×

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!

IBM Claims Breakthrough Energy-Efficient Algorithm

kdawson posted more than 4 years ago | from the sensible-consistency dept.

Earth 231

jitendraharlalka sends news of a claimed algorithmic breakthrough by IBM, though from the scant technical detail provided it's hard to tell exactly how important the development might be. IBM apparently presented its results yesterday at the Society for Industrial and Applied Mathematics conference in Seattle. The breathless press release begins: "IBM Research today unveiled a breakthrough method based on a mathematical algorithm that reduces the computational complexity, costs, and energy usage for analyzing the quality of massive amounts of data by two orders of magnitude. This new method will greatly help enterprises extract and use the data more quickly and efficiently to develop more accurate and predictive models. In a record-breaking experiment, IBM researchers used the fourth most powerful supercomputer in the world... to validate nine terabytes of data... in less than 20 minutes, without compromising accuracy. Ordinarily, using the same system, this would take more than a day. Additionally, the process used just one percent of the energy that would typically be required."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

231 comments

I'd expect this (0, Flamebait)

robinstar1574 (1472559) | more than 4 years ago | (#31284308)

Out of smart people, not greenards

Re:I'd expect this (4, Insightful)

momerath2003 (606823) | more than 4 years ago | (#31284556)

The funny thing about energy efficiency is that it saves companies money, but they get to spin it as being "green." [For example, when grocery stores eliminate plastic bags to be "green," what they really mean is they're eliminating bags to be "cheap."] If this new algorithm has no penalty associated with it, then it saves time and energy, therefore money and "the environment."

Re:I'd expect this (1)

Nerdfest (867930) | more than 4 years ago | (#31284686)

On their mainframes, IBM still charges for 'MIPS', which is processor usage ... and they charge rather a lot. This could potentially cost them a lot of money, although it's unlikely the efficiency can be applied to the sort of simple business transactions that are typically done on that sort of hardware.

Re:I'd expect this (2, Informative)

Anonymous Coward | more than 4 years ago | (#31284898)

AH you are not seeing the real potential of this.

It took them 20 mins to do. Meaning they can do 70 more customers in one day. Charge 10% more for the same job. Poof 70x1.1xcost gross profit. Oh and it cost them 99% less power wise. Margin just went up by 99%. Meaning they can also undercut competitors in the field. Or resize the computer so it still takes a day and still sell by the same price point. So it just costs them 99% less to do powerwise and customers pay the same amount.

Wont cost them a thing. In fact I would be willing to bet they make even more. Wait until the MBA's are done spinning it.

Re:I'd expect this (1)

Nerdfest (867930) | more than 4 years ago | (#31285044)

For their cloud computing stuff, absolutely, but customers typically 'own' their own mainframes.

Re:I'd expect this (1)

Amouth (879122) | more than 4 years ago | (#31285524)

which means now i need one or more less to get the same job done - OR i don't need to add one for an increased work load or i could power extras down for later days or or sell them to another group.

any time you can make existing equipment more efficient the gains are wonderful because you have already made the investment in buying and maintaining the hardware

Total cost of ownership for equipment is far more than the initial cost to purchase it - and it is a cost i'm going to pay - so if i can get more out of it for that cost - that is a benefit

Re:I'd expect this (1)

digitalunity (19107) | more than 4 years ago | (#31285484)

Not to nitpick, but plastic bags are a lot cheaper than paper bags.

Grocery stores often stop using plastic bags because they're banned on a city or township level.

Re:I'd expect this (-1, Flamebait)

PopeRatzo (965947) | more than 4 years ago | (#31284682)

smart people, not greenards

Somebody had to explain to the "smart people" that it had to be done.

And did you think up "greenards" by yourself or did you hear it from Rush?

Re:I'd expect this (1)

Crudely_Indecent (739699) | more than 4 years ago | (#31285200)

You're talking about a company that builds supercomputers to play chess. They're hardly greenards.

They are, however, moving to greener pastures in response to the demands of the marketplace.

That sounds smart to me.

Color me impressed! (1)

spammeister (586331) | more than 4 years ago | (#31284330)

And that color would be blue! Hopefully us mere mortals will be able to benefit from such algorihtms.

Re:Color me impressed! (1)

BhaKi (1316335) | more than 4 years ago | (#31284386)

Hopefully us mere mortals will be able to benefit from such algorithms.

Which twisted parallel universe are you from?

Re:Color me impressed! (1)

mcgrew (92797) | more than 4 years ago | (#31284462)

Hopefully us mere mortals will be able to benefit from such algorihtms

It's a certainty. Your cell phone is more powerful than the biggest supercomputer that existed in 1970.

Re:Color me impressed! (1)

lxs (131946) | more than 4 years ago | (#31284654)

And this is a benefit how exactly?

Re:Color me impressed! (2, Funny)

PopeRatzo (965947) | more than 4 years ago | (#31284728)

You don't realize that to post his comment, mcgrew traveled back in time from 2104 using his cell phone.

Re:Color me impressed! (1)

ad0n (1171681) | more than 4 years ago | (#31284788)

..using a technology that was invented by Shampoo.

Re:Color me impressed! (1)

mcgrew (92797) | more than 4 years ago | (#31284998)

You don't see the benefits of technology advances? If it advances as fast as the last 40 years, then 40 years from now this giant computer will be the size of your cell phone, and just as cheap.

Re:Color me impressed! (1)

Bakkster (1529253) | more than 4 years ago | (#31285446)

And this is a benefit how exactly?

If your PC or cell phone does similar tasks, its computational load is reduced by two orders of magnitude (in other words, somewhere in the range of 1%). That means your computer of cell phone spends 1% of the time doing the work, and the other 99% of the time either doing other useful work (making it faster) or in standby (making it use less energy, or last longer on battery power, or the same time on less battery).

I consider all these things benefits. Of course, it depends on if the algorithm is actually used in PCs or personal devices, or if it is only used in corporate environments. Even then, these same benefits would conceivably be passed to consumers in terms of services, reduced cost, or additional earnings.

Re:Color me impressed! (1)

Tuoqui (1091447) | more than 4 years ago | (#31284584)

ofcourse it will, dont you realize the NSA will be using this to crack encryption like 10000% faster? :P

Re:Color me impressed! (1)

PopeRatzo (965947) | more than 4 years ago | (#31284692)

Hopefully us mere mortals will be able to benefit from such algorihtms.

Not if the energy industry has anything to say about it.

Wat (4, Funny)

Anonymous Coward | more than 4 years ago | (#31284354)

reduces the computational complexity, costs, and energy usage for analyzing the quality of massive amounts of data by two orders of magnitude.

I guess they stopped using Windows Vista?

Re:Wat (1)

bsDaemon (87307) | more than 4 years ago | (#31284506)

They had to. It won't run on some lame-ass 4th most powerful supercomputer in the world. It requires at least the third most powerful.

Re:Wat (2, Funny)

biryokumaru (822262) | more than 4 years ago | (#31284594)

I heard a rumor that someone got it running on a VM under Linux on a Beowolf cluster of the 6th, 7th and 12th fastest, but the UI was really laggy.

Re:Wat (0)

Anonymous Coward | more than 4 years ago | (#31285282)

I heard a rumor that someone got it running on a VM under Linux on a Beowolf cluster of the 6th, 7th and 12th fastest, but the UI was really laggy.

yeah, but Ferris is really sick, so we're putting up with it. SAVE FERRIS BUELLER!

Cool, they've "discovered" PostgreSQL. (1, Interesting)

Anonymous Coward | more than 4 years ago | (#31284362)

After we moved from MySQL to PostgreSQL, we saw similar performance improvements. Then we doubled our performance again when we moved to FreeBSD from Linux. We never expected a few software changes to have such a big impact, but were happy that we could reuse all of our existing hardware.

just trying to be relevant (5, Insightful)

pydev (1683904) | more than 4 years ago | (#31284372)

Sounds like someone found a faster algorithm (maybe just constants), and since energy efficiency is the hot new thing, "faster" is now translated into "saves energy".

Re:just trying to be relevant (4, Interesting)

Dunbal (464142) | more than 4 years ago | (#31284494)

I find it interesting on a philosophical level to think about what computing is doing to us. CPU's require energy to perform calculations. Then there's the system overhead, a fixed energy cost that included the assembly and set up costs, and the running and maintenance/replacement costs. Now obviously humans have been almost taken out of the equation. Where before you had thousands of workers all requiring to be fed, all requiring furniture and space and light and reasonably cool/warm air, all of them needing transport, and all of them victims of entropy and therefore needing accident and health insurance, taking sick days, etc. We've come a long way.

Now you just need the brains. Brains to design the system, brains to drive the investigation, and brains to try to improve the algorithms the system uses. To save even more energy. Of course eventually physical limits will be reached. There's no escaping the fundamental laws of our universe. But the energy "savings" from doing it the "old way" is translated into the ability to essentially brute-force the universe with raw computing power. Er, but what are we going to do with all the people who just don't "have" the brains? They get a free ride?

Sorry I'm waxing philosophical today.

Zombie Computer Says: (4, Funny)

WrongSizeGlass (838941) | more than 4 years ago | (#31284578)

Now you just need the brains. Brains to design the system, brains to drive the investigation, and brains to try to improve the algorithms the system uses. ... Er, but what are we going to do with all the people who just don't "have" the brains?

Mmmm, brains ...

Re:Zombie Computer Says: (1)

Urkki (668283) | more than 4 years ago | (#31285406)

Er, but what are we going to do with all the people who just don't "have" the brains?

Mmmm, brains ...

Indeed. Whatever they "have", I bet the stuff tastes just the same and provides just the same proteins, prions and other nutrients a growing child needs!

Re:just trying to be relevant (1)

Anonymous Coward | more than 4 years ago | (#31284652)

If you're a socialist, then we have a responsibility to those people and should do our best as a society to see that their needs are met, and perhaps help them to get into educational programs where they can develop the brains to improve themselves and do the same thing for others. If you're a capitalist you think that they should get out of your way, shut the fuck up with all their whining, and concentrate on not fucking up your coffee order at Starbucks. If you're an American you've probably been brainwashed to think that the former is communist, and that the gubmint is gonna take your money, and that the latter is the one true path, because the sleazy politicos you look up to say so.

Re:just trying to be relevant (1)

thedonger (1317951) | more than 4 years ago | (#31285176)

Fail.

I want the people at Starbucks to not fuck up my order because they were hired to not fuck up coffee orders.

The problem with socialism is that as people expect more and more from their government they begin to expect less and less of themselves. If you socialist, wealth-redistributing, vomit-spewers scorn the idea of trickle-down economics in business why do you think it will magically work at the highest levels of government? In fact, it can work in business because companies are ultimately accountable to consumers. The government, however, becomes decreasingly accountable to it's citizenry until it becomes a tyranny when people are lulled into false security by the socialist agenda.

Capitalism isn't perfect, but don't scorn it because all you have left to live for is fucking up my order when I go to your Starbucks. Ass.

Re:just trying to be relevant (3, Funny)

biryokumaru (822262) | more than 4 years ago | (#31284776)

Er, but what are we going to do with all the people who just don't "have" the brains? They get a free ride?

That [welfareinfo.org] seems [stopthehou...ailout.com] to [propublica.org] be [bnet.com] the [securitygu...sguide.com] way [adelphi.edu] it's [vatican.va] been [funlol.com] working [bloomberg.com] so [thecarpetb...report.com] far [wikipedia.org].

Re:just trying to be relevant (4, Insightful)

zippthorne (748122) | more than 4 years ago | (#31285090)

In a post scarcity economy? Yeah, everyone gets a free ride. Everything changes if you can get to that.

Re:just trying to be relevant (0)

Anonymous Coward | more than 4 years ago | (#31285148)

I find it interesting on a philosophical level to think about what computing is doing to us. CPU's require energy to perform calculations. Then there's the system overhead, a fixed energy cost that included the assembly and set up costs, and the running and maintenance/replacement costs. Now obviously humans have been almost taken out of the equation. Where before you had thousands of workers all requiring to be fed, all requiring furniture and space and light and reasonably cool/warm air, all of them needing transport, and all of them victims of entropy and therefore needing accident and health insurance, taking sick days, etc. We've come a long way.

Now you just need the brains. Brains to design the system, brains to drive the investigation, and brains to try to improve the algorithms the system uses. To save even more energy. Of course eventually physical limits will be reached. There's no escaping the fundamental laws of our universe. But the energy "savings" from doing it the "old way" is translated into the ability to essentially brute-force the universe with raw computing power. Er, but what are we going to do with all the people who just don't "have" the brains? They get a free ride?

Sorry I'm waxing philosophical today.

Your ravings is to philosophy what slaps are to fire bombing Dresden

This is a pretty good energy-saving algo... (1)

FreeUser (11483) | more than 4 years ago | (#31284672)

Implemented for Linux, but analogously applicable to other systems. Running this once should reduce your PC's energy consumption to near zoro:


#!/bin/bash
#
# save-energy.sh
#
# Save enormous amounts of energy, irrespective of cost in lost computation
# must be run as root /sbin/shutdown

Of course, effeciency will be lost if you do anything else with your PC (like turn it back on), but hey, no algorithm is perfect for all use cases.

Re:This is a pretty good energy-saving algo... (1)

FreeUser (11483) | more than 4 years ago | (#31284688)

Feh, slashdot reformatted /sbin/shutdown to be part of the preceeding line, ruining the joke. Ah well, time to get more coffee and do some more day-job work.

Re:This is a pretty good energy-saving algo... (3, Funny)

biryokumaru (822262) | more than 4 years ago | (#31284804)

Running this once should reduce your PC's energy consumption to near zoro:

The only problem is, with all that jumping around and swordplay, Zorro ends up using tons of energy.

Re:just trying to be relevant (0)

Anonymous Coward | more than 4 years ago | (#31284800)

Did you actually read the article? Why was parent modded up? 1 day processing to 20 minutes processing is obviously a measure of speed. Common sense tells you that spending 20 minutes to do something takes less energy than taking up to a day doing the same thing.

Re:just trying to be relevant (3, Informative)

pydev (1683904) | more than 4 years ago | (#31285140)

Did you actually read the article?

Well, that's hard to do since there was no reference. But the guy seems to be talking about "Massively Parallel Low Cost Uncertainty Quantification". This is probably the same work as this:

http://portal.acm.org/citation.cfm?id=1645413.1645421 [acm.org]

The work has nothing to do with energy savings, it's just about a fast, approximate algorithm for a fairly common operation.

Common sense tells you that spending 20 minutes to do something takes less energy than taking up to a day doing the same thing.

My point exactly. The whole press release is analogous to saying that you save a lot of energy by compiling with "-O0" instead of "-O4".

Re:just trying to be relevant (1)

sakonofie (979872) | more than 4 years ago | (#31285430)

I kept thinking that they just took the 20 min. running time and divided that by 1 day. This is roughly 1.38 percent. Make an assumption about energy consumption being constant while the machine is running, and viola instant buzzword compliance. But then I read the article,

*the JuGene supercomputer at Forschungszentrum Julich requires about 52800 kWh for one day of operation on the full machine, the IBM demonstration required an estimated 700 kWh

Which is roughly 1.32 percent. So no big surprises.

Impressive but (3, Funny)

QX-Mat (460729) | more than 4 years ago | (#31284378)

Can it organise my porn?

Re:Impressive but (1)

DoofusOfDeath (636671) | more than 4 years ago | (#31285096)

Can it organise my porn?

Nope. In the early 20th century, Turing proved that no logically consistent porn library can contain both "donkey tennis" and "David Hasselhoff". Sorry

Re:Impressive but (0)

Anonymous Coward | more than 4 years ago | (#31285392)

This was disproved, he just needed to default to a lawful neutral donkey. duh.

Re:Impressive but (0)

Anonymous Coward | more than 4 years ago | (#31285190)

Can it organise my porn?

Sure! In fact, that shouldn't take it more than a minute... After all, you don't either...

Re:Impressive but (0)

Anonymous Coward | more than 4 years ago | (#31285250)

Can it organise my porn?

Yes, and in less time than it takes you to... uh, organize yourself.

Penis.

Green-washing (1)

AdamInParadise (257888) | more than 4 years ago | (#31284406)

I'm all for energy-efficient algorithms and datacenter but this PR is nothing but green-washing. IBM's algorithm is just faster so it uses less energy. Duh.

Automatically spreading loads across datacenters in multiple locations to take advantage of local environmental conditions so you don't have to use chillers, now that's something.

Re:Green-washing (4, Insightful)

gandhi_2 (1108023) | more than 4 years ago | (#31284542)

With faster algorithms, the machine can just get more jobs done in the same amount of time. But the jobs will just keep coming, so the energy use never changes.

Or are the new algorithms SO fast that all processing needs of humanity will be done in a week, thereby allowing us to turn off all supercomputers? Now that would save energy.

Re:Green-washing (1)

GatesDA (1260600) | more than 4 years ago | (#31284922)

Improving the performance by two orders of magnitude probably won't cut energy costs now, but it would allow massive cost and energy savings in the future.

Organizations that would normally be upgrading to a larger, more energy-hungry supercomputer would be much more likely to skip the purchase. If they do upgrade — or if they're buying their first supercomputer — they'll be able to get the performance they wanted with a tiny fraction of the hardware, which also means a tiny fraction of the cost and power consumption.

Re:Green-washing (1)

KnownIssues (1612961) | more than 4 years ago | (#31284960)

With faster algorithms, the machine can just get more jobs done in the same amount of time. But the jobs will just keep coming, so the energy use never changes.

This is true, but the energy-cost-per-job is still 1/100th the cost and if you're paying to run the job, that could be a significant savings.

Re:Green-washing (2, Funny)

arkenian (1560563) | more than 4 years ago | (#31285214)

With faster algorithms, the machine can just get more jobs done in the same amount of time. But the jobs will just keep coming, so the energy use never changes.

Or are the new algorithms SO fast that all processing needs of humanity will be done in a week, thereby allowing us to turn off all supercomputers? Now that would save energy.

Hey now! Everyone knows that 5 IBM mainframes covers the entire world market for computers.

Clarification? (4, Insightful)

Twinbee (767046) | more than 4 years ago | (#31284426)

Can someone please clarify exactly what they've achieved here? All I hear is that they can somehow sift through large quantities of data much quicker. What kind of data? What are they trying to extract? And for what end?

Re:Clarification? (4, Funny)

Xest (935314) | more than 4 years ago | (#31284474)

"What kind of data? What are they trying to extract? And for what end?"

The web. Porn. Fun.

In that order.

Re:Clarification? (1)

swillden (191260) | more than 4 years ago | (#31285084)

Can someone please clarify exactly what they've achieved here? All I hear is that they can somehow sift through large quantities of data much quicker. What kind of data? What are they trying to extract? And for what end?

I don't know about the rest of it, but I can answer the last question: To boost IBM's stock price! And as the holder of a number of IBM stock options, I must say I think that's a wonderful goal. :-)

Re:Clarification? (5, Informative)

godrik (1287354) | more than 4 years ago | (#31285234)

The conference proceedings are not online yet. So I am not sure. I could not even find the title of the talk on the conference web page

I know people who are at SIAM PP and they are all : "why are they talking about PP on slashdot ?". There was no major anouncement. I'll check the proceedings again next week, but I believe there is no major improvement. IBM is probably just trying to get some more light.

We can find the following IBM talks in yesterday page :
http://meetings.siam.org/sess/dsp_programsess.cfm?SESSIONCODE=9507 [siam.org]
The paper have the same author and name than this paper published last year :
http://portal.acm.org/citation.cfm?id=1645413.1645421 [acm.org]

So they are probable publishing an improvement on their 2009 work.

not news for nerds: there's no detail! (0, Redundant)

drinkypoo (153816) | more than 4 years ago | (#31284430)

No explanation of how these two orders of magnitude of improvement were achieved. Less space than a Nomad. Lame.

Nine terabytes of data? (0)

Anonymous Coward | more than 4 years ago | (#31284450)

So what kind of porn was that, and why is this of interest to the enterprise?

Saves Energy? (0)

WrongSizeGlass (838941) | more than 4 years ago | (#31284452)

If you're running the fourth most powerful supercomputer in the world you are not saving energy. Period.

Get this type of 'efficiency' running on mobile & portable devices and laptops first. Then you can claim some sort of energy related victory.

Re:Saves Energy? (1)

Geoffrey.landis (926948) | more than 4 years ago | (#31284520)

The word "energy efficiency" now gets appended to anything. The story really isn't about energy efficiency, that's just a buzzword.

Of course, if you do anything faster or more efficiently, if doing it uses energy, then doing it more efficiently uses less energy. Paint it green!

Re:Saves Energy? (1)

meow27 (1526173) | more than 4 years ago | (#31284644)

if you are using a super computer to process 9 TBs in a day

and the same one doing the same thing in 20 minutes...

thats pretty damn efficient. that is 20/1440 minutes
or
1/72 of the time. and 1/72 the energy consumed.

TFA is worthless (5, Insightful)

Anonymous Coward | more than 4 years ago | (#31284476)

This would be a real story if it gave implementation details, but it doesn't even tell us what the algorithm does; therefore it's totally worthless. Get this crap off the front page.

Re:TFA is worthless (1)

b4dc0d3r (1268512) | more than 4 years ago | (#31284630)

I have discovered a truly remarkable explanation which this internet is too small to contain.

Re:TFA is worthless (0)

Anonymous Coward | more than 4 years ago | (#31285320)

+1, Fermatty.

Re:TFA is worthless (0)

Anonymous Coward | more than 4 years ago | (#31284668)

Did the cold fusion researchers give any "implementation details" before they announced their breakthrough? Real innovation is communicated through press-conferences, not research papers ...

Re:TFA is worthless (2, Insightful)

belthize (990217) | more than 4 years ago | (#31284830)

Implementation details are not equivalent to merely clarifying what the heck it does. In the case of cold fusion it's pretty clear what it does: cold fusion. In the case of this press release it does "algorithmy things to your data really fast".

Re:TFA is worthless (1)

belthize (990217) | more than 4 years ago | (#31284816)

Did you RTFA, they said right there it verifies data. Picture you have 400TB of HC particle data that you want to reduce but somebody stuffs some porn, pictures of their trip to Aruba and a loads of warez right smack in the middle of it. What are you going to do ?

    Well IBM can help, they can verify that data and within mere hours remove that weird 399TB of noise and you're left with pure signal.

Re:TFA is worthless (1)

Abcd1234 (188840) | more than 4 years ago | (#31284936)

I don't mean to offend, but... are you even a programmer? There is no magic "verify data" algorithm. Supposing your scenario were to occur, you'd have to produce an algorithm that was specifically designed to either a) detect the specific form of noise you want to remove, or b) detect the signal you want to extract.

Re:TFA is worthless (1)

belthize (990217) | more than 4 years ago | (#31284970)

Was my post that confusing ... removing 399TB of noise from your 400TB HC data leaving the porn and warez .. hint hint.

Maybe I should have put /snark at the end of the post or something. I was agreeing with the OP that the article was entirely short on content.

Re:TFA is worthless (1)

Abcd1234 (188840) | more than 4 years ago | (#31285318)

Maybe I should have put /snark at the end of the post or something.

You could've, but it's early, I haven't had any coffee yet, and I'm a bit of a dumbass at the best of times, so there's no guarantee that would've made any difference at all.

Re:TFA is worthless (1)

zippthorne (748122) | more than 4 years ago | (#31285400)

Yes it was. I think we'd all assumed that you'd meant that the porn was occupying the middle 399TB of the drive...

Re:TFA is worthless (1)

KnownIssues (1612961) | more than 4 years ago | (#31284994)

Right, we can have a post that the new Apple tablet device might be called the iSlate because it "just makes sense" , but a story that appears to be true isn't interesting just because it doesn't give implementation details.

This really says nothing (2)

somersault (912633) | more than 4 years ago | (#31284508)

Without more information, this really sounds like they just had a horribly-slow-but-at-least-it-works algorithm in the first place and now done some work on making it more efficient. They don't even say what type of processing was being done on the data..

Empty statements (5, Funny)

qmaqdk (522323) | more than 4 years ago | (#31284538)

...for analyzing the quality of massive amounts of data...

I have an algorithm that does that in O(1):

return "Not the best quality, but pretty good.";

This is marketing... (1)

mr exploiter (1452969) | more than 4 years ago | (#31284608)

just in case you don't know how marketing looks like. Until there is a technical paper from IBM we could just assume that someone said "I have an idea! Lets use quicksort instead of bubble sort!".

Soulnds like Improvements to Data Mining (1)

fast turtle (1118037) | more than 4 years ago | (#31284662)

and Business Inteligence software. Things that large corps use to help make decisions (Goldman-Sachs?) and manipulate the banks/markets even faster today so Yea! This is a big deal to corps. Not so big a deal to individuals other then the damn corps can make idiot decisions even faster now.

So what's it mean to games? (1)

h00manist (800926) | more than 4 years ago | (#31284690)

Is there hope for a merge of all virtual fragmented universes into a single universe? We we can explore strange new worlds; seek out new life and new civilizations; boldly go where our avatar hasn't gone before?

Techniques from parameterized algorithms? (2, Insightful)

AlgorithMan (937244) | more than 4 years ago | (#31284738)

ZOMFG!!!! PNOIES!!!!
  • Kernelzation + Memoization
  • Branching-Vector minimization

regularly produce this magnitude of algorithm speedup...

Mixed emotions... (2, Interesting)

bwcbwc (601780) | more than 4 years ago | (#31284768)

As a computer engineer, I'm fascinated by the potential improvements in performance.

As a wired citizen, I'm terrified of the additional data-mining capabilities this will provide to our corporate overlords.

Re:Mixed emotions... (2, Insightful)

magsol (1406749) | more than 4 years ago | (#31285040)

And as an interested academic, I'm disappointed that this (so far) appears to be nothing more than a marketing ploy.

What was the algorithm? (1, Redundant)

spiffmastercow (1001386) | more than 4 years ago | (#31284862)

What was the algorithm? For all I know (having not read TFA), it could be that they replaced bubble sort with quicksort.

Re:What was the algorithm? (1)

swillden (191260) | more than 4 years ago | (#31285156)

What was the algorithm? For all I know (having not read TFA), it could be that they replaced bubble sort with quicksort.

Given that this is from the very well-respected IBM research labs, I really doubt it's anything trivial or obvious.

Given that the press release came through IBM's PR machine, I'm sure that the announcement overstates the applicability of the result.

A more informative link (3, Informative)

jbuhler (489) | more than 4 years ago | (#31284876)

Here's a link with actual content on what the algorithm does:

http://www.hpcwire.com/features/IBM-Invents-Short-Cut-to-Assessing-Data-Quality-85427987.html

Re:A more informative link (0)

Anonymous Coward | more than 4 years ago | (#31285106)

From that link:

The solution the IBM'ers came up with was to replace the inverse covariance matrix method with one using stochastic estimation and iterative refinement. This enabled the researchers to cast the problem as a linear system. "The key is that the number of linear systems that we solve is small," explains Bekas. "So if you have, say, one million data samples, then you only have to solve 100 linear systems."

Fault tolerance is a by-product of the stochastic estimation model. "If for example something goes wrong in your machine while it is solving one of the linear systems, you can safely ignore it and you can go on to the next one," says Bekas. "On the other hand, if you were to do full matrix inversion [and] something went wrong at the end of a very large matrix calculation, then your data is destroyed." The technique maintains accuracies of three, four, or even five digits, which according to him, far exceeds what is required for applications.

[...]

Now that IBM's intellectual property related to the algorithm has been patented and the technology is out of the experimental stage, the next step is to begin commercialization. There is no dearth of potential applications: weather forecasting, supply chain management, nuclear weapons simulation, astrophysics, magnetic resonance imaging, and all kinds of business intelligence -- essentially any analytics or modeling application where data quality is a driving issue. Perhaps the lowest-hanging fruit is financial portfolio analysis, where exposure to risk is at the very heart of the application. IBM has a Business Analytics and Optimization group within their consulting organization ready to start client engagements.

So... (0)

Anonymous Coward | more than 4 years ago | (#31285266)

are they marketing the price of the new algorithm? Peak oil trumps software. If they open source it...never mind.

Here's the actual paper. (5, Informative)

mattdm (1931) | more than 4 years ago | (#31285372)

"Low cost high performance uncertainty quantification", full text available in PDF.

http://portal.acm.org/citation.cfm?id=1645421&coll=GUIDE&dl=GUIDE&CFID=77531079&CFTOKEN=42017699&ret=1#Fulltext [acm.org]

And, here's the abstract:

Uncertainty quantification in risk analysis has become a key
application. In this context, computing the diagonal of in-
verse covariance matrices is of paramount importance. Stan-
dard techniques, that employ matrix factorizations, incur a
cubic cost which quickly becomes intractable with the cur-
rent explosion of data sizes. In this work we reduce this
complexity to quadratic with the synergy of two algorithms
that gracefully complement each other and lead to a radi-
cally different approach. First, we turned to stochastic esti-
mation of the diagonal. This allowed us to cast the problem
as a linear system with a relatively small number of multiple
right hand sides. Second, for this linear system we developed
a novel, mixed precision, iterative refinement scheme, which
uses iterative solvers instead of matrix factorizations. We
demonstrate that the new framework not only achieves the
much needed quadratic cost but in addition offers excellent
opportunities for scaling at massively parallel environments.
We based our implementation on BLAS 3 kernels that en-
sure very high processor performance. We achieved a peak
performance of 730 TFlops on 72 BG/P racks, with a sus-
tained performance 73% of theoretical peak. We stress that
the techniques presented in this work are quite general and
applicable to several other important applications.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

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

Submission Text Formatting Tips

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

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

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

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

Loading...