Slashdot Mirror


Overclocked Radeon Card Breaks 1 GHz

dacaldar writes "According to Yahoo Finance, noted Finnish over-clockers Sampsa Kurri and Ville Suvanto have made world history by over-clocking a graphics processor to engine clock levels above 1 GHz. The record was set on the recently-announced Radeon® X1800 XT graphics processor from ATI Technologies Inc."

199 comments

  1. Huzzah! by Anonymous Coward · · Score: 5, Funny

    What a day for world history! It will be remembered forever!

    1. Re:Huzzah! by Spy+der+Mann · · Score: 3, Funny

      A small clock cycle for Radeon, a giant step for mankind?

    2. Re:Huzzah! by Anonymous Coward · · Score: 4, Informative
      note that before you go celebrating too much, the 1ghz speed was only stable in 2D MODE: the 3dmark score is for when they had backed off the overclock to about 880, see here

      http://www.xtremesystems.org/forums/showthread.php ?p=1104977#post1104977 sampsa is asked Were you able to run any benchmarks at that speed or was that a Windows stable shot???? Anyway that is still hella fast with no artifacts. sampsa's response Just a Windows shot in 2D.

      so still impressive, but not what they describe

  2. Awesome! by Anonymous Coward · · Score: 1, Funny

    First Duke Nukem Forever post
    First Imagine a Beowulf Cluster of those post
    First Can Netcraft confirm that? post

    1. Re:Awesome! by Anonymous Coward · · Score: 2, Funny


      Hmm. Your ideas are intriguing to me and I wish to subscribe to your
      newsletter.

    2. Re:Awesome! by jzeejunk · · Score: 1

      but ... Can it run linux? :p

      --
      sarchasm
    3. Re:Awesome! by someone300 · · Score: 1

      Or, more importantly, will it run on linux?

    4. Re:Awesome! by Xua · · Score: 1

      Yes, maybe overclocked this far it will attempt to compete on linux with nvidia which have decent drivers. But who cares about extreme overclocking when drivers are shitty.

    5. Re:Awesome! by Anonymous Coward · · Score: 0

      Yeah, but does netcraft confirm a beowulf cluster of these? I for one would like to welcome our old soviet Russian Ati overclocking overlords.

      ?

      ?
      Profit!!

    6. Re:Awesome! by JustADude · · Score: 1

      You must be new here.

    7. Re:Awesome! by c_forq · · Score: 1

      Yes, but will it run OSX86?

      --
      Computers allow humans to make mistakes at the fastest speeds known, with the possible exception of tequila and handguns
    8. Re:Awesome! by Anonymous Coward · · Score: 0

      Graphics cards don't run on operating systems, they run on electricity. (And on liquid nitrogen...)

    9. Re:Awesome! by Anonymous Coward · · Score: 0

      You forgot one!

      "In Soviet Russia, Radeon's overlock YOU.."

  3. One wonders... by kko · · Score: 5, Interesting

    why this announcement would come out on Yahoo! Finance

    --
    No, seriously, I just come here for the articles.
    1. Re:One wonders... by JamesTRexx · · Score: 2, Funny

      Looking at the article I'd say to give ATI shares a boost.

      --
      home
    2. Re:One wonders... by grub · · Score: 1


      Look at the bottom of the page. It's just a press release announcing that ATI was the first to get to 1 GHz. Basically a "fuck you" to Nvidia, nothing more.

      --
      Trolling is a art,
    3. Re:One wonders... by Jarnis · · Score: 5, Insightful

      ... because ATI made a big press release about it.

      Since their product is still mostly vapor (you can't buy it yet), and nVidia is currently owning them in the high end market because ATI's product is so late, one has to grasp straws in order to try look l33t in the eyes of the potential purchasers.

      Wish they'd spend less time yapping and more time actually putting product on the shelves.

      Nice overclock in any case, but ATI putting out a press release about it is kinda silly

    4. Re:One wonders... by joemawlma · · Score: 0

      Yeah, this link would have probably been better. http://apps.ati.com/ir/PressReleaseText.asp?compid =105421&releaseID=772964 They pretty much say the same thing though.

    5. Re:One wonders... by Anonymous Coward · · Score: 0

      Wow, it's vapor? Sure must have been REALLY hard to make a cooling system for that then. Oh wait, what's this, they're selling it on newegg? http://www.newegg.com/Product/Product.asp?Item=N82 E16814102610.

      Wake up you mindless troll.

    6. Re:One wonders... by Eugene · · Score: 3, Informative

      that's 1800XL, (comparable to 7800GT). 1800XT is probably still a month away from release.

    7. Re:One wonders... by Jarnis · · Score: 1

      These guys were overclocking an X1800XT they got directly from ATI.

      X1800XL is out (tho even it is not buyable yet in most part of europe), but XT is nowhere to be seen - and it's been three weeks since the 'launch'.

  4. No big surprise by Z0mb1eman · · Score: 4, Funny

    I didn't have Slashdot in a full screen window, so the headline read:

    Overclocked Radeon Card Breaks
    1 GHz

    Was wondering why an overclocked card breaking is such a big deal :p

    --
    ClutterMe.com - easiest site creation on the Net. Just click and type.
  5. 7ghz by Anonymous Coward · · Score: 0

    They should have clocked it to 7.1 GHz with liquid nitrogen...

  6. Benchmarks? by fishybell · · Score: 5, Funny

    Without the pretty graphs how will I know what's going on?!

    --
    ><));>
    1. Re:Benchmarks? by b0r1s · · Score: 1

      Well, it probably ran really fast for a few minutes, then broke.

      Video drivers, as notoriously buggy and fragile as they are, don't handle clock speed changes very well at all. You can get a few percent without much problem, but the difficulty scale starts climbing much faster than CPU overclocking.

      Congrats, though - it's only a matter of time until it happens in production chips.

      --
      Mooniacs for iOS and Android
    2. Re:Benchmarks? by Mr.+Sketch · · Score: 5, Informative

      Graphic showing 3DMark score of 12419:
      http://www.muropaketti.com/3dmark/r520/12419.png

      Pictures of their setup/methods:
      http://www.muropaketti.com/3dmark/r520/ghz/

    3. Re:Benchmarks? by __aaxwdb6741 · · Score: 1

      One thing I'd like to know is - How does overclocking my graphics card, improve my (graphic) gaming experience?

    4. Re:Benchmarks? by netkid91 · · Score: 1

      It's all about the FPS. The more frames DirectX and OpenGL can put out in a second, the smoother the picture renders. A standard NTSC T.V. signal is 29.7 FPS, while the average GFX card these days can pull off 6000(not that I have ever had such a high framerate, must be my 600MhZ celery CPU and PCI(not express) Xtasy branded ATI Radeon 9200 card)

      --
      NO~, I read Slashdot because I think it's stupid.....
    5. Re:Benchmarks? by PhotoBoy · · Score: 1

      The 3DMark picture shows the core clocked at 882Mhz, does that mean it's not benchmark stable at 1Ghz or just that ATITool was mis-reading the core?

    6. Re:Benchmarks? by roadrunnerro · · Score: 1

      Average is 6000 maybe if only blitting in 2D... Usually you lock max to the refresh rate - e.g. 100Hz. However with a better card you can set more graphics options (in-game / aniso / anti-alias etc.) to "high" and still get a usable framerate (over 40 fps; preferably over 60 and without stuttering).

    7. Re:Benchmarks? by diablomonic · · Score: 4, Informative
      have a look at xtremesystems.com/forums, this is where they talked about it first (I was reading it there a couple of days ago). at that stage they had graphics core at 1.0 something ghz and memory at 2.0 something ghz, but it was only stable in 2d mode. the highest they could get in 3dmark at that stage was around 12400 and yes, that was with the overclock backed off a bit to 800 and something

      in other words... still impressive (no other chip has been able to overclock to 1ghz, even in 2d mode) but not quite what you were hoping for

      --
      watch "the money masters" on google video
    8. Re:Benchmarks? by netkid91 · · Score: 1

      Ehhh, 30FPS is usually enough for me, but that's because I'm not made of money to buy fancy GFX cards and PC components. But still, it's all about the FPS you can crank out of your card...now back to downloading CD 5 of OpenSuSE.

      --
      NO~, I read Slashdot because I think it's stupid.....
  7. GPU to excel CPU by hadj · · Score: 1

    The performance of GPU's seem to grow faster than those of CPU's. I remember someone had proposed to use GPU's to proces generic data. It would be 12 times faster than a CPU.

    1. Re:GPU to excel CPU by TEMM · · Score: 2, Interesting

      GPU's are great at working on linear algebra problems, which are basically what graphics are. For general purpose computing however, they would not be that much faster than a CPU

    2. Re:GPU to excel CPU by steveo777 · · Score: 3, Interesting
      I recall reading an article on /. a long time ago involving a group of coders from MIT or something like that who pitted a P4 CPU against an ATI or nVidia GPU that was running at about a third the clock speed with a tenth of the memory. They were, of course, running mostly linear equations and the CPU got it's pants kicked in by just under an order of magnitude IIRC.

      What I've been waiting for is some sort of mathematics program (I used to use Mathematica in college) that could utilize this concentrated power, rather than hampering the CPU.

      Does anyone know if any researchers have gone as far as to utilize a GPU for anything like this?

      --
      This sig isn't original enough, it's time to come up with something witty...
    3. Re:GPU to excel CPU by Saiyine · · Score: 1


      It would be 12 times faster than a CPU.

      No. The G in GPU stands for Graphics, not Generic :P. They are x times faster than CPUs doing what they are designed to do, matrix computations, so the trick would be to use matrix-related algorithms to accomplish the same work you would do with a CPU.

      More info at the BrookGPU web.

      --
      Hosting 20G hd, 1Tb bw! ssh $7.95
    4. Re:GPU to excel CPU by LLuthor · · Score: 3, Informative
      --
      LL
    5. Re:GPU to excel CPU by OzPeter · · Score: 2, Informative

      You mean like these people are doing?

      Generic GPU programming

      --
      I am Slashdot. Are you Slashdot as well?
    6. Re:GPU to excel CPU by Jerry+Coffin · · Score: 4, Informative
      The performance of GPU's seem to grow faster than those of CPU's. I remember someone had proposed to use GPU's to proces generic data. It would be 12 times faster than a CPU.

      Go here for several examples of this -- far from simply having been proposed, it's been done a fair number of times.

      The thing to keep in mind with this is that while the GPU has a lot of bandwidth and throughput, most of that is due to a high degree of parallelism. Obviously 1 GHz hasn't been a major milestone for CPUs for quite a while, but CPUs are only recently starting to do multi-core processing, while GPUs have been doing fairly seriously parallel processing for quite a while.

      Along with that, the GPU has a major advantage for some tasks in having hardware support for some relatively complex operations that require a fair amount of programming on the CPU (e.g. multiplying, inverting, etc., small vectors, typically has a single instruction to find Euclidean distance between two 3D points, etc.)

      That means the GPU can be quite a bit faster for some things, but it's a long ways from a panacea -- you can get spectacular results applying a single mathematical transformation to a large matrix, but if you have a process that's mostly serial in nature, it'll probably be substantially slower than on the CPU.

      Along with that, development for the GPU is generally somewhat difficult compared to development on the CPU. Writing the code itself isn't too bad, as there are decent IDEs (e.g ATI's RenderMonkey) but you're working in a strange (though somewhat C-like) language. Much worse is essentially a complete lack of debugging support. Along with that, you have to take the target GPU into account in the code (to some extent). I just got a call in the middle of a meeting this morning from one of my co-workers, pointing out that some of my code works perfectly on my own machine, but not at all on any his. I haven't had a chance to figure out what's wrong yet, but I'm betting it stems from the difference in graphics controllers (my machine has an nVidia board but his has Intel "Extreme" (ly slow) graphics).

      --
      The universe is a figment of its own imagination.

      --
      The universe is a figment of its own imagination.
    7. Re:GPU to excel CPU by Isca · · Score: 1

      The more interesting processor to do this with would be this:
      http://www.ageia.com/technology.html
      Graphics card do certain types of mathematical equations very well. The physics PPU specializes in more complex processing.

    8. Re:GPU to excel CPU by 2short · · Score: 1

      What exactly is "generic data"? If a GPU chip could do a CPU chips job 12 times as fast, it would be used as a CPU chip.
          GPU chips are designed to do a certain type of calculation (matrix multiplication) as quickly as possible, and, unsurprisingly, they can do it a lot faster than chips designed for a much wider array of calculations. 3D graphics is a sufficiently popular application that it has caused chips to be designed for rapid matrix multiplication, but various other applications require this caclulation as well, so for some of those, you might get a speed-per-dollar boost by getting a GPU to do the calcs for you.
          Way back in days of yore I knew an astonomy prof who wanted to do a bunch of calculations about galactic gas densities, or some such, and this required a whole ton of interpolation. He got an expansion card for his PC from some two-guys-in-a-garage hardware company that would do this many orders of magnitude faster than the CPU could hope to. They built it using chips designed for CD players.
          In either case, it's not that the chip in question was magically better. Rather, specific applications needed a specific calculation to be very fast, and were important enough that someone designed a special purpose chip to do it, and optomized the hell out of it. Then there were other apps that needed that calculation; and while they weren't themselves worth designing a special chip for, they were worth figuring out how to hack the existing tech into something usable.

    9. Re:GPU to excel CPU by Mostly+a+lurker · · Score: 5, Informative
      A good question! This excerpt from a recent article in Extreme Tech seems relevant:
      The third future project at ATI is dramatically improved support for the GPGPU scene. These are researches, mostly academic, that are tapping into the massive parallel computing power of graphics processors for general computing tasks, like fluid dynamics calculations, protein folding, or audio and signal processing. ATI's new GPU architecture should be better at GPGPU tasks than any that has come before, as it provides more registers per pipeline than either ATI's old architecture or Nvidia's new one. This is a sore spot for GPGPU developers but not really a limitation for game makers. The improved performance of dynamic branching in the new architecture should be a huge win for GPGPU applications as well. Developers working to enable general purpose non-graphics applications on GPUs have lamented the lack of more direct access to the hardware, but ATI plans to remedy that by publishing a detailed spec and even a thin "close to the metal" abstraction layer for these coders
    10. Re:GPU to excel CPU by Intocabile · · Score: 1

      Since these days GPUs are masively parrallel it is easy to throw more transistors at chip designs. They ad redundency to make yeilds higher and sell chips with some defects as low end parts.

    11. Re:GPU to excel CPU by Eivind · · Score: 1
      For general purpose computing however, they would not be that much faster than a CPU

      Umm, you're out of your mind. Or more precisely, you're trying to hard to guard your statements. "not that much faster" is rubbish.

      Obviously, for "general purpose computing" a GPU would not only not be "that much faster" than a CPU, but indeed, it would be significantly slower

      If this wheren't so, we'd offcourse be using our GPUs as CPUs (or more likely, construct CPUs the way GPUs are constructed)

  8. Speed play offs. by neologee · · Score: 5, Funny

    I always knew ati would finnish first.

    1. Re:Speed play offs. by eosp · · Score: 1

      Feed it salmiakki...that will make anything run faster. On a side note, onko totta, että suomalaisessa jouluperinteessä joulupukki oli lapsia syövä villisika?

    2. Re:Speed play offs. by ElNerdoJorge · · Score: 0

      Of course, look at Linux.

    3. Re:Speed play offs. by Anonymous Coward · · Score: 0

      Was there ever a doubt?

      not in any canadians minds

  9. A bit presumptious? by syphax · · Score: 4, Insightful

    have made world history

    I think that's going a bit far. Good for them and everything, but world history? V-E day, Einstein's 1905, Rosa Parks refusing to give up her seat on the bus- these events impact world history (sorry for the all-Western examples); making a chip oscillate faster than an arbitrary threshold does not.

    --
    Simple Unexpected Concrete Credible Emotional Stories
    1. Re:A bit presumptious? by bcattwoo · · Score: 5, Funny

      What are you talking about? I'm sure I will have next October 26 off to celebrate Overclocked Radeon Broke 1GHz Barrier Day. Heck, this may even become Overclocked GPU Awareness Week.

    2. Re:A bit presumptious? by Pulzar · · Score: 1

      What are you talking about? I'm sure I will have next October 26 off to celebrate Overclocked Radeon Broke 1GHz Barrier Day. Heck, this may even become Overclocked GPU Awareness Week.

      I'll be the first one to ask my company to give everybody a day off to celebrate such a day. I'll celebrate anything, really, as long as I get my day off.

      --
      Never underestimate the bandwidth of a 747 filled with CD-ROMs.
    3. Re:A bit presumptious? by Anonymous Coward · · Score: 0

      I for one say HELL YEAH!!
      Someone give me a pen so I can write the Whitehouse
      to make this a federal holiday.

    4. Re:A bit presumptious? by Dirtside · · Score: 1

      Yeah, but the real bitching will come when they move the holiday to the fourth Monday of October so that people can get a three-day weekend. How dare they! Have they no sense of history?!

      --
      "Destroy science and religion. Science would re-emerge exactly the same; but not religion." - Penn Jillette, paraphrased
    5. Re:A bit presumptious? by Anonymous Coward · · Score: 0

      My guess is they had an error in translation. They probably meant to say world record not world history.

    6. Re:A bit presumptious? by Spy+Handler · · Score: 0, Flamebait
      Rosa Parks on a bus is hardly world history, I'm sorry.

      Funny how you would mention this and omit something like Pearl Harbor. lol

    7. Re:A bit presumptious? by syphax · · Score: 1


      Cuz I already had one WWII event.

      My post was not intended to be a comprehensive list of great events in World History. I also omitted, e.g., the expulsion of the Persians from Greece circa 480 BC, and so forth.

      What matters with Rosa Parks was what happened afterward. A civil rights movement that fundamentally impacted US culture, and the rights of ~20M African Americans. Maybe not up there with WWII, but not inconsequential.

      And it was also a nod to acknowledge her due to her recent death.

      --
      Simple Unexpected Concrete Credible Emotional Stories
    8. Re:A bit presumptious? by Anonymous Coward · · Score: 0

      Rosa Parks is US history, you retard. No one in the rest of the world gives a fuck about how backwards the US is.

  10. 3D Mark? by SirDrinksAlot · · Score: 1

    I'm not going to take that seriously until I see some actual 3DMark results. I can overclock my 9800Pro to some insane speeds but once I start to push it I get all kinds of corruption.

    1. Re:3D Mark? by Ironsides · · Score: 1
      --
      Fly me to the moon Let me sing among those stars Let me see what spring is like On jupiter and mars
    2. Re:3D Mark? by Anonymous Coward · · Score: 0

      Doesn't seem very impressive considering the cpu is very overclocked also. I have heard of NVIDIA's 7800GTX doing 10k with mild overclocking, certainly not liquid nitrogen that's for sure.

    3. Re:3D Mark? by SirDrinksAlot · · Score: 1

      Hooray! Christmas came early this year!

    4. Re:3D Mark? by diablomonic · · Score: 1

      this score was NOT gained by runnning at 1ghz, it was only stable at 1ghz in 2d, they backed off to 8 hundred and something for the 3dmark. see xtremesystems.com/forums for more info (in extreme 3d section)

      --
      watch "the money masters" on google video
  11. n00b by Anonymous Coward · · Score: 2, Funny

    i clocked mine to 12 ghz with a combination of liquid magnesium and wd40.

    1. Re:n00b by captnbmoore · · Score: 0

      You missed the most imortant part the DUCT TAPE!

      --
      The Navy Motto "IF it ain't broke Fix It" "A day is wasted if you don't learn something new"
  12. Global Warming by koick · · Score: 1, Redundant

    AHA! There's the proverbial smoking gun for global warming!

    1. Re:Global Warming by Anonymous Coward · · Score: 0

      hahahaha, dude. You're languishing at score: 1 while some spoon who posted the exact same comment RIGHT BELOW YOU is +5 funny. Your life sucks.

  13. The culprit by ChrisF79 · · Score: 4, Funny

    I think we've found the source of global warming.

    --
    Finance tutorials and more! Understandfinance
    1. Re:The culprit by Anonymous Coward · · Score: 0

      [stands up]

      I broke the dam!

    2. Re:The culprit by Idontpostmuch · · Score: 1

      I broke the dam!

      We didn't listen!

    3. Re:The culprit by Anonymous Coward · · Score: 0

      [stands up]

      I broke the dam!

    4. Re:The culprit by Buzz_Litebeer · · Score: 1

      Even though this is funny, there is a trilogy called the "nights dawn" trilogy which noted that the earth could overheat just from the waste heat given off by all of the appliances and energy being pumped into the atmosphere every day.

      --
      If you don't vote, you don't matter, so don't waste your time telling me your opinion
    5. Re:The culprit by Anonymous Coward · · Score: 0

      I broke the dam!

    6. Re:The culprit by Anonymous Coward · · Score: 0

      Niven also theorized "heat is produced as a waste product of civilization" in Ringworld. Lighting, distilling water, cooling systems(!), food shipments....

    7. Re:The culprit by garo5 · · Score: 1

      No, the real reason about global warming can be found from this chart - Garo

  14. World history? by Seanasy · · Score: 2, Insightful
    ... have made world history...

    Uh, it's cool and all but not likely to be in the history books. (easy on that hyperbole, wiil ya)

    1. Re:World history? by FidelCatsro · · Score: 2, Funny

      I am getting fed up with all the hyperbole around here ,they are worse than Hitler

      (*Think about it*^)

      --
      The only things certain in war are Propaganda and Death. You can never be sure which is which though
    2. Re:World history? by ichigo+2.0 · · Score: 1

      But it's Hyperbole day!

    3. Re:World history? by SeaFox · · Score: 1

      Uh, it's cool and all but not likely to be in the history books.

      Until someone writes the Wikipedia entry for it. I can see it five years from now...

      On this date in 2005, ATI Technologies sucessfully crossed to the 1 Ghz barrier with Computer Graphics Cards, ushering in a new era in computer gaming.

    4. Re:World history? by FidelCatsro · · Score: 1

      The brave soul who gave his GPU to advance Marketing hype .. Lest we forget

      --
      The only things certain in war are Propaganda and Death. You can never be sure which is which though
  15. Someday people will ask... by Keith+Mickunas · · Score: 4, Funny

    where were you when the first video card was overclocked to 1GHz. And most people will respond "huh?".

    Seriously, "world history"? There's no historical significance here. It was inevitable, and no big deal.

  16. Historical? by Anonymous Coward · · Score: 1, Insightful

    How is this any more historical than overclocking it to 993 mhz? Its not! 1ghz is just a nice round number. It I overclock one to 1.82 ghz tomorrow, no one will care!

    1. Re:Historical? by Anonymous Coward · · Score: 1, Funny

      Yeah, but if you can hit 2.0 GHz...

    2. Re:Historical? by Experiment+626 · · Score: 1

      How is this any more historical than overclocking it to 993 mhz?

      What if Apollo 11 had travelled 99.3% of the way to the moon? What if the Manhattan Project built a bomb with only 99.3% of a critical mass of Uranium in it? What if the Continental Congress had gotten 99.3% of the votes to declare independence, but then decided just to stay a British colony?

      History is made by those who achieve something, not by those who just come really close and then fail. Centuries from now, when this event is looked back upon and judged by posterity, it is these brave souls who dared to break the 1 GHz barrier who will be rightfully lauded, not some poor failure of a man who could only get his video card to go 933 MHz.

    3. Re:Historical? by micpp · · Score: 1

      Either you're joking or you're missing the point. 1GHz is not some magical point, it's just an arbitary number that is a byproduct of our base 10 number system. 100% however is ALL of something, so that is actually relevant.

    4. Re:Historical? by mithras+the+prophet · · Score: 1
      Either you're joking
      ding, ding.
      --
      four nine eighteen twenty-7 thirty-nine forty-7 fiftyeight sixty-nine seventy-9 eighty-8 one-hundred-and-nine one-twenty
    5. Re:Historical? by Anonymous Coward · · Score: 0

      Everything is historical. Historical just means that it happened. I think you mean "historic."

    6. Re:Historical? by micpp · · Score: 1

      Well it's hard to tell sometimes. Normally jokes are funny.

  17. We'll just see by crottsma · · Score: 5, Funny

    NVidia will make a competitve model, with blackjack, and hookers.

    1. Re:We'll just see by MmmmAqua · · Score: 1

      In fact, forget the blackjack! And the competetive model!

      --
      Arr! The laws of physics be a harsh mistress!
    2. Re:We'll just see by Jerry+Coffin · · Score: 1
      NVidia will make a competitve model, with blackjack, and hookers.

      According to most of the reviews, nVidia's competitive model is the 6800GT -- which is now a generation out of date.

      --
      The universe is a figment of its own imagination.

      --
      The universe is a figment of its own imagination.
    3. Re:We'll just see by Anonymous Coward · · Score: 0

      Thanks Bender... See you at the moon casino! LOL

    4. Re:We'll just see by leoxx · · Score: 1

      Next year in Jerusalem!

    5. Re:We'll just see by forkazoo · · Score: 1

      No, no -- it's "forget the blackjack, and screw the competetive models!"

    6. Re:We'll just see by Ziviyr · · Score: 1

      Dawn and Dusk do card games now?

      --

      Someone set us up the bomb, so shine we are!
  18. Here's some pictures of it... by joemawlma · · Score: 0
  19. What's the point of these tests? by pclminion · · Score: 3, Insightful
    If you cool a chip, you can make it run faster. This is a matter of physics that doesn't need to be tested any more than it already has been. In some small way I appreciate the geek factor but I'm far more interested in geek projects that have some practical use.

    And as for being the first people in the world to do this... the chances of that are small. I'm sure there are people at Radeon (and other companies) who have done things far more bizarre, but didn't announce it to the world.

    1. Re:What's the point of these tests? by spencerogden · · Score: 1

      Yes, but a lot of different chips have different overclocking potential. It's interesting to see which can be pushed the furthest, even if its impractical. Beside, since when are geeky pursuits practical?

    2. Re:What's the point of these tests? by pclminion · · Score: 2, Insightful
      Yes, but a lot of different chips have different overclocking potential. It's interesting to see which can be pushed the furthest, even if its impractical.

      Really, I don't think it's interesting whatsoever. It's like testing the strength of various bulletproof glass samples at a temperature of -100 C. The fact is, bulletproof glass is not used in such environments so the test gives no useful information.

      Beside, since when are geeky pursuits practical?

      I can't believe you're being serious. My geeky pursuits pay for my house.

    3. Re:What's the point of these tests? by LesPaul75 · · Score: 1
      This is a matter of physics that doesn't need to be tested any more than it already has been.
      Yeah, but it's also well known that if you force more air/gasoline/nitrous into a car engine, it will go faster. But people continue to try to break land speed records. It's human nature. People do it just for the sake of doing it.
      I'm sure there are people at Radeon (and other companies) who have done things far more bizarre, but didn't announce it to the world.
      The company is ATI, and no, they don't do anything like this. They don't care what happens to their chips at -80C or +180C. All they do is test them a little bit beyond the limits of their recommended operating range. If you operate a chip way outside that range, they aren't going to guarantee that it will work.
    4. Re:What's the point of these tests? by slackmaster2000 · · Score: 1

      Agreed. Yes it's pretty neat, but I'm not sure if it tells us anything useful.

      They had the GPU cooled to -80C. Heat is a *huge* limiting factor in what a processor is capable of. So taking heat out of the equation and then being amazed that a GPU reached 1Ghz is a tad silly.

      What would be cool is to see some gaming benchmarks on the GPU running that fast as a sort of look into the future. Although it's not really looking into the future since there is a lot more to a next generation GPU than just clock speeds. Actually, you can just imagine it with about the same results... so maybe it's not so cool, scratch that :)

      Anyhow, I'm sure they had a lot of fun doing it, so good for them!

    5. Re:What's the point of these tests? by Anonymous Coward · · Score: 0

      Dude, you're not going to get a 386 to run at 5GHz even if you cool it to absolute zero. There's a limit to how far you can go with that "if you cool a chip, you can make it run faster" line.

    6. Re:What's the point of these tests? by pclminion · · Score: 1
      The company is ATI

      Yeah I goofed, sorry.

      They don't care what happens to their chips at -80C or +180C. All they do is test them a little bit beyond the limits of their recommended operating range.

      I highly doubt it. I have some pretty intimate knowledge of what sorts of things go on at a certain giant chipmaker, and believe me, all kinds of crazy shit has been done that you don't know about simply because they don't tell you. I imagine ATI is similar. I don't know if they've done anything exactly like this, but the experiments certainly reach into this realm of the bizarre.

      The difference is, they have specific reasons for conducting those tests other than "Whooo, look what I did!"

    7. Re:What's the point of these tests? by wolrahnaes · · Score: 1

      Maybe not a early-90s era production 386, but given the relative simplicity of the 386 in comparison to a modern chip like a Pentium 4 (which is already nearling 4GHz from the factory, though it still gets beaten by far lower clocked Athlon 64s...), I believe producing a 80386 compatible chip that runs at over 5GHz on air cooling should be pretty easy.

      --
      I used to get high on life, but I developed a tolerance. Now I need something stronger.
    8. Re:What's the point of these tests? by aka1nas · · Score: 1

      To get a 386 to run at that speed, you would have to re-engineer the chip so much that it wouldn't resemble a 386 anymore. There are issues such as clock skew and other timing issues that would prevent the chip from running at that speed even if fabbed on a newer, more efficient manufacturing process.

    9. Re:What's the point of these tests? by wolrahnaes · · Score: 1

      Well I did say it probably wouldn't have much in common design-wise with a classic 386. I'm just saying that if overclockers can regularly break 6GHz with a modern P4, then by applying the same design and fab technology to a simpler spec like a 386 one could easily make a new generation of 386 that runs at extreme clock speeds.

      I am in no way a chip engineer (in fact I recently dropped out of a computer engineering program to switch to business), so it's just speculation on my part, but the logic seems to work. I would be interested to see if a 7 GHz or so 386 could keep up with a 2.6 GHz Athlon 64 in modern applications, of course comparing them in optimised form for each proc. I'm just curious to see how much all the new processor features have improved performance, or if we should have just kept trying to overclock the living shit out of our older CPUs....

      --
      I used to get high on life, but I developed a tolerance. Now I need something stronger.
    10. Re:What's the point of these tests? by Anonymous Coward · · Score: 0

      Part of the reason an i386 was simple is that it had a less severe shortage of front-side bus bandwidth to work around. Even after you modify it to work on a modern motherboard, any code that can't run entirely in its tiny cache is going to waste almost all of those five billion clock cycles in wait states.

    11. Re:What's the point of these tests? by Nadir · · Score: 1

      Well, Linux started off as a geeky pursuit. I'd say it's pretty practical :)

      --
      --
      The world is divided in two categories:
      those with a loaded gun and those who dig. You dig.
    12. Re:What's the point of these tests? by aka1nas · · Score: 1

      You can scale a current P4 to 6 or 7 Ghz potentially if cooling is not an issue. If you tried to do 50 Ghz with "Super-Duper Extreme Cooling" or even with a straight die-shrink on some future smaller process, it wouldn't work. A straight die shrink of a 386 might do 100 or 200Mhz, but I doubt much more. I am pretty sure they do actually do use 386s fabbed on more modern processes in the embedded market as microcontrollers, so it would be interesting to see what speeds those run at. I doubt it's much(2 or 3x) more than the original ones did.

  20. Not for the weak by Mr.+Sketch · · Score: 5, Insightful

    The team, optimistic that higher speeds could ultimately be achieved with the Radeon X1800 XT, attained the record speeds using a custom-built liquid nitrogen cooling system that cooled the graphics processor to minus-80 degrees Celsius.

    It seems we may have a ways to go before it can be done with standard air cooling. I actually didn't think that operating temperatures for these processors went down to -80C.

    1. Re:Not for the weak by Anonymous Coward · · Score: 0

      Maybe we should take one into space. It's pretty cold out there, I bet they could squeeze 2GHz out of it easily.

    2. Re:Not for the weak by Anonymous Coward · · Score: 0

      You'd get wrong answers due to cosmic rays. Even NASA's golden tinfoil hats aren't perfect; they also use slow chips with huge feature sizes (larger transistors take more energy to malfunction).

    3. Re:Not for the weak by moonbender · · Score: 1

      It's pretty cold, but it's also fairly well isolated, with space being, well, a vacuum. The only way for heat to escape is via thermal radiation, ie. slowly.

      --
      Switch back to Slashdot's D1 system.
  21. comon now by Silicon+Mike · · Score: 5, Funny

    If I could only go back in time and add liquid nitrogen to my 8088 processor. I know I could have gotten it up to 5.33 mhz, no problem. NetHack benchmarks would have been off the chart.

    1. Re:comon now by Carnil · · Score: 1

      Shhh, don't say that too loud, I'm sure there are enough geeks with old machines to spare...

  22. GPU vs. CPU Speed by Anonymous Coward · · Score: 1, Interesting

    I've always wondered...Why have GPU speeds always been so much slower than CPU speeds?

    Are they made on a different process? Are they made with different materials? Are there signifigantly more transistors on a GPU?

    Why don't we have a 3Ghz GPU?

    1. Re:GPU vs. CPU Speed by freidog · · Score: 3, Informative

      Since DirectX 8 (I think), the color values have been floating point numbers, this is to avoid loosing a lot of possible values through all blending with multi-texturing and effects (fog, lighting ect) which are of course much slower than very simple integer calculations. Even on the Athlon64's FP add and muls are 4 cycles, you'd have to make the top end A64 about 700mhz if you make them single cycle execution. (multi-cycle instructions aren't as bad a thing on the CPU as there are plenty of other things to do while you wait, not so in GPUs).

      GPUs have also tended to focus on parallel execution - at least over the last few years - increasing the number of pixels done at the same time, to compensate for not being able to hit multi-ghz speeds, so yes they have many more transistors than typical CPUs (the 7800GTX might break 300 million, well over 250 million) - and of course heat is an issue if you push the voltage and / or clock speeds to far. The last few generations of GPUs have been up around 65-80W real world draw, more than most CPUs out there. And of course GPUs have very little room for cooling in those expansion slots.

    2. Re:GPU vs. CPU Speed by xouumalperxe · · Score: 5, Insightful

      Well, while the CPU people are finally doing dual core processors (essentially, two instruction pipelines in one die, plus cache et al), the GPU people have something like 24 pipelines in a single graphics chip. Why is it that the CPU people have such lame parallelism?

      To answer both questions. Graphics are trivial to parallelize. You know to start with that you'll be doing essentially the same code for all pixels, and each pixel is essentially independent from its neighbours. So doing one or twenty at the same time is mostly the same, and since all you need is to make sure the whole screen is rendered, each pipeline just needs to grab the next unhandled pixel. No syncronization difficulties, no nothing. Since pixel pipelines don't stop each other doing syncing, you effectively have a 24 GHz processor in this beast.
      On the other hand, you have an Athlon 64 X2 4800+ (damn, that's a needlessly big, numbery name). It has two cores, each running at 2.4 GHz (2.4 * 2 = 4.8, hence the name, I believe). However, for safe use of two processors for general computing purposes, lots of timing trouble has to be handled. Even if you do have those two processors, a lot of time has to be spent making sure they're coherent, and the effective performance is well below twice that of a single processor at twice the clock speed.

      So, if raising the speed is easier than adding another core, and gives enough performance benefits to justify it, without the added programming complexity and errors (there was at least one privilege elevation exploit in linux that involved race conditions in kernel calls, IIRC), why go multiple processor earlier than needed? Of course, for some easily parallelized problems, people have been using multiprocessing for quite a while, and actually doing two things at the same time is also a possibility, but not quite as directly useful as in the graphics card scenario.

    3. Re:GPU vs. CPU Speed by pclminion · · Score: 1
      the color values have been floating point numbers [...] which are of course much slower than very simple integer calculations.

      You say this as if it is both true and obvious. In fact, it is false. For several years now, floating point arithmetic has been just fast (and in many cases, faster) than integer arithmetic. I have actually sped up code which was previously cleverly written to use integers, just by switching to doubles.

      What is still very slow is converting from integers to floats, and vice versa. Avoid casts, and feel free to use floating point wherever you wish you had it. Your code won't suffer in the slightest.

    4. Re:GPU vs. CPU Speed by be-fan · · Score: 1

      The Athlon64's adds and muls are pipelined, so its still 1 per cycle. If you look at the pipeline of a GPU (dozens of stages), you'll probably find that add and mul takes even longer.

      --
      A deep unwavering belief is a sure sign you're missing something...
    5. Re:GPU vs. CPU Speed by Anonymous Coward · · Score: 0

      Most CPUs take years to make and have highly customized, tweaked logic and cache units. GPUs have a much shorter cycle (~6 months) and so thus must use more "off-the-shelf" design. Hence the higher transistor count and lower clockspeed. Not to say that's entirely the reason - as others have mentioned, graphics code is far easier to parallelize than multi-purpose code.

  23. And you thought slashdot was bad by Edunikki · · Score: 1

    After the LCD screen "news" earlier, I am glad to see that the unashamed marketting is submitted to Yahoo on this one ;).

  24. It was 2D mode only by anttik · · Score: 5, Interesting

    Sampsa Kurri told in a Finnish forum that it was over 1 GHz only in 2D mode. They are trying to run it with same clocks later. ATI left some tiny details away from their press release... ;P

    1. Re:It was 2D mode only by jandrese · · Score: 4, Funny

      It also apparently crashed a lot. This is kind of like saying "I got a Volkswagon Beetle up to 200kph[1]!!!" with a whole lot of modifications.

      [1] Going downhill

      --

      I read the internet for the articles.
    2. Re:It was 2D mode only by slackmaster2000 · · Score: 2, Interesting

      Are you sure? TFA does say "Noted Finnish over-clockers Sampsa Kurri and Ville Suvanto achieved graphics engine clocks of 1.003 GHz and a memory speed of 1.881 GHz (940.50 MHz DDR (dual data-rate) memory clocks) with maximum system stability and no visual artifacts."

      The phrase "maximum system stability" though might be misleading. If you define it as just POSTing, then man I've done some awesome overclocking myself! :)

      Interesting that these overclockers are "noted", and "Finnish." That does sort of give them a little mystique, no? Anytime I hear about a Noted [country name] [scientist|engineer] I always think of an older guy in a white lab coat in some top secret super science facility working on amazing advances in science, like overclocking consumer video cards.

    3. Re:It was 2D mode only by pkw111 · · Score: 0

      Ummmm ya. The article itself has this information. On that same linked page with the pictures. It says near the bottom:
      "Now we have succesfully ran graphics card beyond the 1 GHz barrier in 2D-mode and next we are looking to do the same in 3D-mode."

      So there it is.

    4. Re:It was 2D mode only by Anonymous Coward · · Score: 0

      The trick isn't getting a VW up to 200kph. It's how do you stop the bloody thing once you get it there!

  25. Wow, watch the paint dry too. by NerdBuster · · Score: 0

    That's about how exciting this post is. What a dull day for news.

    1. Re:Wow, watch the paint dry too. by wcrowe · · Score: 1

      Snooze for nerds...

      --
      Proverbs 21:19
  26. Cheating by AC-x · · Score: 1

    Liquid Nitrogen cooling is a bit of a cheat, didn't Toms Hardware get over 5ghz out of a 3ghz P4 a few years ago by constantly pouring liquid N over it?

    I'm gonna wait until you can get 1ghz with a practical cooling solution before getting too excited (tho the way CPUs are heading these days cryogenic cooling may come as stock in a few years!)

    1. Re:Cheating by ciroknight · · Score: 1

      LN2 isn't really a cheat; it's pretty accessible through common channels, and even commercial nitrogen cooling is available. Also, if you do a quick Google, you can find screenshots of a 7GHz nitrogen cooled P4. Kinda validates the platform, even if they couldn't ship it due to power constraints.

      GPUs on the otherhand aren't anywhere near overclockable so this is quite the hack.

      --
      "Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
    2. Re:Cheating by superpulpsicle · · Score: 1

      You are going to have to wait a long ass time. As practical cooling is just a $5 fan from ATI. Yes I am the victim of countless fried stockspeed ATI cards, I speak from experience.

  27. Quake IV by Anonymous Coward · · Score: 1, Funny

    And it still can't play Quake IV

    1. Re:Quake IV by YodaToad · · Score: 1

      Actually, if you want to make a jab at not being able to run something you'd have better luck with F.E.A.R. Quake IV actually runs nicely on systems that couldn't even begin to run F.E.A.R.

  28. This record already broken by Ezku · · Score: 3, Informative

    Sampsa and Ville already broke their own record by overclocking the same setup to over 1GHz for both the GPU and memory. See pictures over at Muropaketti.

  29. Hot Hot Hot! by tradjik · · Score: 2, Funny

    Now, just pair that up with Intel's new dual-core Xeons and watch your power meter spin! At least you won't have to worry about the increase in gas prices this winter, you can just run your PC to heat your home.

    1. Re:Hot Hot Hot! by idonthack · · Score: 1

      Xenons? Pfft.
      ---
      (\(\
      (-.-) Give me back my damn feet!
      Generated by SlashdotRndSig via GreaseMonkey

      --
      Why is it that when you believe something it's an opinion, but when I believe something it's a manifesto?
    2. Re:Hot Hot Hot! by MrNemesis · · Score: 1

      Easy way around that - hook up a generator to your spinny-spinny leccy meter ;)

      --
      Moderation Total: -1 Troll, +3 Goat
  30. FPS by koick · · Score: 5, Funny

    Cuz you know it's like way better to play Quake IV at 953 Frames Per Second. Totally!

    1. Re:FPS by dogmatixpsych · · Score: 1

      Yep, now we can play the crappy eye-candy games at twice the speed and end the pain twice as soon for only 4 times the cost.

      New record! Doom 3 in 5 minutes.

    2. Re:FPS by BlogPope · · Score: 1
      New record! Doom 3 in 5 minutes.

      Ever play old DOS games that have no or limited sense of timing for the underlying hardware? Hmm, passes the 486 test so I'll run with dealy Y, then laugh as one touch of the control rockets your tank to the other side of the screen while the old 10 second tank round reloads look like automatic fire?

      --
      My other car is a Popemobile
    3. Re:FPS by KylePflug · · Score: 1

      Hehe. I was playing an emulated Escape Velocity and I had that problem. It was impossible to tell what was going on.

      If only we could make Doom III go by that fast...

    4. Re:FPS by Anonymous Coward · · Score: 1, Funny

      Are you kidding? Quake IV? Have you actually tried playing multiplayer out on the net. Try a CTF game with 16 people. If you're lucky this *might* actually get you 30-40 FPS. :)

    5. Re:FPS by DocSavage64109 · · Score: 1

      I remember having the same problem playing Elite on a 25mhz 486sx Packard Bell! Luckily the computer had a key-combination you could use to slow it to 4.77mhz.

  31. That's sad... by Xshare · · Score: 5, Funny

    That's just sad... that video card now has more clockspeed and more memory than my own main computer.

    1. Re:That's sad... by mcrbids · · Score: 1

      That's just sad... that video card now has more clockspeed and more memory than my own main computer.

      Curious thought - the human brain has about 50% of its mass devoted to processing sight and patterns in images... Sounds about right, doesn't it?

      --
      I have no problem with your religion until you decide it's reason to deprive others of the truth.
    2. Re:That's sad... by Anonymous Coward · · Score: 0

      No worries. It will probably cost as much as a boat or a house.

    3. Re:That's sad... by quark101 · · Score: 1

      You make a jest out of it...

      It's true for me...

    4. Re:That's sad... by CharonIDRONES · · Score: 1

      And probably costs more too . . .

      -Brandon

    5. Re:That's sad... by kesuki · · Score: 1

      the human brain also runs on a dual hemisphere model, and has the capability in the event of 'damage' to a critical controller section of the brain remap other portions of the brain to control those functions (sometimes, depending on the type and extent of damage to the brains circuitry)

      the brain also relies on quantum effects for certain computational effects, has a 1.5 GB hardware ROM (DNA) that includes the full specification of every tissue and every protein in the body... and can store and recall an incredible amount of visual, auditory and other data... the actual amount of data, and the compression techniques used are currently unknown, but the human brain has roughly a thruput of 40TB/s operates on 90-100 watts of electricity, and weighs in at around 3 lbs of course it's carrying case adds another 7 lbs, and the power supply brick/locomtion device weighs anywhere from 60 to 600 lbs more... but in terms of simple operations a CPU can already process 2000 times as many simple operations as a human brain can, but the draw back is that the pentium cannot dynamically reconfigure it's hardware interconnect layers for different types of processing, and is not designed or optomized for the type of complex operations the human brain is, not to mention it's data thruput rate is still about 1,000 slower than that of the human brain. so the straight skinny is the human brain can move data around many fold faster, and perform many more complex operations on the data than a modern processor. for computer to 'catch up' to the human brain they need about 10,000 times as much memory and the ability to read and access that memory with 1,000 times more bandwith. in other words, a cleverly designed and programmed cluster of 1,000 computers could concievebly attempt to run a human brain simulation program.

  32. Needs comparatively less cooling... by Anonymous Coward · · Score: 0

    ...than a Pentium IV.

    But I do love having a PIV now that winter is here.

  33. Jeez... by Anonymous Coward · · Score: 0

    ...is there anything one can't do with that stuff?



    (Judging from Big boys, I doubt it.)

    1. Re:Jeez... by idonthack · · Score: 1

      Put out processor fires :)
      ---
      (\(\
      (-.-) Give me back my damn feet!
      Generated by SlashdotRndSig via GreaseMonkey

      --
      Why is it that when you believe something it's an opinion, but when I believe something it's a manifesto?
  34. Because it's worth zilch without... by GrAfFiT · · Score: 4, Informative

    ...the pictures of the rig : here they are, 3DMark05 included.

  35. rosa parks by drewxhawaii · · Score: 0, Offtopic

    not really sure why she gets all the credit for that. she wasn't the first, and far from the only...

    1. Re:rosa parks by Anonymous Coward · · Score: 0

      not really sure why she gets all the credit for that. she wasn't the first, and far from the only...

      She gets the credit because she agreed to serve as the test case for a long and possibly dangerous series of judicial procedures. The ACLU wanted to find someone who was strong enough to bear up under whatever could be thrown at her, and had zero skeletons in her closet (e.g., earlier minor brushes with the law, a history of activism, connections to the Communist Party, etc.). Unlike the other possible plaintiffs, she was older (42, not a teenager or in her 20s), which gave her a certain motherly gravitas.

  36. O RLY? by irc.goatse.cx+troll · · Score: 3, Informative

    http://www.bfgtech.com/7800GTX_256_WC.html

    BFG GeForce(TM) 7800 GTX OC(TM) with Water Block. Factory overclocked to 490MHz / 1300MHz (vs. 400MHz / 1000MHz standard), this built-to-order card will feature a water block instead of a GPU fan for those wanting to purchase or who may already have an existing liquid-cooled PC system. BFG will hand-build your card using Arctic Silver 5 Premium Thermal Compound. Easily hooked up to any existing 1/4" tubing system or to 3/8" tubes with the included adapters, this card runs cool and silent. BFG Tech is proud to offer their true lifetime warranty on this graphics card. (Card with water block requires internal or external water cooled system, sold separately.)

    --
    Pain lasts, kid. Its how you know you're alive. Sometimes I think this growing up thing is just pain management-TheMaxx
    1. Re:O RLY? by be-fan · · Score: 1

      So? That's running at 490 mHz core 1300 mhz memory. This Radeon is running at 1000Mhz core and 2000Mhz memory.

      --
      A deep unwavering belief is a sure sign you're missing something...
    2. Re:O RLY? by GarfBond · · Score: 2, Insightful

      Good job not even reading the summary. The card you referenced is under half the speed of this ridiculously overclocked ATI card, which happens to be 1GHZ core/1.8GHZ memory.

  37. Hookers? I'll buy it! by Anonymous Coward · · Score: 0

    nt

  38. you know when you need a new pc by Anonymous Coward · · Score: 0


    when new video cards are faster than your CPU

  39. benchmarks not the right ones by Anonymous Coward · · Score: 0

    The 3dmark you link to is not at 1ghz, so those cant be the right benchmarks

  40. Why so cold? by elgatozorbas · · Score: 1

    Good point! Why must they be so cold? I always thought that the problem was removing heat (i.e. not letting it get hot) rather than making it ridiculously cold. Anyone?

    1. Re:Why so cold? by gardyloo · · Score: 1

      If you can come up with a clever way of removing heat from a chip quickly without making its surroundings much cooler, I'm sure we'd all be happy to hear it.

    2. Re:Why so cold? by Anonymous Coward · · Score: 0
      I always thought that the problem was removing heat (i.e. not letting it get hot) rather than making it ridiculously cold.

      Well for one thing, being submerged in liquid nitrogen is a pretty damn good way to remove heat :-P

      Transistors are not instantaneous devices -- it takes time for them to switch between "on" and "off". This time decreases as the transistor gets colder. But that's not the main reason to cool the chip.

      The other reason is that shorter clock pulses have less energy in them than longer ones. The wires within the chip have resistance which continually saps this energy even further. On chips there is a concept called "fan-out" which basically means how many different places the same signal is being sent. This divides the energy still further. If the clock pulses get too fast, the fan out and resistance combine to chop the pulses up so small that they are no longer able to reliably trigger the transistors, and the chip just stops working.

      Keeping the chip extremely cold reduces the wire resistance and lets you get away with shorter clock pulses.

    3. Re:Why so cold? by c_woolley · · Score: 0

      Would a vucuum and a water hose do the trick?

    4. Re:Why so cold? by elgatozorbas · · Score: 1
      If you can come up with a clever way of removing heat from a chip quickly without making its surroundings much cooler, I'm sure we'd all be happy to hear it.

      Actually I doubt that you understand my point, but to answer your question: anything accepting heat at a temperature which is well beyond the temperature of the uncooled system is ok. This need not be a cryogenic temperature.

      If you would stick the processor in ice water it would remain at more or less zero degrees C, the only problem being that evaporating water may form a heat isolating layer and that the water would short-circuit the tracks. Ice water has an infinite capacity for accepting heat from stuff above zero degrees (as long as there is ice). While these cryo systems may be cool (obviously) they are not essential for 'normal' cooling, hence my question if they offer a real advantage.

    5. Re:Why so cold? by gardyloo · · Score: 1

      Yes, I'm quite aware of thermodynamic arguments. As you say, though, a major difficulty is conducting heat away from the hot portions. You could have a huge amount of room-temperature water flowing by the chip, and cool it quite effectively. However, this requires, well, a huge flow rate, which necessitates noisy pumps, etc. Besides which, you get to deal with heat flux rates, which (to a good approximation) are simply proportional to the temperature differences between the hot portions and the cold portions. Why not increase the heat flux by cooling the coolant? Then you don't need such ridiculous flow rates. And the nicest coolant around right now is the liquid nitrogen.

    6. Re:Why so cold? by elgatozorbas · · Score: 1
      Why not increase the heat flux by cooling the coolant? Then you don't need such ridiculous flow rates. And the nicest coolant around right now is the liquid nitrogen.

      Firstly, it is rather easy to make a permanent 'ice water reservoir' (or similar) while it is nontrivial to produce liquid nitrogen. Admittedly for a short test this is no real issue (bear in mind I never said it was BAD, just asked if it had any advantages to use liquid N).

      Secondly this large temperature difference between the coolant and ambient (not all of the PCB or even CPU comes in contact with the N) can cause thermal problems of differential expansion leading to bad contacts etc.

      And there may be other reasons.

    7. Re:Why so cold? by Anonymous Coward · · Score: 0

      The colder the better, at 0C it will not even get over 750Mhz!!

      What is important here is to lower the circuit electrical resistance, lowering the temperature to -80 lower the resistance allowing higher clock rate (electron can get to there destination faster because they get less collisions with the atoms that now vibrate a lot less)

    8. Re:Why so cold? by Anonymous Coward · · Score: 0

      Temperature is analogous to voltage. The die will heat up until the temperature difference is enough to draw as much energy out as the power supply is bringing in. A small fast die could remain far above 0 C forever, no matter how much ice water you pump through or how big the heat sink is. The only way to make the die cooler is to make it bigger (not just adding a sink, but actually spreading out the heat source, which hurts performance) or put it in a colder environment (so the cooling rate per unit area is higher).

    9. Re:Why so cold? by fluffy99 · · Score: 1

      Because the flow of heat through a material is proportional to the temp drop. You need to get the outside of the chip that cold to get enough heat flowing out to keep the temp inside within the operating temp. The -80 deg temp was taken on the outside of the chip. I don't think the gpu has an internal diode to measure the internal temp.

  41. Cause by carguy84 · · Score: 0

    OutKast wrote a song about her.

  42. It'll just about... by David+Horn · · Score: 5, Funny

    It'll just about be able to handle Windows Vista... :-)

    --
    PocketGamer.org - For the gamer on the go!
    1. Re:It'll just about... by Cervantes · · Score: 1

      Great. If you hadn't suggested it, we'd be fine, but now they're rewriting the min-spec on the packaging as we speak.

      Thank you very much, you bastard.

      --
      If I knew the wedgies I gave you back in 6th grade would have resulted in this . . . I might have taken a moments pause.
  43. Well by Anonymous Coward · · Score: 0

    At least these guys are ready for Vista!!

  44. More markup = more nesting by Anonymous Coward · · Score: 0

    First tired joke about first tired joke post post.

    You too are a meme!

  45. Computer rice by Anonymous Coward · · Score: 0

    Overclockers and their ilk remind me of ricers in the automotive world -- both use a lame "turn it to 11" approach instead of real ingenuity and creativity in increasing performance. And whether the engine blows up from excessive boost and nitrous, or the CPU/GPU burns up from heat, they risk equipment damage by toying with technology they don't understand. What's even worse is, they take pride in doing it.

  46. Congrats by camzmac · · Score: 1, Funny

    Dear enthuiastic customer(s),

    Congratulations, you have succeeded in clocking our cards past 1000 MHz. You are now in the ranks of Albert Einstein, Mary Curie, and Shakespeare. Many of our employees believe you are now cooler than santa claus.

    Your friend,
    ATI

  47. warming up? eke! by VolciMaster · · Score: 1
    "We're just warming up," joked Kurri.

    To -80 degrees? Ouch! How cold were you before that?

    1. Re:warming up? eke! by Anonymous Coward · · Score: 0

      They're in Finland, silly.

  48. Also the precision of GPUs is limited by renoX · · Score: 1

    When ATI or NVidia says that their GPU is 64bit, this means that the ARGB use 64bit which makes 16bit per component.
    16 bit floating point number may be a problem due to the small precision.

    1. Re:Also the precision of GPUs is limited by be-fan · · Score: 1

      Actually, the GPUs are 128-bit, with 32-bit floats.

      --
      A deep unwavering belief is a sure sign you're missing something...
    2. Re:Also the precision of GPUs is limited by renoX · · Score: 1

      Thanks for the correction, you're right.

      Still to put it into perspective Intel floating point goes up to 80bit (less if your using the vector units).

  49. Are you kidding by Anonymous Coward · · Score: 0

    "attained the record speeds using a custom-built liquid nitrogen cooling system that cooled the graphics processor to minus-80 degrees Celsius."

    Everyone can do this.....

  50. Do you think... by real_bassman · · Score: 0

    ...it can run Windows Vista now?

    1. Re:Do you think... by niteskunk · · Score: 1

      On 640x480x16, maybe...

  51. Not as Funny As You Think... by Anonymous Coward · · Score: 0

    Let's see... you're using more power to run the overclocked board. So that likely uses more fossil fuels to produce the electricity.

    You're putting out more heat into the environment, so that's warming up the environment, even if just a little.

    You do know that a respectable percentage of worldwide energy use goes to computers, the internet, etc.?

    (Sorry to spoil teh funny, but someone had to say it...)

    1. Re:Not as Funny As You Think... by Anonymous Coward · · Score: 0

      Is that really significant next to worldwide use of automobiles, airlines, cargo trucks, heating, streetlights, aluminum smelting....

  52. heh by Anonymous Coward · · Score: 0

    I misread it as: Overated ATI Card. But yeah, one reason NVIDea is owning ATI is compatibility, and fairly decent cards at low and high ends.

  53. BFD! by wcrowe · · Score: 1

    Mine goes to eleven.

    --
    Proverbs 21:19
  54. WTF? by Dwonis · · Score: 1
    Since when is clock speed a meaningful indication of special-purpose chip speed?

    On the other hand, 'almost 2 GHz memory speed' is a little more meaningful. At least they mentioned that.

  55. My... by Anonymous Coward · · Score: 0

    ...E-Penis is bigger than yours!

    You know this will boil down to a new pissing contest with those who inflate their ego with clock timings... sheesh

  56. lower resistance & superconductivity by ilautar · · Score: 1

    One logical explanation would be to lower resistance.

    The lower you get on temperature, the lower resistance of various materials becomes. You can even reach superconductivity, where [C|G]PUs will go crazy in power.

    With lower resistance, you could lower voltage and get the same functionality (since voltage drops are now smaller). This reduces heat produced, and frequency can be increased as signals are stronger.

  57. A Fraud! A Sham! A Scandal! by TheVorp · · Score: 2, Insightful

    Not sure if anyone else noticed, but the videocard in question was actually overclocked to 1003.50 MhZ, not exACTly a true GhZ, eh? This is the same kind of math that rips me off of gigs on my mp3 player and HDD. Nevertheless, I welcome the first vc to be clocked to 0.97998046875 GhZ!

  58. REDUNDANT? by Anonymous Coward · · Score: 0

    Um, if you look at the timestamp, this posting was first to mention global warming! And speaking of redundancy, it's THE WHOLE REASON we have global warming anyway: 5 million people on the planet can be pretty wasteful and not impact things, but if 7 billion people even just fart, you have a problem.

  59. No! by SandMonkey · · Score: 1

    The fools! They no not what they have done! The grad was never ment to go that fast! They could tear a hole in the very fabric of the universe! Too la...

    --
    Schrodinger's cat- A cat is put in a sealed box. Attached to which is a radioactive nucleus and a canister of poison gas