Beta

Slashdot: News for Nerds

×

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

Thank you!

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

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

Grid Computes 420 Years Worth of Data in 4 Months

Zonk posted more than 7 years ago | from the that-is-a-lot-of-nerd-hours dept.

Biotech 166

Da Massive writes with a ComputerWorld article about a grid computing approach to the malaria disease. By running the problem across 5,000 computer for a total of four months, the WISDOM project analyzed some 80,000 drug compounds every hour. The search for new drug compounds is normally a time-intensive process, but the grid approach did the work of 420 years of computation in just 16 weeks. Individuals in over 25 countries participated. " All computers ran open source grid software, gLite, which allowed them to access central grid storage elements which were installed on Linux machines located in several countries worldwide. Besides being collected and saved in storage elements, data was also analyzed separately with meaningful results stored in a relational database. The database was installed on a separate Linux machine, to allow scientists to more easily analyze and select useful compounds." Are there any other 'big picture' problems out there you think would benefit from the grid approach?

cancel ×

166 comments

Malaria? (-1, Offtopic)

Anonymous Coward | more than 7 years ago | (#18048118)

This seems like a waste of computing resources to me. How many people do you know with malaria? Cancer is far more prevelant.

Re:Malaria? (0)

Anonymous Coward | more than 7 years ago | (#18048168)

You can kill malaria with poisons/pesticides and by changing the ecosystem, so in this sense it's preventable. Some cancers are preventable (lung cancer), while others not so easily.

Re:Malaria? (1)

Anonymous Coward | more than 7 years ago | (#18048212)

But not all lung cancer is preventable. Non smokers can have virus caused cancer in the lungs.

Re:Malaria? (1)

Fordiman (689627) | more than 7 years ago | (#18048654)

I, ah, though quinine cured malaria...?

Re:Malaria? (2, Informative)

God'sDuck (837829) | more than 7 years ago | (#18049396)

quinine cures malaria strains not yet resistant to quinine.

Re:Malaria? (4, Informative)

Soporific (595477) | more than 7 years ago | (#18048234)

According to:

http://archive.idrc.ca/books/reports/1996/01-07e.h tml [archive.idrc.ca]

Malaria kills quite a few people every year so I don't think it's a waste.

~S

Re:Malaria? (3, Insightful)

alshithead (981606) | more than 7 years ago | (#18048320)

When you consider global warming...malaria WILL become a huge problem for many areas that haven't had to worry about it before now. This is in no way a waste. Buy your quinine now and while you're doing it...buy stock in the companies that manufacture it.

Re:Malaria? (4, Funny)

Anonymous Coward | more than 7 years ago | (#18050412)

Yes, I'm concerned about global warming too. But I think you're off base about malaria. Sure, there is a chance that malaria will be more prevalent. However, I think our real resources should be put to combating the animal predators from the North who will want to eat us for lunch.

First, when global warming happens, all the polar bears will come South looking for something to eat. We are probably on the top of their list. First, the bears will be real angry at us because we melted their front yard. And secondly, we happen to be the fattest creatures around--there is a lot of meat on our bones. And don't even get me started on what will happen to our shrubbery when the reindeer head this way.

I think instead of wasting CPU cycles on malaria, we instead should be using those computing resources searching for a safe but effective polar bear repellent. That way we have our priorities straight. Just my 2 cents.

Re:Malaria? (2, Insightful)

iminplaya (723125) | more than 7 years ago | (#18048380)

Unfortunately, most of the people killed are considered somewhat "less than" human. It goes a long way to explain the lack of interest, while other diseases are more politically expedient. The profit margins just aren't there.

Re:Malaria? (0, Troll)

sumdumass (711423) | more than 7 years ago | (#18048596)

It isn't somewhat less then human. It is not seeing the need to rush and aid someone who lives near danger on purpose. Especialy when the most effective control has been taken off the market because of enviromental concerns.

I mean, would you really think it is most benificial sending food to starving children living in an area incapable of supporting life (like s desert) over moving them to a place that could?

Re:Malaria? (3, Insightful)

iminplaya (723125) | more than 7 years ago | (#18048690)

Actually I'm sure they would love to move to more fertile, profitable areas. Unfortunately, there are others with a different agenda who like to keep them away. Those people are getting much more outside help than the starving kids. Let's not forget the economics of the arms trade with african warlords and corrupt tinpot generals who are, of course, "good for our interests". I'm also aware that basic sanitation and clean water, both cheap and easy to achieve with the right thinking, will take care of probably a full 90% of the problem. Their old traditions are responsible for much of it. The parent's link lead me to this [archive.idrc.ca] . It has to be just the tip of the iceberg. So the chemical insecticides are not needed. There are far too many unexplored, easily accessable natural solutions.

Outsiders really aren't interested in Africa's problems, unless it interferes with "free trade". This will be solved by the Africans with relatively little outside help. It's just the usual numbers game.

I've heard that gin is a good mosquito repellent.

Re:Malaria? (0, Flamebait)

sumdumass (711423) | more than 7 years ago | (#18049158)

Well, My piont was that nobody in their right minds think that some people are less then human. They just don't jump at a cause to help them because of various reasons. You pointed out a few good ones too.

As for waiting untill it effects free trade. It is normal for a person to not care much about situations that don't effect them. This isn't anything new or novel. It might not be the best practice to have but it is a reality in life. I really don't see much wrong with it other then it tends to lend the opinion that if you don't think your being heard do something to effect something they care about. But even this is a trivial concern. Most humans get this idea from their parrents who ground them from nitendo or something they think you like to punish you.

Personaly, I have enough troubles running my own life without having to concern myself with someone across an entire ocean that doesn't influence my life at all. And when malaria does effect my life, you bet your bottom dollar that I would use anything to stop it even if it was bad for the enviroment. Why, Because it is that easy to control and rid the risk of it.

Re:Malaria? (2, Informative)

iminplaya (723125) | more than 7 years ago | (#18048966)

After a little poking around, I found what looks like the stuff [realgreenlawns.com] they put on the nets. It was under their noses all along. And I would venture to think that the they (the Africans) have known about it for a very long time. I'm too lazy to find out how well it controls these guys [ox.ac.uk] , something even more neglected in mass media. Nature triumphs the computer again. Okay, now I'm drifting off topic, but it at least I did it seamlessly and gracefully :-)

Re:Malaria? (1)

DonnieD701 (735118) | more than 7 years ago | (#18050156)

Hey, this stuff kills all kinds of insects... Won't somebody think of the larvae?

Re:Malaria? (1)

Ambitwistor (1041236) | more than 7 years ago | (#18050376)

I mean, would you really think it is most benificial sending food to starving children living in an area incapable of supporting life (like s desert) over moving them to a place that could?
1. Deserts aren't incapable of supporting life.
2. Most starving children don't live in places as hostile as deserts.
3. Where would you like to move them? How many tens of millions of refugees would you like to support in your home country, give land to, find jobs for, and so on? If it's not a majority, which other countries would you prefer take on the task of relocating entire nations?
4. In short, have you considered the social, political, and economic implications of a mass relocation project?

Re:Malaria? (0)

Anonymous Coward | more than 7 years ago | (#18048434)

you must live in a western nation

Re:Malaria? (1)

tkdog (889567) | more than 7 years ago | (#18050384)

You're a troll. But for the record millions of people have malaria right now, there aren't easy cures especially for certain strains and the economic toll is huge.

gnaa (-1, Offtopic)

Anonymous Coward | more than 7 years ago | (#18048126)

join teh gnaa if u r tootaly a winrar

Excellent (5, Funny)

President_Camacho (1063384) | more than 7 years ago | (#18048132)

The search for new drug compounds is normally a time-intensive process, but the grid approach did the work of 420 years of computation in just 16 weeks.

Cue the stoners in 5, 4, 3, 2....

Re:Excellent (0, Troll)

Mullen (14656) | more than 7 years ago | (#18048188)

It's Friday night and they are too stoned to respond to that setup.

Re:Excellent (2)

Mr2001 (90979) | more than 7 years ago | (#18048198)

It's a shame the tagging system doesn't allow numeric tags. I had to tag this story "fourtwenty" instead.

This is evil (0)

Anonymous Coward | more than 7 years ago | (#18048370)

4/20 is the birthday of Adolf Hitler. Therefore, this is very evil.

Plus, 4+20-1 is 23. ((4*20)-11)/3 is also 23. More proof of it's evilness.

Re:Excellent, I'll Drink to that! (1)

SubliminalVortex (942332) | more than 7 years ago | (#18048382)

I'll take a Gin and Tonic (with Quinine, of course).

Are there any other 'big picture' problems... (-1, Flamebait)

Anonymous Coward | more than 7 years ago | (#18048404)

out there?

Yes. For example, how did a carpetbagging bitch who murdered her accountant get to be the senator of New York and the leading Democratic presidential candidate?

Re:Excellent (2, Funny)

Varun Soundararajan (744929) | more than 7 years ago | (#18048440)

The Answer to The Ultimate Question Of Life, the Universe, and Everything == 42 Malarial Drug Research == 420 420 is 419 + 1 (419 - remember Nigeria?) Malarial Drug Research/Answer to Ultimate question = 420/42 = 10 remove 0 from 10 :-) and it is 1 , subtract 1 from 420 and it is 419..... Something is really really fishy...

Re:Excellent (2, Funny)

Varun Soundararajan (744929) | more than 7 years ago | (#18048476)

The Answer to The Ultimate Question Of Life, the Universe, and Everything == 42

Malarial Drug Research == 420

420 is 419 + 1 (419 - remember Nigeria?)

Malarial Drug Research/Answer to Ultimate question = 420/42 = 10
  remove 0 from 10 :-) and it is 1 , subtract 1 from 420 and it is 419.....

Something is really really fishy...

----
comment already exceeded retard limit, hence no sig.

Re:Excellent (2, Funny)

CommunistHamster (949406) | more than 7 years ago | (#18049906)

Numerology: For when you have no real evidence.

Re:Excellent (1)

TapeCutter (624760) | more than 7 years ago | (#18050092)

Love the (non-)sig.

Re:Excellent (1)

UncleTogie (1004853) | more than 7 years ago | (#18048924)

I am not as think as you stoned I am.

Re:Excellent (1)

riff420 (810435) | more than 7 years ago | (#18049376)

I am as stoned as I think you are, and I think you're very stoned, but only because I am.

YEAAAAH.

look at the name.... (1)

ganjadude (952775) | more than 7 years ago | (#18048962)

sorry... nothing to contribute today but my name {thats what alcohol does... if i was (just) stoned, i would have a few pages to contribute}....damn alcohol....

Wikipedia? (3, Interesting)

JonathanR (852748) | more than 7 years ago | (#18048176)

It strikes me as strange that something like Wikipedia could not be distributed across user's PCs in more of a peer-to-peer fashion. Surely the web itself could benefit from further decentralisation. This issue bothered me some years ago, when I discovered that my desktop PC at work had about 40Gb of unpartitioned disk space. I often wondered about the sense of running file servers in big organisations, when each user probably has a few tens of gigabytes of unused or unpartitioned disk space. If illicit music and video can be distributed by P2P, why not all information?

Re:Wikipedia? (0)

Anonymous Coward | more than 7 years ago | (#18048242)

Bandwidth is not free. This would just be shifting the cost towards everyone else.

Re:Wikipedia? (0)

Anonymous Coward | more than 7 years ago | (#18048310)

And how do you propose this important company data is backed up? This creates a bigger problem than it solves, much easier to backup a single file server than 100 separate PCs with data on each one.

Re:Wikipedia? (2, Interesting)

Fordiman (689627) | more than 7 years ago | (#18048762)

The system would be designed for it.

P2P isn't a good model, but I can think of one:
Data, as it is created, is stored in the users' shared folder. As other users go to access it, a copy is made from the cloud (as long as filename/size/hashes match) and that copy is used so long as the creator's copy hasn't been modified. When writes are done, they're done locally, and a patch is sent to the original copy. If the creator can't be contacted, or his copy doesn't exist, the last-writer becomes 'creator'. The file's creator is identified by his DC user name.

Backing up is simple. For every creation/update that is made, a patch is queued or sent to a backup server. The server ONLY queues the originals and patches, so that past-versions are accessible. As space becomes unavailable (say, below 10%), the backup server alerts the IT guys that it needs to offload some stuff, and condenses changes of the oldest files in the local copy. When a delete is made, that is considered a write and handled accordingly.

In the event of a reinstall (ie: the local copy of the files are deleted, but the world hasn't been notified), the user, upon connection would query the backup server to see where his stuff has gone, and get it back.

One could create this system to act like an SMB share, with access levels and program-independent drive/directory mapping, but with one added benefit: user-creation and auto-mapping. The DC would automatically tell the system which peer-shares are available to him upon login. The user can then filter out what he needs as he uses it, but can index-search it all (a query is sent to the backup server, which, like a good little machine, has been indexing as backups are made).

Lastly, for reverse compatibility, the backup server could provide SMB access to its copies, ensuring that non-updated systems can still access their stuff.

I don't know about most organizations, but I work at Penn, and a system like this could work admirably.

Re:Wikipedia? (0)

Anonymous Coward | more than 7 years ago | (#18048402)

because it's really fucking slow compared to a centralised system? it's a dumb ass idea.

Re:Wikipedia? (1)

MrCoke (445461) | more than 7 years ago | (#18048424)

Because Wikipedia contains information, 'facts', figures and data. Place it on P2P and it will be tampered with a lot more then now.

IMO.

Re:Wikipedia? (1)

TodMinuit (1026042) | more than 7 years ago | (#18048500)

Because Wikipedia contains information, 'facts', figures and data.

Oh man... That's a good one!

Re:Wikipedia? (1)

battery111 (620778) | more than 7 years ago | (#18048504)

I really don't think tampering is much of an issue since people can freely edit facts and figures in wikipedia anytime they want anyway. However, the previous concerns about speed and bandwidth costs are valid points. As for corporate fileservers. aside from the backup issues mentioned previously, there is also the issue of ensuring everyone sees the same thing. It's much easier, say, with software, to have all the software stored centrally and have all computers get their software from this one place. Makes updates much easier, and ensures version consistancy across the enterprise. I don't remember where it was, probably slashdot, a few weeks ago when it was mentioned that there is a movement back towards dumb terminals. Reasons being cost (terminals are much cheaper than PC's), and ease of management. P

Re:Wikipedia? (0)

Anonymous Coward | more than 7 years ago | (#18048728)

http://freenetproject.org/ [freenetproject.org]

Anonymous, peer-to-peer information net.

Re:Wikipedia? (0)

Jessta (666101) | more than 7 years ago | (#18048760)

Yes, wikipedia could be decentralised. But between different web servers in data centres not to people's desktop computers.
I would find it really annoying that the particular data I wanted was on your computer and your computer wasn't on or was infested with malware because you don't know how to properly administer you computer.

The main reason for having central file servers are:
1. Backups - By storing all the data in a central location it's much easier to make sure that all data is properly backed up
2. Security - By storing all the data in a central location it's much easier to restrict access to only authorised users.
3. Availability - It's easier/cheaper to implement system to maintain high availability(RAID, UPS, fall over systems) of data on a centralised system.

40GB is so cheap that it's not worth the effort to utilise.

Re:Wikipedia? (1)

mollymoo (202721) | more than 7 years ago | (#18049096)

1 and 3 come down to having multiple nodes and copies of the data, which is trivial for a distributed network. The security thing can be dealth with using existing crypto stuff - hashes for integrity of it's no sensetive, encryption if it is sensetive. 40GB may be cheap, but 400TB (a mere 10 000 users) isn't so cheap.

Re:Wikipedia? (2, Informative)

elchuppa (602031) | more than 7 years ago | (#18049508)

Well this is an excellent question. Actually Van Jacobson is on google video [google.com] with a presentation on this precise pet peeve of yours. The main concern I have with the idea, at least with how Van Jacobson presents it is that with information addressed by content rather than location, it's slightly more challenging to locate it. At least with the IP system you can route closer towards your destination at each hop up and then down... But data without an authoritative source is basically lost. If you don't have it, you don't really have any reason to inquire about it with any one node over any other. There is a space for peer to peer data systems, and he does have a point over those live media feeds getting saturated. The truth is that all data should be potentially torrented. That's why bittorrent may be one of the most fascinating and potentially effective inventions in the modern(internet) software era (last 10 years). Bugger. so I don't have much constructive to say what with my current state of mind, except that most of the other replies are rudely and stupidly dismissive of the idea. It both resonates and feels like the future, but it's not a trivial problem. Actually it most certainly is... it's just a matter of stating it so that it is trivial.

Your hard drive yes, Wikipedia no. (1)

SanityInAnarchy (655584) | more than 7 years ago | (#18049752)

Your work computer can be managed by the company you work at; they can even revoke root if they're concerned about security. There are actually a few existing distributed filesystems for Linux, though most of them suck, and the few I've seen with the potential not to suck either cost money or are a long way from being stable on Linux. Haven't seen ANY of these on Windows.

Someone mentioned backup, which isn't a big deal. Ever heard of RAID? Yeah, it could be something like that.

Although if it's a desktop PC, the 40 gigs probably isn't worth the power required to keep your computer on, and they're probably better with insanely aggressive local stores to speed up disk access. But again, these kind of suck for Linux.

The closest thing to a solid, clean design that I can find for Linux network filesystems is NFS, and that doesn't have any of the features we're talking about -- not without combining it with one of these other kludges...

Re:Wikipedia? (1)

ikkonoishi (674762) | more than 7 years ago | (#18050430)

Overhead mostly. Also there is a good chance of important data being lost when one of the computers holding part of a critical application goes offline. Sure you could add redundancy, and rate the importance of certain things so they would go to dedicated systems, but then you have even more overhead.

IA and speed (1)

briancnorton (586947) | more than 7 years ago | (#18050500)

It's called information assurance. There are reasons that a Netapp/EMC array costs $25,000 per terabyte when a 1TB maxtor usb drive costs less than $1000. The first is that it is made to tolerate faults and be redundant. Sure you could do this in an enterprise, but then you end up with massive duplication to get around people turning off their computers, a massively expensive and complex distribution and tracking system, and higher failure and lower performance of desktop drives that are now running your webserver and processing an access DB for the local user. The second is speed. Data IO has always been my limiting factor. Working with any kind of media, large databases, etc, speed is king. Not only are desktop drives single channel and slower (RPMs), but they are now seperated over a network that may already be flooded. Information assurance isn't cheap, but it's worth it.

Ok, how does this apply to patents? (4, Interesting)

zappepcs (820751) | more than 7 years ago | (#18048180)

If the grid solution finds THE cure for H5N1, will it be patentable? If not, who pays for the R&D to implement it? Who gets the patent? Do the thousands of people who allowed their PCs to be used get anything? Will big drug companies be able to use this and keep the prices low for the final product?

Re:Ok, how does this apply to patents? (4, Interesting)

Dr. Spork (142693) | more than 7 years ago | (#18048280)

These are all good questions, and every user who volunteers their computer for something like this should find answers to them. I'm quite sure that the stuff discovered by distributed networks does not automatically enter the public domain, but in cases like SETI and protein folding, the organizers explicitly state that it will. But it wouldn't be illegal for a drug company to use volunteers' computers just for corporate profit. You have to judge the merit of each of these projects on a case-by-case basis. Remember also that there is a cost to participating: you have to run your computer at peak power, and this will add several hundred dollars to your utility bills each year while polluting the planet with extra coal smoke and CO2.

Re:Ok, how does this apply to patents? (1)

iminplaya (723125) | more than 7 years ago | (#18048312)

Will big drug companies be able to use this and keep the prices low for the final product?

And people accuse me of living in a fantasy world...

Re:Ok, how does this apply to patents? (1)

Crazy Gilmore (1065234) | more than 7 years ago | (#18048656)

I think you are confusing grids with distributed peer-to-peer computing networks. Grids are formed of (usually) clusters of nodes, usually running Linux. They are designed for problems that require massive amounts of computation, often involving multiple cooperation nodes running in parallel, and normally amounts of data so large that it is simpler to send the programs to a cluster near the data. http://en.wikipedia.org/wiki/Grid_computing [wikipedia.org] Shared processing systems a la seti or BOINC are loosely coupled systems where a modest amount of CPU power running a fairly small set of data is contributed to a larger project. In a grid system the users are normally researchers at universities or research institutions and the ownership of the IP is fairly clear.

Re:Ok, how does this apply to patents? (1)

edschurr (999028) | more than 7 years ago | (#18049766)

I don't see why people are very concerned about the patents. Yeah, I want cheaper medicine, but expensive medicine is still better than no medicine at all. My CPU is wasting many cycles, and I suspect the electricity won't cost much (although I have to look into that). Then again, maybe our CPU time is valuable enough that the pharma companies would rather give up the patent than give up the time. I doubt it. The alternative might be Universities.

Re:Ok, how does this apply to patents? (1)

Mutatis Mutandis (921530) | more than 7 years ago | (#18050282)

What the grid computing will have produced is likely to be a set of predicted structure-activity relationships (SARs), i.e. calculations that say that molecules of a certain shape and with a certain charge distribution might be active. You can patent a group of molecules for a certain disease, so I guess that this would be patentable. (Who gets the patent is not actually that important. Licenses have been invented to solve that problem.) However, if you want to have a claim that stands up to some contest, you would better also demonstrate activity in the real world. Lots of people in the business are very skeptical about in silico drug discovery, and not without reason. The art is still in its infancy.

The gorilla in the room is the harsh reality that a SAR is not a drug. Lots of potentially interesting compounds will have too toxic side effects, will simply not be soluble enough in water, or fail to be taken up by the gut, or are quickly eliminated by the liver. Finding a drug that is effective and safe is much more complicated than finding a chemical structure that interacts with some protein. So, before you jump in the air with joy because malaria is finally eliminated, please wait another ten years.

Fast computational generation of hits is a nice idea, and great if it works, but this discovery step would normally be the fastest in the process anyway, and the cheapest. (Which does not mean that it is cheap, it is just less ghastly expensive than the rest.) So, although very interesting, this is not the quantum leap forward that we need to produce much cheaper drugs. It might actually be more useful if we were able to do good in silico toxicology and metabolism studies, but this requires one to construct a computer model of a human being, which is a rather more complex problem.

Re:Ok, how does this apply to patents? (1)

tkdog (889567) | more than 7 years ago | (#18050432)

This is offtopic, but. H5N1 aka "bird flu" - the problem isn't finding a cure. We can and do make effective influenza vaccines all the time. The problem is that if or when a strain with a high mortality rate that is also easily spread presents itself we likely won't have time to make enough vaccine - or effective antivirals (which we can also already make) and distribute them to everyone that needs them. So millions of people get sick and some percentage die mostly because the health care system has collapsed under the weight of the pandemic. That's what the concern is.

years of computation? (4, Funny)

convolvatron (176505) | more than 7 years ago | (#18048182)

sorry, i missed that definition. what is that in library of congresses per human hair?

Re:years of computation? (0)

Anonymous Coward | more than 7 years ago | (#18048506)

42.

Wow, 25% scalability! Amazing! (2, Insightful)

Saint Stephen (19450) | more than 7 years ago | (#18048190)

(420 years / 16 weeks) / 5000 computers = 1:4 scalability!!!

Frickin amazing! No one's EVER done that before.

Re:Wow, 25% scalability! Amazing! (1)

Bob54321 (911744) | more than 7 years ago | (#18048296)

I don't know - the Mozix cluster at work achieves about the same efficiency... I.T. won't listen that there is something incredibly wrong as I employed as a statistician so obviously know nothing about computers!

Re:Wow, 25% scalability! Amazing! (1)

TodMinuit (1026042) | more than 7 years ago | (#18048516)

That 420 was based on some benchmark. Perhaps a 1GHz Pentium or something. Perhaps the average CPU on the grid was higher.

Re:Wow, 25% scalability! Amazing! (1)

jZnat (793348) | more than 7 years ago | (#18048576)

Working on generic PCs using idle CPU, that's probably pretty good, right? These aren't dedicated grid computers as far as I can tell.

Re:Wow, 25% scalability! Amazing! (1)

DeQuincey (221531) | more than 7 years ago | (#18048618)

You're glossing over some important points.

1) I'm pretty sure that the servers have to send the same job out to multiple clients. That is, you can't assume that it's sufficient to have only one computer return a result for one job. There's the possibility that the result is incorrect or never returned.

2) The point of grid computing is to reduce both the cost and time required to do the computation. The entire endeavor would be more efficient if you had full control over the entire grid, i.e. a huge cluster. The entire endeavor would also be more expensive. (Last I heard, Sun is having a hard time finding customers for it's grid computing service. It might just be that $1/CPU-hour is too expensive.)

3) Distributed computing of this sort depends on unused CPU cycles. You can't expect 100% CPU utilization out of all 5,000 machines that took part in the project.

So, what you comparing this to arrive at your cynical conclusion?
Did you consider the difference in cost?

Re:Wow, 25% scalability! Amazing! (4, Informative)

nick_davison (217681) | more than 7 years ago | (#18048662)

Worse...

It's over 4 months, not a fraction of a second.

If I have a task that takes 100 seconds to run and I want it completed in under a second, scalability becomes a challenge... I have to figure out how to break it in to at least 100 distinct parts and deal with all of the communication lags associated. To have any kind of fault tolerance, I probably want to break it in to at least 1,000 tasks so that if one processor is running fast, it can get fed more and if one processor corrupts its process, I don't find out right at the end of the second, with no room to compensate, that I have to run re-run that full second's worth of processing elsewhere to make up for it. That's where the challenge comes in.

If I have a task that takes 100 seconds to run and all I'm trying to do is run it a lot of times over a period of time that's many times greater, I can run it 864 times a day per system with absolutely no scalability issues whatsoever and simply send the relatively small complete result sets back. With 100 systems, if each one can run a distinct task from start to finish, I'd be expecting pretty much dead on 100 times the total number crunching as there are absolutely no issues with task division, synchronization or network lag.

In this case, they ran 5,000 computers over 4 months. Assuming a single task is solvable in under 4 months by a single system, they should have had no difficult task division problems to solve, absolutely minimal synchronization issues and next to no lag issues to address. In short, even a pretty inefficient programmer should be able to approach 1:1 scalability in that easy of a scenario.

Efficiency of algorithms is a challenge when you want a single result fast. When you want many results and are prepared to wait so long as you're getting very many of them, that's an incredibly easy distributed computing problem.

I've got one... (3, Funny)

cultrhetor (961872) | more than 7 years ago | (#18048196)

how abouutt a drog thet maks slshdaughters spel gooder and youze gooderest grammer?

Re:I've got one... (1)

alshithead (981606) | more than 7 years ago | (#18048348)

I me know understandk youse repli. Cangst youse spik eenglishk forun us wes be dats spik eenglisk? :)

Re:I've got one... (1)

stinerman (812158) | more than 7 years ago | (#18048376)

Christ, just put the puppy down for a few seconds.

Re:I've got one... (1)

alshithead (981606) | more than 7 years ago | (#18048428)

floopleborp :)

Re:I've got one... (1)

UncleTogie (1004853) | more than 7 years ago | (#18048972)

TO quote Dolton Edwards' story, Meihem In Ce Klasrum:

"Even Mr. Yaw, wi beliv, wud be hapi in ce noleg cat his drims fainali keim tru."

Here's one (4, Funny)

realmolo (574068) | more than 7 years ago | (#18048200)

Would it be possible to use all that computing power to make an electronic voting machine that works?

Oh wait! How about a voting machine based on "quantum computing"! Then we wouldn't even have to vote, the machine would already know who won.

Goddamn liberal qubits! Bunch of flip-floppers!

Stupid conservative qubits! They think that there is ONE and ONLY ONE answer for everything!

Re:Here's one (5, Funny)

iminplaya (723125) | more than 7 years ago | (#18048344)

Then we wouldn't even have to vote, the machine would already know who won.

That's a no-go. Reading the result will change them. Kinda like what happened in Florida :-) Proof that you can do quantum processing with pencil and paper without all these electronical contraptions.

From the Article (4, Funny)

imstanny (722685) | more than 7 years ago | (#18048204)

Up to 5,000 computers were used at any one time, generating a total of 2,000GB of useful data.


Based on the size of useful data GRID collected from 5,000+ machines and the quantity of pornography on my computer, they are claiming that: porn != useful.
...GRID computing; you disappoint me.

Mathematicians and computers scientists unite! (3, Funny)

cowscows (103644) | more than 7 years ago | (#18048208)

In an amazing breakthrough which will no doubt have profound implications on Moore's Law, it has been discovered that multiple computers can accomplish in a shorter time what would take much longer on a single computer! Researchers will next launch a study to see how much faster 6000 video ipods working simultaneously can play through all the songs on the iTMS compared to a single first generation ipod shuffle.

The next Shakespear? (1)

hack slash (1064002) | more than 7 years ago | (#18048252)

Perhaps if enough PCs were put to the task they could create new Shakespearean masterpieces. 64bit Night and all that.

Re:The next Shakespear? (1)

Illogical Spock (1058270) | more than 7 years ago | (#18048544)

Oh, yeah! To bit or not to bit, that's the question!

Gerrymandering (-1, Offtopic)

Teresita (982888) | more than 7 years ago | (#18048298)

Are there any other 'big picture' problems out there you think would benefit from the grid approach?

Using distributed computing to find molecular cures or the shape a protein will fold into as it comes out of the business end of a ribosome is all well and good, but if you can find a shape on the political map that concentrates all left-wingers into little ghetto-districts and gives solid 55% majorities to right-wingers across all the other ones, and you can deliver this IT solution around the time of the 2010 reapportionment, the Bush Administration has a no-bid contract with your name on it.

Re:Gerrymandering (1)

alshithead (981606) | more than 7 years ago | (#18048406)

"Using distributed computing to find molecular cures or the shape a protein will fold into as it comes out of the business end of a ribosome is all well and good, but if you can find a shape on the political map that concentrates all left-wingers into little ghetto-districts and gives solid 55% majorities to right-wingers across all the other ones, and you can deliver this IT solution around the time of the 2010 reapportionment, the Bush Administration has a no-bid contract with your name on it."

Did you have to go to politics with this? We all know that G.W. is a moron and only a shade of intelligence compared to his father. Republicans suck, Democrats suck, and Libertarians don't suck as bad only because they can hardly get elected. The US (and most other countries) are ruled by the few that have the wealth. Corporate welfare rules. No one who can make a difference gives a shit about the environment or global warming and we are all going to hell in hand basket. The ones who do care can't make a difference unless they sell their souls in order to get elected. How the hell does politics come into your equation for this story?

Re:Gerrymandering (1)

sumdumass (711423) | more than 7 years ago | (#18048582)

lol.. gerymandering has been around since almost the beginging of politics in the US. Why would the bush administration need what it already has? Besides, they don't partition the political boundries, the states do.

And it seems to be the democrats working to groups all the liberal leftwingers into the same district. Of course this is probably an unintended reaction to keeping people dependent on social programs that hand out instead of help up. You may wonder why an imbecile Like bush won the elections instead of the democrats. After you exhaust all you resources consider this, The one side attempts to place alarge portion of the population into a dependency to keep them loyal to keeping them in power. The other side has been able to show this to get into power. You can figure who fits wich side on your own.

5,000 Computers (1)

iminplaya (723125) | more than 7 years ago | (#18048364)

Up to a full megawatt or more for sixteen weeks. How much does that cost where you live? Still, it's a great bang for the buck. So how long would it take with a beowolf cluster of these?

Lots of things still out there (4, Informative)

Raul654 (453029) | more than 7 years ago | (#18048454)

(Preface - My research group specializes in parallel computing) There are classes of problems so computationally intensive that the computers that can do them in a reasonable amount of time won't be invented for decades. Almost all of these are simulations of physical reactions (invitro drug simulation, climate simulation, biomolecular engineering sims, physics sims, 'etc). As a general rule, these problems scale weakly (meaning that as you add more computers, you can simulate more datapoints, and get more accurate results). If memory serves, the hardest problem I can recall involved hydrogen fusion simulations, requiring computers 10-1000 times faster than the best in the world today.

How about open source, distributed search (3, Interesting)

classh_2005 (855543) | more than 7 years ago | (#18048472)

This looks interesting:

http://www.majestic12.co.uk/ [majestic12.co.uk]

I think (0, Offtopic)

ryepnt (1064238) | more than 7 years ago | (#18048492)

I think that a lot of the world's problems could be solved like this; the downside of course being that some guy in an island would have to sit underground and insert 4 8 15 16 32 43 over and over. (prays someone who kept up with the lost experience read that and understood) ha

the biggest issue (1)

battery111 (620778) | more than 7 years ago | (#18048532)

You know, I think the thing that aggravates me the most is that these distributed computing systems are helping drug companies find cures to illnesses using OUR processing power and computers WE paid for, only to sell us the drug that they would have been hard pressed to develop without our hardware back to us at an extremely inflated price.

Re:the biggest issue (1)

dvice_null (981029) | more than 7 years ago | (#18048594)

If you have for example cancer and a drug company is making money for providing you the cure for it. You really don't care how they got it, as long as you are able to pay for the drug. It is better to have expensive drug rather than not having it at all. You are not forced to participate.

But there is of course a better solution also. Drug research could be funded by goverments, with tax money. This would allow cheap drugs and all the research data could be public, which would speed up the research a lot, assuming that same amount of money would be used. Or the other way around, the same amount of research could be archieved with smaller amount of money. Free is always better than closed.

Other areas to benefit (1)

dave562 (969951) | more than 7 years ago | (#18048634)

Are there any other 'big picture' problems out there you think would benefit from the grid approach?

The development of models to find relationships among individuals based upon their phone records, email communications, webpage preferences and other easily recorded and identified identifying tidbits of digital transactional receipts. Of course, I'm sure that there are various three letter agencies already well ahead of me on that one. (High guys!)

Grid Computing Projects (2, Interesting)

1mck (861167) | more than 7 years ago | (#18048676)

I've been donating my processor time for quite awhile now for the Malaria research, and even though the drug companies will probably benefit from my donation, they would not have these breakthroughs if people didn't donate that time, and it is the fact that a breakthrough will be found is what keeps me donating my processor time. It's a great feeling knowing that I've contributed to a possible cure towards this disease! Other projects that could need the services of Grid Computing, I believe that was the original question that was put forth, are imaging analysis (any field), physics (particle research, etc), and I can also see Grid Computing being used also for computer animations where the time to render animations would be greatly reduced, and allowing movies, and shows to be released much faster than before. (With this application, it would be known that you are contributing to a product that a company will be making a profit, and the only reason to do it is get these movies, shows to market faster. I, for one, would love to see a sequel to The Incredibles, and to be a part of that would be fantastic, even to just have my name mentioned in the credits!) One thing that needs to be done for these projects to get the maximum exposure for Grid Computing is to dumb down the process. A Noob would be hard pressed to set up Boinc Manager to do the Malaria research.

Grid computing vs distributed computing projects (2, Informative)

Crazy Gilmore (1065234) | more than 7 years ago | (#18048688)

Much of this discussion is totally misdirected because the writers are confusing a distributed computing project like SETI or BOINC - http://en.wikipedia.org/wiki/BOINC_client-server_t echnology [wikipedia.org] - with a grid system - http://en.wikipedia.org/wiki/Grid_computing [wikipedia.org] . They are completely different things.

Re:Grid computing vs distributed computing project (0)

Anonymous Coward | more than 7 years ago | (#18048990)

Grid computing is ill-defined, but it is about distributed processing, as is BOINC. BOINC (which now powers SETI@home) is a potential component or subset of what is now considered to be Grid. Some similar systems preexisted the current work on Grid, e.g. Condor, but then the Grid concept was first referenced at the end of the 1960s. Grid now adds concepts such as services (again not a new idea), and also workflows (again not new) and also work on data distribution.

The work that was done under WISDOM was unlike SETI@home in that it was distributing work to clusters (e.g. GridPP machines) rather than individual machines using gLite from EGEE, with local job managers then taking the work to the individual machines. SETI@home uses BOINC as the end-to-end work distribution system. Reading between the lines the Storage Request Broker (SRB) was probably used to control data access.

big deal (1)

itsmarsh (1000515) | more than 7 years ago | (#18048692)

Gus Gorman has a patant on this already called the Ultimate Computer, I believe it's in the Grand Canyon.

No it didn't (1)

arodland (127775) | more than 7 years ago | (#18048702)

It did 4 months worth of computation in 4 months. If it had been 420 years worth of computation it would have taken 420 years. It's like infomercials that say "and you get all this, a $899 value, for $30!" Obviously it's not "a $899 value" or you would be selling it for that instead of $30. Perhaps, though, they mean that they did 420 processor-years of work over the course of 4 months (meaning that they would have had an average of 1260 cores doing something useful at any time).

Re:No it didn't (1)

Raxxon (6291) | more than 7 years ago | (#18049080)

Assuming your math is accurate (and I'm too tired to look honestly) why were 5k systems used? Were the remaining 3740 used for control/coordination? If so that seems a little... sloppy in my mind. Or were these linked via a SETI-like configuration where nodes were coming on-/going off-line "at random"?

Re:No it didn't (1)

arodland (127775) | more than 7 years ago | (#18049212)

Your guess is as good as mine. My math is good as far as I can tell. It might have just been one of those things where you can only parallelize a problem so far, so nodes spent more of their time waiting for required results than doing anything. Or it could have been, as you said, an unreliable environment where the computers weren't dedicated. Or the numbers could be entirely off. I'm not horribly worried about finding out the specifics either :)

Yeah....so did they find the cure ? (0)

Anonymous Coward | more than 7 years ago | (#18048808)

or just 420 years worth of junk data ?

In Soviet Matrix, grids run on YOU (2, Funny)

iamacat (583406) | more than 7 years ago | (#18048956)

I imagined a beowulf cluster of those, nekked and petrified. Then I got ashamed of myself for rehashing the old meme and dumped hot grits in my pants. As I was convulsing on the ground, there was only one thought left in my mind:

"Does it run Linux?"

Re:In Soviet Matrix, grids run on YOU (1)

Fred_A (10934) | more than 7 years ago | (#18049724)

And how long does it take to run an infinite loop ?

420 years of data in for months (1)

MarsDude (74832) | more than 7 years ago | (#18049062)

So actually it is just 4 months of data with the new standard they set.

SETI@home (1)

Kained (190462) | more than 7 years ago | (#18049138)

This may be a bit obvious to all you /.rs ... but what the hell...

http://setiathome.berkeley.edu/ [berkeley.edu]

SETI@home is a scientific experiment that uses Internet-connected computers in the Search for Extraterrestrial Intelligence (SETI). You can participate by running a free program that downloads and analyzes radio telescope data.

Re:SETI@home (1)

edschurr (999028) | more than 7 years ago | (#18049732)

I always thought SETI@home was kind of silly. If I'm going to donate CPU time, do I really want to look for ET gazallions of light-years away, or do I want to cure cancer?

moNd down (-1, Troll)

Anonymous Coward | more than 7 years ago | (#18049252)

*BSD is dead. reaper Nor do tyhe

A question: Did it work? (1)

Catharsis (246331) | more than 7 years ago | (#18049298)

If the headline were "NEW MALARIA DRUGS FOUND WITH AID OF GRID COMPUTING" I would be much more impressed.

It's all well and good to tie a big grid to a problem, but if you don't ask the right questions, you won't get useful answers.

Are there any significant grid computing success stories?

-pvh

two big problems that need a grid (1)

master_p (608214) | more than 7 years ago | (#18050014)

Are there any other 'big picture' problems out there you think would benefit from the grid approach?

I can think of two:

this [microsoft.com]

...and this. [3drealms.com]

The female psyche (1)

MICHICAUST (732976) | more than 7 years ago | (#18050272)

Which is, according to all evidence and experience, a most... intriguing problem to a male consciousness. Now that there is the technology available, we should _FINALLY_ take advantage of it and find out about the secret inner workings of this giant enigma! Go grid computing! - Michael

Volunterism? (0)

Anonymous Coward | more than 7 years ago | (#18050284)

Why should I volunteer my time and money to subsidize some company when they will make millions(billions) of dollars a year?

  Do you volunteer for google? Microsoft? or Target for 4 month without pay?

  My tax payers money already go to NIH which subsidizes all the drug development research in the world. What do I get out of it? 40 dollars per tablet medicine?

  Fuck this. They want my work, they will pay me. They want 5000 computers, I will set up the servers, they will pay my workers and my company money. End of the story. This is no fucking communism where all the workers work for peanuts and scum bags daughters fucking fly on super sonic jets from moscow to paris so she can fucking buy perfume.

  Fuck this project, fuck it with a blunt spoon.

 
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

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

Submission Text Formatting Tips

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

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

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

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

Loading...