beowulf Cluster" post!

[sxtxixtxcxh]

in soviet russia, rusty 386 beowulf clustered overlords, for one, welcome YOU

Powered by vegetable oil...just like

[Anonymous Coward]

many slashdotter's blow-up girlfriends. POW!

Re:Powered by vegetable oil...just like

[Anonymous Coward]

Dude, that doesn't even make sense.

Re:Powered by vegetable oil...just like

[Anonymous Coward]

shut up and pass the oil...my blow-up doll is getting dry

Cool

[Xerp]

With a veggie oil powered generated, they really should have a distro called OilSlix...

Don't forget to mention the...

[Expert Determination]

...Oakland Technology Exchange.

Back to the Future

[craXORjack]

Dr. Emmett Brown: Marty, I'm sorry. But the only power source capable of generating 1.21 gigawatts of electricity is a bolt of lightning.

Marty McFly: [startled] What did you say?

Dr. Emmett Brown: A bolt of lighting. Unfortunately, you never know when or where it's ever gonna strike.

Marty McFly: Hmmmm... What about vegetable oil?

Dr. Emmett Brown: Well of course, vegetable oil. But where are we going to get vegetable oil in 1955?

Re:Back to the Future

[operagost]

I'm sure in 1985, Wesson is in every corner drugstore!

Re:Frist "Beowulf Cluster" post!

[Tablizer]

I think I regret feeding the animal now

Some sample energy consumption figures...

[SuperBanana]

Just for comparison's sake, I borrowed some Kill-A-Watt meters and measured my gear.

• Powerbook 1ghz 17": Idling, about 15w, full-bore 29W or so
• Dual P3-850 2U rackmount: 150W
• Dual 2Ghz G5 Xserve rackmount: 175W
• Mac Mini 1.25ghz: Idling, 11W, full bore, about ~25W
• Celeron (original celeron) 450mhz PC. No hard drives, one CPU fan, one PSU fan, floppy, 2 net cards, CDROM drive. 65W, idling (running a bsd-based firewall.)

The shocker was how low the Mini's power consumption was, and how high the celeron router. Also, the Xserve, Mini, and Dual P3 all had power factors of .99, whereas the celeron had a power factor of about .6...ie, not power-factor corrected.

Oh, and switchgear? Varied from 1W (yes, ONE watt!) to ELEVEN for an old 100BaseT switch. The lowest power consumers were newer hubs, second by a pair of gigabit switches I bought within the last year that were about 5-7W.

Re:Some sample energy consumption figures...

[runderwo]

whereas the celeron had a power factor of about .6...ie, not power-factor corrected.

That's nothing to do with the CPU or the PSU age, and everything to do with how cheaply designed the PSU was. There are tons of brand new PSUs on the market with absolutely crap power factors.

Re:Frist "Beowulf Cluster" post!

[rdoger6424]

In Korea, only the very old rusty 386 beowulf clustered overlords, for one, welcome you.

how much total energy...

[zogger]

...to completely produce every new component in a new machine, fab it, assemble it, all the components top to bottom case to mobo, power supply to optical drives and etc, etc, and ship it around? The general societal TCO? Are those prices and watts and ergs and joules and BTUs and whatnot in the calculations of how much it "costs" in energy compared to just using an older machine for a much longer time period before it is junked? And how much does it cost to safely junk an old machine? Can we add in the eventual environmental cleanup costs here as well? Judging by various "superfund" costs it is not cheap. Judging by health insurance costs it is not cheap. Judging by cost of oil and what is apparently necessary politically to keep that oil flowing to run the mines to run the smelters to run the ships to run the trucks and so on and so forth is not cheap. What is the cost of peoples' medical expenses from all the poison in the environment from the throw away culture because something a few years old is now "obsolete", even if it is still functional?

I don't know the exact answers to any of those questions, just take a SWAG at it and say "not cheap", and I think it is fair to ask the questions and not just fixate on the "cost of running" the machine by todays kilowatt/hr quote and some CPU benchmarks.

Etherboot

[Kadin2048]

It would seem from the ParallelKnoppix that the preferred way to build a cluster is by network booting them. It's possible to boot each node from a Live CD but the author of the tutorial at least doesn't seem very enthused about the idea.

So it would seem that if you were going to troll for donations, your minimum spec would be something that either had a bootable NIC in it, or was capable of accepting one that you'd be able to acquire easily (i.e., has PCI slots, no old ISA garbage).

If it was me trying to build a cluster in a real hurry, I'd think the best thing to do would be to take etherbootable PCs and put them in the cluster, and take everything that wouldn't boot and rip them apart for spares. Doesn't seem like it would be worth the time to screw around with old/unsupported hardware, or building custom boot images.

We Are Trapperkeeper

[PingXao]

We are one.

Screw you, Fatass.

Heh, screw YOU!

I wish them luck...

[teebob21]

I got excited about cluster computing a couple years back. I spent about $600 on parts for a 12-node Pentium II cluster, then spent 3 weeks setting it all up. I then spent another 6 weeks with a comp sci professor trying to reverse-engineer the Folding at Home client to parallelize the data units. (Psst...don't tell Vijay!) Our solution was to use the F@H client as-is, and to network the nodes as additional drives and run a client with a different machine ID on each drive.

As it turned out, a single 1.1GHz P3 was doing more folding than 12 350MHz P2's working in parallel. I scrapped the cluster and sold the parts on eBay. My electricity bill dropped about $100 a month afterwards. Again, I wish them luck.

Re:I wish them luck...

[Anonymous Coward]

So one fast machine did more work on protein folding than twelve slower machines? Not surprising considering the differences in clock speed and chip design - but looking at the multipliers which other commenters have been bandying about, if you use that one fast machine for much of anything else, suddenly the twelve machines grinding away on just the one task are going to catch up. 15x speed doesn't help quite as much when you start multitasking.

Re:I wish them luck...

[Anonymous Coward]

This probably had more to do with the arch of the cpu then anything

For example I have a ppro 200 (use it for fairly light work, home use proxy cache, yes im bored). Yet it smoked most p2 400s. It was because the cache was nearly on die for the ppro and same speed as the cpu. Yet for the p2s it was a good distance away and half the speed (if you were lucky). It was not until the p3 came out with the cache on the same chip that we saw what the ppro arch could do again. As it was on chip and the same speed as the cpu again. The p4 cut the speed of the cache and its performance suffered for it.

Those folding at home things and seti are very memory subsystem dependent. If you look at the stats you will see computers with half a meg to one meg of cache that are on chip blowing away similar kind of machines where the cache is not on chip.

These days its fairly hard to buy a new computer where the cache is not on chip. So you may need to look in the 600-1000 mhz ranges to see this.

I would be willing to bet if you had underclocked the 1.1ghz computer to 350 mhz that it would still have beat one single node. Just simply to arch changes in the computer itself.

Hex

[tsa]

The first thing I thought when I read the title was: Hex! I read too much Pratchett...

I did this once

[DurendalMac]

With 16 old Beige G3s, Mac OS 10.2.8, and XGrid PR2. Yeah, it was crap, but I did it just to do it. I got all sixteen running and ran some of the Xgrid scripts, but beyond that, I had no use for the damn thing. I only had 10Mbps hubs anyway. Built the thing for next to nothing, too.

Historical note

[reboots]

ACCRC has been parallel processing with vegetable oil for a while now. Here are some photos of their cluster I took during a visit circa July 2004, with another pic of the generator.

AFAIK the generator uses straight vegetable oil, rather than biodiesel which is formulated for use with unmodified diesel fuel systems. Note the copper heat exchanger and foil insulation on the generator; the oil must be heated to reduce its viscosity before introduction to the engine.

At this point I think SUSE was their distro of choice, at least for the desktop (SUSE/KDE is visible on the monitor node console). Not sure what the rest of the cluster was running.

...reclamation of fuel & CPU cycles?

[itomato]

Unloved fry grease meets unloved computers to make parallel super(?)computing cluster. How is this bad in any way?

Already partially complete

[chazchaz101]

I voulenteered at ACCRC for quite a while up untill about 7 or 8 months ago. When I was there, the generator was working to some degree and the cluster was up to somewhere around 20 GHz total CPU power. At that point, he had done several renders including a nice fly by of a chess board and I'm sure he's done a lot more since then.

The Make Faire seems like a good opertunity to expand and show off the cluster, and demonstrate what can be done with technology generally concidered antiquated.

MOD PARENT UP.

[Anonymous Coward]

It's true.

For speech and debate, I researched, wrote, and delivered a speech about electronic waste. To summarize it: we discard 7 million tons of electronics every year (that's 50 pounds from every man, woman, and child in America). Furthermore, e-waste is uniquely toxic: you can't landfill it (lead and mercury tend to leach out of electronics), and you can't incinerate it (plastics release dioxin when burned). So, as it turns out, we export it: according to "Exporting Harm", a groundbreaking exposé by the Basel Action Network, corrupt recycling corporations are illegally dumping electronic waste overseas. In fact, 50-80% of our supposedly "recycled" electronics actually end up in third-world villages, poisoning their land, water, and air.

The proposed solution was:

1. Ratify the Basel Ban on international hazardous waste export (157 other nations have already done so; the United States is the only industrialized nation on Earth that has refused to join.)
2. Phase out the use of 7 of the most toxic chemicals used in PC manufacturing (all of the European Union nations have already banned these 7 particular chemicals, and thanks to the Electronic Waste Recycling Act of 2003, the state of California will do so by 2007)
3. Adopt producer take-back programs (similar to those in Europe and Japan), in order to give manufacturers an incentive to design and build cleaner computers in the first place.* The easier it is for a company to recycle the "taken-back" computers, the more of an edge they have over their competitors.

In the meantime, as a consumer, it's very important to make sure that your local recycler doesn't export. The Basel Action Network maintains a list of recyclers that have pledged to get rid of hazardous wastes responsibly: http://www.ban.org/pledge/Locations.html

*Note: because of this requirement, manufacturers will actually sell the "cleaner" version of a PC (made with fewer toxins) to European and Japanese consumers, and sell the "dirtier" version to US consumers.

Better "Beowulf Cluster" post!

[CdBee]

In soviet russia, rusty 386 beowulf clustered overlords, for one, welcome donations of old hardware!

Sorta.

[Anonymous Coward]

Well, I don't comment here all that often anymore, but wth, it's Saturday morning.

Intarweb access can be as cheap as $7/mo for dialup. Yes, it's slow, but with a free computer whereas there was none before, people will take what they can get.

A free, old PC of mine served as a springboard into Linux for a neighbor of mine without the funds to buy a new PC or OS for it (hence Linux) himself. He was elated to share (slowly) tracks of his guitar playing with old bandmates and still contribute. Now, none of this is pro/big-time/fast/whatever, but for a guy on disability, on fixed-income and not too mobile - it could be worse.

I've graduated, moved on, but still get a note from time to time on a Linux thing, which I'm happy to help out with assuming I've not answered it before ;)

They charge a fee to donate?

[nurb432]

What sort of garbage is that?

Not worth it

[mnmn]

Not worth it at all except for slashdot-article posts. You can buy an Athlon64 cpu + motherboard + 512mb ram for $250 and thats equal in power to dozens of PII machines, which will use up $250 worth additional power in under a year. Consider issues of space, the fact that its way more work and unreliability, and its obvious the pace of development is so fast that using 10 year old machines is never worth it. If you need to run many single-threaded apps, its still better to use one Athlon64 machine... but even better to use a dual-core or an Ultrasparc T1 with 8 cores, each core working equal to many PII machines.

The only use (slower) PIII and older machines have, is to be sent to poorer countries with knoppix CDs, since they have no money but enough labour to work and fix the computers. Electricity is generally cheaper there too (Iran, Pakistan, central asian, african) so it becomes worthwhile. So instead of building megaclusters, please donate them to poorer countries.

Re:Not worth it

[tinkertim]

I think the whole point of the 'project' was to show that older hardware still had usefuless to some people, though useless to most. Mostly to (I think) try to convince people to get off their duffs, go out to the garage, grab those two old desktops and drop them off some place that could use them.

And don't forget Linux people tend to do things simply because they can. However I agree this is not great feat. This was plugging in a bunch of computers to a switch tossing in some CD's and powering up the boxes.

I once toyed around with some ULV p3 SBC's that I got in a lot. Nice low profile ones with a CF socket, all kinds of I/O risers and 2 on board nics. 5V at a pretty low draw, I was going to use some photovoltaic cells and some marine batteries to make a little eco cluster. CF is large enough (came with each one) to hold an etherboot setup / initrd and each one can handle 2 x 256 SODIMMs. May still do it if I can find a free weekend.. and the SODIMMs cheap enough.

If any applause is warranted, shoot over to the Parallel Knoppix site and drop the author a line.. he's doing some interesting things and is really enthused about his project. I host the only US mirror for k-pix, he could use some more.

Point being (and yep I have one) don't just post about how bad someone else's idea was .. enjoy yourself some and tinker with your own :) Nothing wrong with taking some time to do something completely senseless if you enjoy it.

Help Africans?

[Anonymous Coward]

Not with *my* hardware. id rather burn it my front yard than help out a bunch of fucking jungle bunnies.

A great deal...

[Junta]

Well, one, many applications can work in a very heterogeneous environment, if the work is divided correctly. The easiest examples are protein folding where each system can work an individual protein, and the faster ones don't need to wait to get more work units, rendering, breaking encryption, certain types of physics simulations.

Now let's assume you have an application where you can't efficiently divide the work such that there is no intrinsic codependency between node work, and that what you say holds, that the slowest node dictates performance for the whole cluster. The simple workaround is to have the number of jobs running on nodes be asymmetric. I.e. you have 6 systems at 1 GFlop/s each and 6 at 2 GFlop/s each. So on the first 6, run 1 'thread' per node, on the latter 6, run 2 threads per node. It would of course be more complex depending on the characteristics of the node and job, but generally if an application can be scaled to arbitrary number of nodes for computing, you can scale it asymmetrically. Of course, be sure the other subsystems of each node are sufficiently good to handle twice the workload, particularly memory.

Vegetable Oil?

[EmagGeek]

I wonder how terrible the emissions are on that old generator.

Re:Vegetable Oil?

[chawly]

Fries with that ?

Well!

[Davey McDave]

I for one welcome our vegetable oil consuming, self replicating computer overlords, and wish to remind them how valuable I can be rounding up slaves for their vast recycling of old computer parts.

Yeah yeah, it had to be done, mod me down already.

Re:Well!

[chawly]

May I join you ? Perhaps there should be an official song of welcome ? I agree that it was imperative ..... absolutely imperative.

What can you *do* with a cluster?

[shish]

On a tangent; I got 8 PIIs working together with clusterknoppix - then having spent the day setting it up, realised I had absolutely no use for it -- any ideas?

Veggie Oil is not the same thing as Biodiesel

[uranus65]

http://en.wikipedia.org/wiki/Biodiesel/

Re:I wish them luck... but in South Korea ?

[chawly]

I think that your post implies that "In South Korea, where only old people have the time for this kind of thing, they can't do it because of the cost of the electricity !" Perhaps they might try if they had a generator which ran on fish oil. Donations anyone ?

Cluster...

[Baiken]

Imagine a Beo......, forget it

Achain is as strong as...

[MadMagician]

It's a common observation, if you've ever done any benchmarking, that the weakest peice of a cluster is the bottleneck. It's conceivable that heroic programming could adjust for this, but it doesn't happen in the Real World [aka MPI].

The cube

[PermanentMarker]

And so the first cube was born. There was no new technologie invented for it to work. But all kind of technologies had been assimilated in it. It was an intrestic peace of hardware and was running neurologic software. So it could improve and adept to new hardware. Trough a tiny speaker we could even hear it talk.

I'm a the borg you'l be assimilated and adepted to my collective hardware, Resistance is...

Well then the sound stopped as one peace of hardware broke, and we're now trying to make a kind of cluster of cube's so they can repair eachother. It is also thought that this would be more impresivly powerfull.