LHC COMPUTING GRID
Image: © CERN
More In This Article
-
Overview
The Large Hadron Collider: Countdown
-
The Best Science Writing Online 2012
Showcasing more than fifty of the most provocative, original, and significant online essays from 2011, The Best Science Writing Online 2012 will change the way...
Read More »
When the Large Hadron Collider (LHC) begins smashing protons together this fall inside its 17-mile- (27-kilometer-) circumference underground particle racetrack near Geneva, Switzerland, it will usher in a new era not only of physics but also of computing.
Before the year is out, the LHC is projected to begin pumping out a tsunami of raw data equivalent to one DVD (five gigabytes) every five seconds. Its annual output of 15 petabytes (15 million gigabytes) will soon dwarf that of any other scientific experiment in history.
The challenge is making that data accessible to a scientist anywhere in the world at the execution of a few commands on her laptop. The solution is a global computer network called the LHC Computing Grid, and with any luck, it may be giving us a glimpse of the Internet of the future.
Once the LHC reaches full capacity sometime next year, it will be churning out snapshots of particle collisions by the hundreds every second, captured in four subterranean detectors standing from one and a half to eight stories tall.* It is the grid's job to find the extremely rare events—a bit of missing energy here, a pattern of particles there—that could solve lingering mysteries such as the origin of mass or the nature of dark matter.
A generation earlier, research fellow Tim Berners-Lee of the European Organization for Nuclear Research (CERN) set out to create a global "pool of information" to meet a similar challenge. Then, as now, hundreds of collaborators across the planet were all trying to stay on top of rapidly evolving data from CERN experiments. Berners-Lee's solution became the World Wide Web.
But the fire hose of data that is the LHC requires special treatment. "If I look at the LHC and what it's doing for the future," said David Bader, executive director of high performance computing at the Georgia Institute of Technology, "the one thing that the Web hasn't been able to do is manage a phenomenal wealth of data." Bandwidth alone is a major bottleneck. Bader said that for researchers running supercomputer simulations, it's cheaper to write the data to terabyte hard drives and ship them from one supercomputer center to another via FedEx than it is to transfer the gigantic data sets over the net.
The LHC Computing Grid handles data in stages, referred to as tiers. "Tier 0," located at CERN, is a massively parallel computer network composed of 100,000 of today's fastest CPUs that stores and manages the raw data (1s and 0s) from the experiments. It ships portions of data over dedicated 10-gigabit-per-second fiber-optic lines to 11 "Tier 1" sites across North America, Asia and Europe. Brookhaven National Laboratory in Upton, N.Y., for example, receives data from the ALICE experiment, which collides lead ions.
From those sites the data is parceled out for easier access among 140 Tier 2 computer networks based at universities, government labs and even private companies around the globe. Tier 2 is where scientists will actually access data and perform the kinds of hands-on numerical analysis needed to translate the raw 1s and 0s into energies and trajectories of particles.
The crucial element that will make the data accessible, said project leader Ian Bird of CERN's information technology (IT) department in Geneva, is a type of software known as "middleware". The information a user wants may be spread among petabytes of data on different servers and stored in different formats. An open-source middleware platform called Globus is designed to gather that information seamlessly as though it's sitting in a folder on one's own desktop PC.
See what we're tweeting about
24 Comments
Add CommentThere's probably half a billion dollars in equipment in this picture... and probably more in that server room. Can we get the poor guy a flat screen monitor?
Reply | Report Abuse | Link to this". . . on her laptop."
Reply | Report Abuse | Link to thisMany people interpret this kind of language as making a political statement, and, as such, it's very distracting and out of place in a non-political context. I don't understand why the author wouldn't write 'his/hers' or 'hers/his' unless s/he is trying to be political.
Would you have said this if the author had said his?
Reply | Report Abuse | Link to thisI use his unless using formal language in school work, or speaking to particularly padantic feminists. 'His', is actually a very general term, its root word meaning something like a gender nuetral 'it belongs to'.
Her laptop? HER laptop?! HER LAPTOP!?!?!?! Girls belong in the kitchen, not reading data from a large hadron collider
Reply | Report Abuse | Link to thisI understand many women are uncomfortable when the masculine is used as neutral, and for good reason. So I don't use it that way. I also don't use 'man' or 'mankind', 'human' and 'humankind' work fine.
Reply | Report Abuse | Link to thisI think it reasonable to stop using what many consider sexist language, even if the substitute looks or sounds a little awkward.
Why not use the words that were used, until just a few social movements ago,for the gender neutral or indefinite sense: they, them and their/theirs, instead of he/she, him/her, his/hers. The use of the masculine form is a relict from an earlier movement to standardize our language when our underestanding was heavily informed by our patriarchal tendencies. Try it. Try saying a phrase where you might want to use the awkward "he/she, him/her or his/hers" but use "they, them or their/theirs"...you'll find that it works well without the use of that p.c inspired and uselessly kludged-together synthesis.
Reply | Report Abuse | Link to thisWodini, hysterical.
Reply | Report Abuse | Link to thisTomschaffter, ease up bro. I think the idea of post-feminism is that we can use either gender indicative interchangeably. To me, what most keeps this issue alive are the continued assumptions by men that it remains necessary to uphold overreactive PC rules like this. I'm willing to grant the author the benefit of the doubt when it comes either gender possessive, this is 2008. I think your reading of political undertones is about the only political thing going on here.
Oh, one more thing. Isn't this article about networks?
Brookhaven National Lab in Upton, NY accepts data for the ATLAS experiment not ALICE.
Reply | Report Abuse | Link to thisEnter Your Comment Here.
Reply | Report Abuse | Link to thisEnter Your Comment Here.
Reply | Report Abuse | Link to thishere is a tracking list of the most relavent articles...highly recomended...
Reply | Report Abuse | Link to thishttp://www.topodia.com/topic/topicviewer.aspx?guid=2985cd1e-e51a-422c-894b-fc9c1ec3fa69
so what will we find out?
i agree - as i read the word "she" i felt a jarring - distracted sensation. Forgetting what i was reading- I immediately checked the gender of the author (male) - then recalled the essay by Douglas Hofstaedter where he replaces the word "he" with the word "white", transforming hidden sexism into blatant racism. Then i completely forgot what the article was about.
Reply | Report Abuse | Link to thisAlso Doug isn't the word "relict" a self-referential "relic"? Who would use the word "relict" when we have the plain english "relic"???
I think we should re-name the LHC the "Gargantuan Hadron Conflicticator" and make sure it's staffed ONLY by sexy girl physicists with laptops.
Doug, thanks for your comments. I guess I'm so biased in sympathy with perceived sexism that it never occurred to me people would be offended by my suggested usages ('he/she', etc.). The only p.c. I saw was the 'she', for me an attempt to get back at men, rather than finding neutral language. But I understand your point and will try your suggestion ('they', etc.).
Reply | Report Abuse | Link to thisMentalelevation: "Oh, one more thing. Isn't this article about networks?"
Yes, exactly. That's why I started reading the article. But that usage is so distracting to me it interferes with my original purpose. I suspect it distracts many others.
Shlogblog, do you have a reference to Hofstadter's essay? He's one of my favorites, and I'd like to see what he has to say on the subject.
The sub-headline says, "The LHC Computing Grid may teach the Internet how to quietly handle reams of information."
Reply | Report Abuse | Link to thisI know how much a ream of paper is. How much is a ream of information?
Who really cares whether it is his or her, like mentalelevation said it is 2008.
Reply | Report Abuse | Link to thisHowever, doug I has a point, it would have been better to use something that could mean either sex.
Well, I understand that just a half-hour/1 hour/a few hours/1 day/a few days after the LHC starts up, our whole world will be sucked into one of the tiny black holes created and all of us will be -- where on earth or in the universe will be be? Does a reference more or less to "he/she" matter at all if we are all - he's and she's both and it's as well - about to be permanently extinguished?
Reply | Report Abuse | Link to this-- GSC
CORRECTION:
Reply | Report Abuse | Link to thisWell, I understand that just a half-hour/1 hour/a few hours/1 day/a few days after the LHC starts up, our whole world will be sucked into one of the tiny black holes created and all of us will be -- where on earth or in the universe will we be? Does a reference more or less to "he/she" matter at all if we are all - he's and she's both and it's as well - about to be permanently extinguished?
-- GSC
I think you will find that tachyon particles will be of interest and use. According to the special relativity theory tachyons ,if slowed to below the speed of light could be useful. They would transend into the realm of existence and assume to roll of "transmitter of data". What use? The transmission of data from point a to b. What's new ,you may ask? The difference would be the transmission of data through the earth from point a to b. For example, from Tampa, fl to Toyko japan, through the earth . A whole new science of interenal navigation(INAs) with lots of military applications since tacyon data transmissions could not be intercepted( at least not for the foreseeable future.
Reply | Report Abuse | Link to thisGoddamnit! "Before the year is out, the LHC is projected to begin pumping out a tsunami of raw data equivalent to one DVD (five gigabytes) every five seconds." WRONG! Firstly, a regular, single sided DVD holds 4.7GB of data, HOWEVER in their mad quest to sound like they're giving you more for your money, they calculate 1kb=1000b, NOT 1024b, as is the 'proper' method. Hence, a '4.7' GB disc only holds...4.4 GBs of data.
Reply | Report Abuse | Link to thisGSC, you could have just said 'I'm a moron,' and that would have been enough, because from reading your post, that's what you are.
Reply | Report Abuse | Link to thisOne of my friends (f) is responsible for all computer and software equipment of a very large US Army base. No laptops in evidence.My granddaughter is responsible for all IT activities of a large, international bank and mother of my great granddaughter.You run the risk of meeting a female pugilist on day soon! Cornelis Bergmans
Reply | Report Abuse | Link to thisI think the solution to this problem lies in giving new meaning to the internet or LHC intranet or extranets. The keyword is content based networking. I am working on it for a longtime now and addressing the same problem over the delay tolerant networks. So if anyone want to contact me please send an email on : fawad.nazir@acm.org. Regards.
Reply | Report Abuse | Link to thisI think the solution to this problem lies in giving new meaning to the internet or LHC intranet or extranets. The keyword is content based networking. I am working on it for a longtime now and addressing the same problem over the delay tolerant networks. So if anyone want to contact me please send an email on : fawad.nazir@acm.org. Regards.
Reply | Report Abuse | Link to thisI think the solution to this problem lies in giving new meaning to the internet or LHC intranet or extranets. The keyword is content based networking. I am working on it for a longtime now and addressing the same problem over the delay tolerant networks. So if anyone want to contact me please send an email on : fawad.nazir@acm.org. Regards.
Reply | Report Abuse | Link to this