Slashdot Mirror


Intel Shows Off 80-core Processor

thejakebrain writes "Intel has built its 80-core processor as part of a research project, but don't expect it on your desktop any time soon. The company's CTO, Justin Rattner, held a demonstration of the chip for a group of reports last week. Intel will be presenting a paper on the project at the International Solid State Circuits Conference in San Francisco this week. 'The chip is capable of producing 1 trillion floating-point operations per second, known as a teraflop. That's a level of performance that required 2,500 square feet of large computers a decade ago. Intel first disclosed it had built a prototype 80-core processor during last fall's Intel Developer Forum, when CEO Paul Otellini promised to deliver the chip within five years.'" Update: 06/01 14:37 GMT by Z : This article is about four months old. We discussed this briefly last year, but search didn't show that we discussed in February.

164 of 222 comments (clear)

  1. But... by Anonymous Coward · · Score: 2, Funny

    Does it run Linux?

    1. Re:But... by Nom+du+Keyboard · · Score: 5, Funny
      Does it run Linux?

      Yeah. 80 different distributions at once.

      --
      "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
    2. Re:But... by Wolfrider · · Score: 1

      Indeed, but only with Vmware and/or OpenVZ. ;-)

      Seriously, this thing doesn't even support the x86 instruction set (yet?), and is not form-factor compatible with today's processors.

      When it finally comes out, hopefully they will have integrated the "3D" chip-stacking tech into it as well, and HOPEFULLY it will run both cooler and with less power requirements than today's offerings.

      --
      .
      == WolfriderV6 == I'm willing to admit that *I just might* be wrong... Are you??
    3. Re:But... by Fredtalk · · Score: 1

      One core for every version of vista too...

    4. Re:But... by iggymanz · · Score: 1

      and the 80 forks of the FreeBSD project by various disgruntled former developers

  2. cue by russ1337 · · Score: 5, Funny

    Cue the 'needed to run Vista' jokes....

    1. Re:cue by NickCatal · · Score: 2, Funny

      Finally I can realize my dream of playing 500 instances of Quake 3 on one machine!

      --
      -nick
    2. Re:cue by saboola · · Score: 1

      The Xbox 360 uses a triple core PowerPC based CPU, what makes you think they would go back to intel?

    3. Re:cue by homeobocks · · Score: 1, Flamebait

      Oh, I get it! You spell "Microsoft" with a "$" replacing the "s" because Microsoft likes money! Then you write some shallow technical-sounding drivel around it to legitimize your flagrant adolescent fanboyism as Slashdot's trademark pseudo-intellectual circle-jerk! Clever!

      --
      MOUNT TAPE U1439 ON B3, NO RING
    4. Re:cue by Ngarrang · · Score: 2, Funny

      Oh, I get it! You spell "Microsoft" with a "$" replacing the "s" because Microsoft likes money! Then you write some shallow technical-sounding drivel around it to legitimize your flagrant adolescent fanboyism as Slashdot's trademark pseudo-intellectual circle-jerk! Clever! Karma was meant to be burned, not whored.
      --
      Bearded Dragon
    5. Re:cue by benzapp · · Score: 1, Insightful

      Do you have any evidence of this? Are you saying that if I write an application to execute 16 threads simultaneously 16 different processors on a machine running Vista, that application will not see any speed increase over running that 16 thread application on an 8 processor machine?

      Why would this be? And what is with the mac pro nonsense? Do you really think only apple makes 8 core machines?

      --
      I don't read or respond to AC posts
    6. Re:cue by kimvette · · Score: 1

      Considering how slow Vista is compared to Win2K and XP, perhaps in this case you meant "queue?"

      --
      The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
    7. Re:cue by Anonymous Coward · · Score: 1, Funny

      1040? How'd you come up with that number?

    8. Re:cue by billcopc · · Score: 1

      Do you really think only apple makes 8 core machines?


      In the consumer segment, YES!

      Of course you could always contact me about acquiring prebuilt 8 and 16-core Opteron rigs, but I'm not the guy with the neat commercials and the flashy stores.
      --
      -Billco, Fnarg.com
    9. Re:cue by avronius · · Score: 1

      You must be new here...

    10. Re:cue by jellomizer · · Score: 1

      Well using XP I see that there is about Programs that are running on the system at any one time the rest are in a wait state. Most programs are not multi-threaded. So with 8 Cores should be more then enough to run current Vista design. There was an article yesterday saying how the next versoin of Windows will be designed to handle multi-core processors better so I figure this design hasn't changed much.

      No the Mac Pro isn't the only system with 8 cores (2 4 core cpus) it is a common system that has 8 Cores that most people know about. It is there to ilistrate that systems are already out today that support the optimal CPU usage for Vista for people with such configurations to prove me right or wrong. (Checking CPU Useage of vista running) while doing some mostly OS tasks.

      Most programams are not very multi-threaded or paralized, which is the problem with Multi-Core systems if you have 2,4,8,16,32,64... CPUs your performance may not in good relation and for most cases will be the speed of one processor.

      --
      If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    11. Re:cue by ConceptJunkie · · Score: 1

      The sad thing is that "Micro$oft" was an old joke when a lot of people around here were in kindergarten.

      --
      You are in a maze of twisty little passages, all alike.
    12. Re:cue by Ramble · · Score: 1

      I don't think Microsoft shows any preference for Intel, after all their NT architecture was designed to support numerous platforms, simply, IBM had a preference for Intel and Microsoft followed.

      --
      "Oh boy"
    13. Re:cue by Doddman · · Score: 1

      Yeah. Not to sound like an asshole, BUT IT SHOULD BE 1080. gosh

      --
      If creativity is the field, copyright is the fence.
    14. Re:cue by Paradise+Pete · · Score: 1
      80 cores? Why, 4 ought to be enough for anyone.

      I hear he lifted that from Lincoln, but left off the "and seven years" part.

    15. Re:cue by Wolfrider · · Score: 1

      Hmm; your ideas intrigue me, and I have subscribed to your newsletter. ;-)

      If you have info on current costs of 8-way x86-64 boxen, pls feel free to contact me offboard.

      --
      .
      == WolfriderV6 == I'm willing to admit that *I just might* be wrong... Are you??
  3. Older Story by Maddog+Batty · · Score: 2, Informative

    Older story on this here: http://hardware.slashdot.org/article.pl?sid=06/09/ 26/1937237

    Sure would be nice to have a play with it once they have worked out how to program it...

    --
    wot no sig
    1. Re:Older Story by ajanp · · Score: 1
      Oh snap, you just slashdotted the slashdotters.

      Spidey Sense tingles. I sense a conspiracy involving the slashdot admins posting a dupe of an old slashdot article because Intel dishes out the $$ for all those ads. Follow the example of your digg brethren and revolt! REVOLT before its too late!!!!

      --
      File Deletion is Murder.
    2. Re:Older Story by timeOday · · Score: 2, Insightful

      Sure would be nice to have a play with it once they have worked out how to program it...
      It's very likely you can get one at Best Buy before they have worked out how to program with it. The fact is, current programming paradigms simply aren't suited to fine-grained parallelism - and in saying that, I don't mean to imply that such a paradigm can definitely exist. Sure there are many parallel research languages, but whether those could be adopted by mainstream programmers and used to achieve anywhere near linear speedup on mainstream applications is an open issue. Even the PS3, which is oriented to media applications which are relatively easy to parallelize, is getting little benefit from its measly half dozen computational units.

      But with single-thread performance growth at a virtual standstill, Moore's law is going to result in exponential growth in the number of cores, whether or not we're ready to write software for them.

      I wonder if we won't move towards a more "biological" paradigm - massive parallelism, but with massive redundancy and therefore inefficiency from a computational standpoint, but also robustness to hardware and software bugs.

    3. Re:Older Story by timeOday · · Score: 1

      A operating system is not a single process with a single thread. A clean installation of Windows has at least 24 processes at boot time. That means if the Kernel is smart enough it will run each of them on a separate core giving you quite a speed boost, and still leaving lots of space.
      Process-level parallelism is fine for servers, but nearly useless for personal computers. The number of processes is irrelevant, it's the number of runnable processes that matters. Most processes spend most of their time waiting for input, such as an interrupt to fire. Your freshly booted Windows may have 24 processes, but what is the CPU load of all of them put together? Maybe 1%? That's how much speedup your multi-core CPU is providing.
    4. Re:Older Story by Wolfrider · · Score: 1

      --The speed boost will be even better when they reduce the OVERHEAD of running everything on separate cores.

      --
      .
      == WolfriderV6 == I'm willing to admit that *I just might* be wrong... Are you??
  4. IA64 by AvitarX · · Score: 4, Insightful

    I remember when IA64 was the next huge supercomputer on a chip 5 years off.

    It didn't work out too well for Intel.

    --
    Wow, sent an e-mail as suggested when clicking on "use classic" banner, and got a fast response that addressed my msg
    1. Re:IA64 by ciroknight · · Score: 5, Funny

      I remember when Pentium was the next huge chip from Intel that was a few years off.

      I guess we all know how that one turned out.

      --
      "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:IA64 by drinkypoo · · Score: 1

      Also Pentium IV - piece of shit, still pretty damned fast, sold like mad. Sometimes Intel's failures are great successes.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    3. Re:IA64 by Jeff+DeMaagd · · Score: 1

      Itanium isn't doing that badly, but it's been relegated to the "heavy iron" mainframe and supercomputer type systems, and that's a tough market. They made a gamble that didn't work as well as they hoped.

    4. Re:IA64 by timeOday · · Score: 2, Informative

      Itanium is doing ridiculously badly. Intel and HP will never recoup the billions they invested through sales of big iron alone.

    5. Re:IA64 by ArsonSmith · · Score: 1

      But, CPU cores are going to be the MHz of the next 20 years. Remember in the late 80s when 8MHz was alot and 33Mhz and 66Mhz were in the lab? 20 years form now we'll have 2Gigacore CPUs running between 2-3GHz.

      --
      Paying taxes to buy civilization is like paying a hooker to buy love.
    6. Re:IA64 by ozbird · · Score: 1

      I remember when the i860 was being touted as a "Cray on a chip" (for small values of Cray.)
      I don't think I've ever seen one in the wild.

  5. It may be known as "a teraflop", but... by 91degrees · · Score: 5, Informative

    It's known incorrectly.

    The measurement is "FLOPS". Floating Point Operations Per Second. It's an acronym. The 'S' is part of the acronym. Hence even if you only have oneof them, it's still a FLOPS. And it's capitalised.

    Strictly speaking it should be "trillion FLOPS" as well since it's not an SI unit but my pedantry is limitted.

    1. Re:It may be known as "a teraflop", but... by peterpi · · Score: 1

      A trillion flopses?

    2. Re:It may be known as "a teraflop", but... by Anonymous Coward · · Score: 5, Insightful

      The measurement is "FLOPS". Floating Point Operations Per Second. But that spells "FPOPS".

      If we're going to be speaking strictly, get it right:

      FLoating point Operations Per Second
    3. Re:It may be known as "a teraflop", but... by KIFulgore · · Score: 5, Funny

      Trickses flopses... precious...

      --
      - For every action, there is an equal and opposite criticism.
    4. Re:It may be known as "a teraflop", but... by drinkypoo · · Score: 1

      Wow, you got modded up. See if you're on a roll by next explaining the difference between Mebibytes and Megabytes :D

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    5. Re:It may be known as "a teraflop", but... by jagilbertvt · · Score: 1

      Funny how you capitalized FPOPS and not FLOPS. It's really FLoating Point Operations Per Second

    6. Re:It may be known as "a teraflop", but... by eudaemon · · Score: 1

      Er,

      A TERRAflop would have something to do with Earth, I suppose?

      A teraflop on the other hand would be ten to the power of 12 (10^12) flops.

    7. Re:It may be known as "a teraflop", but... by KingMotley · · Score: 1

      Actually they both work because "FLOP" (Floating Operations) is also a valid abbreviation.

    8. Re:It may be known as "a teraflop", but... by fitten · · Score: 2, Interesting

      Actually... I think it's more FLoating Point OPerations per Second.

      One floating point operation (say, an add), is a FLOP, not a FLO. Just like a No OPeration is a NOP (alternatively, NOOP, but assembly mnemonic is almost always NOP). If you want to know the rate at which a processor executes FLOPs, you say that it computes at X FLOPS.

    9. Re:It may be known as "a teraflop", but... by fitten · · Score: 1

      Stupid inability to edit posts... :(

      One floating point operation (say, an add), is a FLOP, not a FLO. Just like a No OPeration is a NOP (alternatively, NOOP, but assembly mnemonic is almost always NOP). If you want to know the rate at which a processor executes FLOPs, you say that it computes at X FLOPS.

    10. Re:It may be known as "a teraflop", but... by 91degrees · · Score: 1

      But that spells "FPOPS".

      [Red face]

      Erm. Yes I was waiting for someone to spot that.

    11. Re:It may be known as "a teraflop", but... by maharvey · · Score: 1

      Why not FLoating-point OPerationS per second?

      A single operation would be a FLOP (FLoating-point OPeration). That is more intuitive and also seems to match how it's used in everyday language. The "per second" is understood from the definition (same as it is for Watts).

      And FLOPES would be FLoating point OPeration EquivalentS per second, for AMD processors.

    12. Re:It may be known as "a teraflop", but... by Hal_Porter · · Score: 1

      A Watt is a Joule per second. There is no such thing as "watts per second"

      Unless you were measuring an increase in power consumption.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    13. Re:It may be known as "a teraflop", but... by vuffi_raa · · Score: 1

      oh I get it now- so you use it like this: microsoft likes FLOPS like vista not vista is a FLOP OS -right?

    14. Re:It may be known as "a teraflop", but... by jagilbertvt · · Score: 1

      I point you to the wiki article:

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

      Not to say, wikipedia isn't flawed at times, but a FLOPS is definitely an acronym of FLoating point Operation Per Second.

      heck one floating point operation per second is 1 FLOPS, not 1 FLOP, since we're measuring a speed over time. 1 FLOP would be a useless measurement. How long did that FLOP take?

    15. Re:It may be known as "a teraflop", but... by fitten · · Score: 1

      Ummm... yes? Looks like we are in agreement there.

      FLOP is not a measurement - it's a thing. FADD (floating point add) is a FLOP (floating point operation). If you had a string of one hundred FADD instructions in sequence in a program, you could say there are 100 floating point operations right there... or 100 FLOPs. Now, if you said that it took two seconds to execute all those 100 FLOPs, you would have 50 FLOPS (100 floating point operations performed in two seconds would be 50 floating point operations per second).

      I guess one may debate whether the "P" in FLOPS (floating point operations per second) is for the "P" in "Per" or is it part of the "OP" in "OPeration". My argument was to say that it was a part of "Operation" as FLOP is an acronym in itself for "floating point operation" and the "per second" is represented by the "S". I guess one could argue that "FLOP" is for "floating point operation" and "FLOPS" drops the "P" in "OPeration" and adds a "P" for "Per".

  6. beowulf cluster? by Anonymous Coward · · Score: 4, Funny

    can you imagine.

    1. Re:beowulf cluster? by jollyreaper · · Score: 5, Funny

      beowulf cluster?

      can you imagine. Yeah, man. Or what if Intel codenamed their next processor Beowulf? *inhales, holds breath, exhales slowly, smoke twisting lazily* Can you imagine a Beowulf cluster of Beowulfs or did I just blow your mind?
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
  7. Deja vu all over again by $RANDOMLUSER · · Score: 3, Insightful

    "Intel CEO promises to deliver magical new uber processor within five years".

    Stop me if you've heard this one before...

    --
    No folly is more costly than the folly of intolerant idealism. - Winston Churchill
    1. Re:Deja vu all over again by Fozzyuw · · Score: 3, Funny

      "Intel CEO promises to deliver magical new uber processor within five years".

      Great now, I have to wait five years before I buy my next computer because nothing else will compare unless it's got 80 cores. My duel core looks soooo small now. =(

      --
      "The past was erased, the erasure was forgotten, the lie became truth." ~1984 George Orwell
    2. Re:Deja vu all over again by Hoi+Polloi · · Score: 1

      Will this save me from getting owned in online games? 50000 FPS should do the trick.

      --
      It is by the juice of the coffee bean that thoughts acquire speed, the teeth acquire stains. The stains become a warning
    3. Re:Deja vu all over again by Veni+Vidi+Dormi · · Score: 1

      Don't you mean Deja Moo (as heard on NPR)

      When you hear the same old line of bull time after time.

      Tag this article, "Deja Moo" /.

  8. core 2 duo has a higher transistor density? by doombringerltx · · Score: 2, Insightful

    Intel used 100 million transistors on the chip, which measures 275 millimeters squared. By comparison, its Core 2 Duo chip uses 291 million transistors and measures 143 millimeters squared. Maybe its just because I haven't had my morning coffee yet, or is that a typo?
    1. Re:core 2 duo has a higher transistor density? by Andy+Dodd · · Score: 2, Insightful

      80 cores means there are probably quite a lot of on-chip interconnects between the cores.

      --
      retrorocket.o not found, launch anyway?
    2. Re:core 2 duo has a higher transistor density? by imsabbel · · Score: 3, Informative

      Core2 has 2 or 4 Mbyte l2 cache. 1 bit cache is 6 transitors == more than 200 of those 291 million transistors are high-density cache. (Density of cache is a lot higher than that of logic, which the 80 core cpu nearly solely is made of).

      (Btw, i fucking HATE the "millimeters squared" expression. Its square millimeter. 275 mm squared would be more than 65 cm^2.)

      --
      HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
    3. Re:core 2 duo has a higher transistor density? by DrDitto · · Score: 1

      Intel does not use the classic 6-transistor SRAM cell. Their SRAM technology is cutting-edge and a couple generations beyond everybody else.

    4. Re:core 2 duo has a higher transistor density? by imsabbel · · Score: 1

      Oh, they do. Or give me a patent or whitepaper for the technology they use instead :)

      --
      HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
    5. Re:core 2 duo has a higher transistor density? by DrDitto · · Score: 1

      I was told it is "equivalent" to 4-transistors by someone at Intel. So unless you work for Intel and know better, I'll take his word over the random slashdotter. I'm not about to go searching for patents on it. Plus I'm pretty sure they keep it a trade secret rather than patenting it. There is a reason why Intel gets more cache capacity out of the same technology generation than its competitors.

    6. Re:core 2 duo has a higher transistor density? by ShakaUVM · · Score: 1

      When you square a unit of measure, it means you lay out one unit long, and one wide, and produces a new, higher-dimension unit.

      It's correct to say 10 meters squared, though it is sort of ambiguous, as you point out, as some will read it as 10x1, and some as 10x10.

  9. Frak everything, we're doing 80 blades by jollyreaper · · Score: 5, Funny
    I'm sorry but when I see these competitions I always come back to this Onion piece. A classic.

    http://www.theonion.com/content/node/33930

    Fuck Everything, We're Doing Five Blades

    By James M. Kilts
    CEO and President,
    The Gillette Company

    Would someone tell me how this happened? We were the fucking vanguard of shaving in this country. The Gillette Mach3 was the razor to own. Then the other guy came out with a three-blade razor. Were we scared? Hell, no. Because we hit back with a little thing called the Mach3Turbo. That's three blades and an aloe strip. For moisture. But you know what happened next? Shut up, I'm telling you what happened--the bastards went to four blades. Now we're standing around with our cocks in our hands, selling three blades and a strip. Moisture or no, suddenly we're the chumps. Well, fuck it. We're going to five blades.

    Sure, we could go to four blades next, like the competition. That seems like the logical thing to do. After all, three worked out pretty well, and four is the next number after three. So let's play it safe. Let's make a thicker aloe strip and call it the Mach3SuperTurbo. Why innovate when we can follow? Oh, I know why: Because we're a business, that's why!

    You think it's crazy? It is crazy. But I don't give a shit. From now on, we're the ones who have the edge in the multi-blade game. Are they the best a man can get? Fuck, no. Gillette is the best a man can get.

    What part of this don't you understand? If two blades is good, and three blades is better, obviously five blades would make us the best fucking razor that ever existed. Comprende? We didn't claw our way to the top of the razor game by clinging to the two-blade industry standard. We got here by taking chances. Well, five blades is the biggest chance of all.

    Here's the report from Engineering. Someone put it in the bathroom: I want to wipe my ass with it. They don't tell me what to invent--I tell them. And I'm telling them to stick two more blades in there. I don't care how. Make the blades so thin they're invisible. Put some on the handle. I don't care if they have to cram the fifth blade in perpendicular to the other four, just do it!

    You're taking the "safety" part of "safety razor" too literally, grandma. Cut the strings and soar. Let's hit it. Let's roll. This is our chance to make razor history. Let's dream big. All you have to do is say that five blades can happen, and it will happen. If you aren't on board, then fuck you. And if you're on the board, then fuck you and your father. Hey, if I'm the only one who'll take risks, I'm sure as hell happy to hog all the glory when the five-blade razor becomes the shaving tool for the U.S. of "this is how we shave now" A.

    People said we couldn't go to three. It'll cost a fortune to manufacture, they said. Well, we did it. Now some egghead in a lab is screaming "Five's crazy?" Well, perhaps he'd be more comfortable in the labs at Norelco, working on fucking electrics. Rotary blades, my white ass!

    Maybe I'm wrong. Maybe we should just ride in Bic's wake and make pens. Ha! Not on your fucking life! The day I shadow a penny-ante outfit like Bic is the day I leave the razor game for good, and that won't happen until the day I die!

    The market? Listen, we make the market. All we have to do is put her out there with a little jingle. It's as easy as, "Hey, shaving with anything less than five blades is like scraping your beard off with a dull hatchet." Or "You'll be so smooth, I could snort lines off of your chin." Try "Your neck is going to be so friggin' soft, someone's gonna walk up and tie a goddamn Cub Scout kerchief under it."

    I know what you're thinking now: What'll people say? Mew mew mew. Oh, no, what will people say?! Grow the fuck up. When you're on top, people talk. That's the price you pay for being on top. Which Gillette is, always has been, and forever shall be, Amen, five blades, sweet Jesus in heaven.

    --
    Kwisatz Haderach
    Sell the spice to CHOAM
    This Mahdi took Shaddam's Throne
    1. Re:Frak everything, we're doing 80 blades by grev · · Score: 1

      Not even close.

      Adding more blades to a razor doesn't have much of an effect on "performance", but increasing the core count on a processor theoretically raises processing power exponentially.

    2. Re:Frak everything, we're doing 80 blades by Evangelion · · Score: 1


      I think you mean theoretically linearly, and in practice logarithmically.

    3. Re:Frak everything, we're doing 80 blades by jollyreaper · · Score: 1

      Not even close.

      Adding more blades to a razor doesn't have much of an effect on "performance", but increasing the core count on a processor theoretically raises processing power exponentially. I'll wait for the benchmarks on finished products. Remember how Intel drove the whole "more mhz=faster computer" thing for the longest time? Engineering will try to explain how things work to Marketing but they'll just run with what they can grasp, even if they don't have a good grip. As I understand it, additional cores help for some applications but don't really help for others. Sorry, I've just been bullshitted by marketing-types too many times to take the whole "80 cores" thing as an automatic good.
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
    4. Re:Frak everything, we're doing 80 blades by avronius · · Score: 1

      The onion article was about competition, not performance. It was a satiric look at how one company feels pressured to innovate in an arena where continuously adding *features* will not have a significant impact on the performance of the product. You can't simply substitute Intel for Gillette and assume that the remainder of the article would mesh up.

      It was an interesting parody. Perhaps not entirely on topic, but related.

      And it was freakin' hilarious.

    5. Re:Frak everything, we're doing 80 blades by Peet42 · · Score: 1

      Ditto. :-)

    6. Re:Frak everything, we're doing 80 blades by jollyreaper · · Score: 2, Insightful

      I find this even funnier:

      http://money.cnn.com/2005/09/14/news/fortune500/gi llette/ [cnn.com] Well shit, they should just rename the Onion to The Daily Prophet. Remember that little bit they did about Bush after the first time he was (s)elected, "Our Long National Nightmare of Peace and Prosperity Is Over?" http://www.godlessgeeks.com/BushNightmare.htm Here it is with links to all the jokes that came true. Shit!
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
    7. Re:Frak everything, we're doing 80 blades by Traa · · Score: 1
      I see your TheOnion piece, and raise you a Dave Barry!

      http://www.washingtonpost.com/ac2/wp-dyn/A61952-20 03Jul15

      Blade Inflation
      By Dave Barry

      What's next from the razor-sharp minds of the shaving industry?

      Attention, consumers with bodily hair: The razor industry has news for you! You will never in a million years guess what this news is, unless your IQ is higher than zero, in which case you're already thinking: "Not another blade! Don't tell me they're adding ANOTHER BLADE!!"

      Shut up! Don't spoil the surprise for everybody else!

      Before I tell you the news, let's put it in historical context by reviewing:

      THE HISTORY OF SHAVING

      Human beings are one of only two species of animals that shave themselves (the other one is salamanders). The Internet tells us that humans have been shaving since the Stone Age. Of course, the Internet also tells us that hot naked women want to befriend us, so we can't be 100 percent sure about everything we read there.

      But assuming that www.quikshave.com/ timeline.htm is telling the truth, Neanderthal Man used to pluck his facial hairs "using two seashells as tweezers." No doubt Neanderthal Woman found this very attractive. "You smell like a clam," were probably her exact words. It was during this era that the headache was invented.

      By 30,000 B.C., primitive man was shaving with blades made from flint, which is a rock, so you had a lot of guys whose faces were basically big oozing scabs. The next shaving breakthrough came when the ancient Egyptians figured out how to make razors from sharp metal, which meant that, for the first time, the man who wanted to be well-groomed could, without any assistance or special training, cut an ear completely off.

      This was pretty much the situation until the late 19th century, at about 2:30 p.m., when the safety razor was invented. This introduced a wonderful era known to historians as "The Golden Age of Not Having Razor Companies Introduce Some Ludicrously Unnecessary New Shaving Technology Every 10 Damn Minutes."

      I, personally, grew up during this era. I got my first razor when I was 15, and I used it to shave my "beard," which consisted of a lone chin hair approximately one electron in diameter. (I was a "late bloomer" who did not fully experience

      puberty until many of my classmates, including females, were bald.) My beard would poke its wispy head out of its follicle every week or so, and I, feeling manly, would smother it under 14 cubic feet of shaving cream and lop it off with my razor. Then I would stand in front of the bathroom mirror, waiting for it to grow again. Mine was a lonely adolescence.

      The razors of that era had one blade, and they worked fine; ask any older person who is not actively drooling. But then, in 1971, a very bad thing happened: Gillette, looking for a way to enhance the shaving experience (by which I mean "charge more") came out with a razor that had TWO blades. This touched off a nuclear arms race among razor companies, vying to outdo one another by adding "high-tech" features that made the product more expensive, but not necessarily better. This tactic is called "sneakerization," in honor of the sneaker industry, which now has people paying upwards of $200 a pair for increasingly weird-looking footwear boasting the durability of thinly sliced Velveeta.

      Soon everybody was selling two-blade razors. So the marketing people put on their thinking caps, and, in an astounding burst of creativity, came up with the breakthrough concept of: THREE BLADES. Gillette, which is on the cutting edge (har!) of razor sneakerization, currently has a top-of-the-line three-blade razor -- excuse me, I mean "shaving system" -- called the "Mach3Turbo," which, according to the Gillette Web site (www.gillette.com) has more technology than a nuclear submarine, including "open cartridge architecture" and an "ergonomic handle" featuring "knurled ela

    8. Re:Frak everything, we're doing 80 blades by Eli+Gottlieb · · Score: 1

      The Onion shouldn't rename itself "The Daily Prophet"! Then they'd have to hire that bitch Rita Skeeter.

    9. Re:Frak everything, we're doing 80 blades by jollyreaper · · Score: 1

      The Onion shouldn't rename itself "The Daily Prophet"! Then they'd have to hire that bitch Rita Skeeter. But wasn't she discredited? Oh, wait... Bob Novak, Bill Orally, Ann Coulter... You're right, they'd end up keeping her. Shit.
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
    10. Re:Frak everything, we're doing 80 blades by Eli+Gottlieb · · Score: 1

      It's not like the Daily Prophet ever predicted anything accurately. They spent a whole year lying to the public about a war, remember?

      Wait, lying about a war to the public? Who do we know who does that?

    11. Re:Frak everything, we're doing 80 blades by tjcoyle · · Score: 1

      Truth is stranger than fiction :)

      Gillette unveils 5-bladed razor

  10. No x86 by Ramble · · Score: 1

    It's hard for me to be too impressed, witha specialised chip you can do almost anything, this isn't different from the claims from a small company that they can make chips run at 10GHz, oh, but it's not x86.

    Build an x86 prototype one and I'll worship at the alter of Intel for years to come.
    --
    "Oh boy"
    1. Re:No x86 by drinkypoo · · Score: 1

      this isn't different from the claims from a small company that they can make chips run at 10GHz, oh, but it's not x86.

      And that is somehow supposed to be a bad thing?

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  11. Not only a dupe... but of an old story by CajunArson · · Score: 5, Insightful
    It must be a really slow news day. From the dateline:

    Published: February 11, 2007

    Not to mention that Slashdot (even Zonk) Covered this LAST YEAR.
    But that's OK, I'm sure Slashdot gave insightful and cogent coverage of real events that actually matter to geeks on this site, you know, like the Release of a new major version of GCC
    Oh wait.... that (like a bunch of other actually interesting stories) would be in the aptly-named, sir not appearing on this website category due to it not making enough banner revenue.
    --
    AntiFA: An abbreviation for Anti First Amendment.
    1. Re:Not only a dupe... but of an old story by Valtor · · Score: 1

      An important new feature of GCC 4.2 is its support of OpenMP. In this age of multi-core CPU, this is a must. It's even supported in MS Visual Studio 2005. OpenMP is the way to go IMHO, if you don't know yet what it is, you've got to check it out...

      --
      "Sockets are the standard networking API, also useful for stopping your eyes from falling onto your cheeks" zeromq.org
    2. Re:Not only a dupe... but of an old story by Mathness · · Score: 1

      "Old" news indeed, and they still write it as if is 80 CPU cores, when it is 80 floating-point cores.

      --
      Carbon based humanoid in training.
  12. Imagine a... by simong · · Score: 5, Funny

    oh.

    1. Re:Imagine a... by tsalaroth · · Score: 1

      You are definitely new here.

  13. AMD's response by drgonzo59 · · Score: 3, Insightful
    This is a nice move by Intel. I wonder what AMD's plans are...81 cores?

    Besides, with most software being single-threaded I don't know if a consumer will immediately need more than 4 cores for a while. I can still see software companies trying to come up with ways to keep all 80 cores busy..."Well, they need at least 20 anti-virus processes, 10 genuine advantage monitors, and we'll install 100 shareware application with cute little icons in the task bar by default. There, that should keep all the cores nice and warm and busy -- our job is done!".

    But in all seriousness, I would expect some extremely realistic environmental physical simulations (realtime large n-body interactions and perhaps realtime computational fluid dynamics)...now that's something to look forward to!

    1. Re:AMD's response by mstahl · · Score: 1

      I think one of the possible uses for an 80-core CPU that nobody's really talked about is multiple redundancy. If one core should somehow get fried, you have 79 left.

    2. Re:AMD's response by drgonzo59 · · Score: 1
      If that's the case, might as well connect all unused heatsinks to a griddle and I'll fry my by bacon and eggs in the morning on them. If some of them burn up or get too hot it's "ok" I got 60 others waiting...

      Or... you could just have two and order a CPU to be delivered when one burns up. In fact that's what happens on some mainframes. If a part fries, the machine calls "home" and the company will send a replacement immediately. Sometimes the administrator will find out something went bad only when the replacement part already arrived at the door.

    3. Re:AMD's response by ciroknight · · Score: 1

      AMD's response was buying ATi in order to work on their future chip, "Fusion", which will incorporate somehow a GPU-type accelerator on-die or at least in-package with a traditional x86 CPU.

      GPUs already have "many cores", if you can really call them that; 16 ROPs, 80 texture units, 64 shader cores, etc. Intel's approach is a much simpler architecture (in fact, "too simple" right now, the cores are practically feature-less), but DAAMIT's makes more business-sense (re-use what we've already got vs. invent something new).

      --
      "Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
    4. Re:AMD's response by drgonzo59 · · Score: 1
      That makes sense. The GPUs sometimes have a a higher transistor count than CPUs...

      The problem with Fusion is if they kill the add-on graphics and you just buy one Fusion processor that costs say $400 to plug into the CPU slot. In the meantime, NVIDIA releases their new generation board and Intel releases a new generation CPU. The consumer can choose to upgrade one or the other or both, but an AMD customer is stuck just one expensive part and would have to upgrade it as one piece.

      Perhaps in the future the CPU, the graphics card and the memory will all be on one giant module. You get high performance but not the ability to customize individual components.

    5. Re:AMD's response by Hoi+Polloi · · Score: 2, Funny

      Kilts becomes AMD CEO:

      81 cores? Fuck that! We're going to 100 cores and putting a goddamn window on the CPU so all of the fan boys can watch the electrons flow. Then we're going to put the ethernet connection DIRECTLY on the chip. Ya, you heard me right, a connector right on the damn chip. You disagree? Great, I need your soon to be empty cube to store my prototypes you pussy.

      Wait! Brace yourself, I've got another one. A speaker slapped onto the CPU. You hear that? That is the sound of genius and of every command to the CPU being broadcast. The bling-bling crowd will eat that shit up like a cupcake at a fat camp. Let Intel suck on THAT for a while.

      --
      It is by the juice of the coffee bean that thoughts acquire speed, the teeth acquire stains. The stains become a warning
    6. Re:AMD's response by Tony+Hoyle · · Score: 1

      Virtualisation - dual and quad core doesn't really cut it for massive levels of virtualisation.. you want to reserve at least a core for your host OS, then you've got to divvy up the rest. With dual core that means you're down to having no smp in your vm's (sucks if they're compile boxes), with quad core that's only 3... get 20-30 machines in there and it's starting to look shaky. 80 cores would scale to hundreds of virtual machines without any particular slowdow.

    7. Re:AMD's response by neurojab · · Score: 1

      Besides, with most software being single-threaded I don't know if a consumer will immediately need more than 4 cores for a while. I can still see software companies trying to come up with ways to keep all 80 cores busy

      You're ignoring the server market, where the applications tend to be highly multi-threaded, and it's not difficult at all to keep your CPUs busy.

    8. Re:AMD's response by A+Holstenson · · Score: 1

      I don't know about simulations but where I work we perform calculations in regards to aircraft performance. And more cores means faster calculations which can mean two things:

      1) More calculations => more customer requests served
      2) Higher precision => better results for customers

      Either thing works for me.

    9. Re:AMD's response by saider · · Score: 1

      As I understand the main purpose of buying ATI is to develop an architecture where you can have an arbitrary number of cores for arbitrary functions. Intel's solution hangs coprocessors out on a peripheral bus (graphics cards). AMDs idea is to make coprocessors peers on the same processor connection fabric. So core 1 of the main processor can talk just as easily to the second core as it can talk to the graphics chip and physics chip (or whatever other specialized core you envision).

      Consider your example of the $400 chip being obsolete with the next generation of chips. In Intel's world, you remove or disable the old one an use the new one. In AMD's world, you use them both. With both chips having the same access to the CPU, both can perform their functions. This opens up tremendous opportunities for software developers and breaks away from the traditional architecture.

      AMD didn't buy ATI to compete better on the intel platform. They want to make their own better platform and move computing away from the CPUPeripheral architecture.

      --


      Remember, You are unique...just like everyone else.
    10. Re:AMD's response by HobophobE · · Score: 1

      whatever other specialized core you envision

      I agree entirely. Depending on the software having generalized cores only makes sense for so long before you're not getting enough parallel code to make it worth it. The obvious solution is to view the chip-space as real estate for some general transistors, some cache, some specialized transistors, and whatever other novel and precious can be squeezed in there. That's up to and including running a portion of the cores overclocked in bursts that would, if sustained, be damaging and then switch off to another set of the cores rapidly (a la crop rotation).

      --

      -HobophobE
      Nothing laughs forever.
    11. Re:AMD's response by Yunzil · · Score: 1

      I can still see software companies trying to come up with ways to keep all 80 cores busy...

      I wrote an application for my job (can't tell you, would have to kill you, etc.) that will gladly use as many processors as you can throw at it. So bring it on, Intel. :)

  14. One flop is enough for me... by drgonzo59 · · Score: 1
  15. Re:Comparison? by $RANDOMLUSER · · Score: 1

    How many Library of Congress' is that?

    --
    No folly is more costly than the folly of intolerant idealism. - Winston Churchill
  16. OK: "Stop, for the love of God!" by drgonzo59 · · Score: 1
  17. Ob by rlp · · Score: 2, Funny

    In Soviet Russia, Intel's 80 core processor imagines a Beowolf cluster of you!

    --
    [Insert pithy quote here]
    1. Re: Ob by FST777 · · Score: 1

      But does it run...

      ah, to hell with all these "obs"!

      --
      Free beer is never free as in speech. Free speech is always free as in beer.
    2. Re:Ob by jjsavage · · Score: 1

      After a grueling 15 seconds of Googling, I can't find out what 'ob' means. Is it 'obscure'?

    3. Re:Ob by cparker15 · · Score: 1

      I'm guessing “obligatory”.

      --
      Have you driven a fnord... lately?

      You must wait a little bit before using this resource; please try again later.

  18. 100 cores on the chip on the wall... by Earl+The+Squirrel · · Score: 1

    I wonder how long before our kids are singing,

    100 cores on the chip on the wall, 100 cores on the chip
    take one down, pass it around
    99 cores on the chip on the wall....

  19. Exponential by drgonzo59 · · Score: 1
    O RLY?

    Add 2 cores, you get 2x TFlops, add 4 -- get 16x, add 8 you get 256x TFlops. Why stop there, add 80 you get 2^80 = 1208925819614629174706176x more TFlops. Heck, add 1000 cores and you can simulate the universe! Well, I am putting my life's savings into Intel stock!

    1. Re:Exponential by Evanisincontrol · · Score: 1

      Ah HA.

      2^42 = 4398046511104x more teraflops.

      With that many flops, you could easily find the answer to the universe, life, and everything. It all makes sense now. Deep Thought wasn't telling us the answer is 42... he was telling us that the answer is Intel! Clever bastard.

  20. teraflop_s_ by Lobais · · Score: 1

    'The chip is capable of producing 1 trillion floating-point operations per second, known as a teraflop'
    Should probably be "known as a teraflops".
    You don't two fps, one fp either, right?

  21. For the love of god... by tomstdenis · · Score: 2, Insightful

    and all that is holy on this sacred Earth ...

    This isn't a general purpose processor. Think "cell processor" on a larger scale. You wouldn't be running your firefox or text editor on this thing. You'd load it up and have it do things like graphics processing, ray tracing, DSP work, chemical analysis, etc...

    So stop saying "we already don't have multi-core software now!!!" because this isn't meant for most software anyways.

    Tom

    --
    Someday, I'll have a real sig.
    1. Re:For the love of god... by ciroknight · · Score: 3, Insightful

      "This isn't a general purpose processor."

      ...Yet. You're right in the fact that these cores are incredibly simplistic, so much so that they make DSPs look functional, but really what's going on here is a science project to develop the on-chip network, not to develop the CPU cores as much. Intel envisions lifting the networking component out of this design and applying it to various different cores, so that a general computing core can be mixed in with DSP cores and other "Application Specific Accelerator" cores.

      So no, this model you're not going to be running Firefox or your text editor on (in fact, I doubt you even _could_ do this, these cores currently are very, very stripped down in their capacity to do work, to where they're basically two MACs tied to a small SRAM and a "network adapter"), but never-say-never, this style of chip is right around the corner.

      --
      "Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
  22. Not usefull yet.. by CockroachMan · · Score: 4, Interesting

    It's useless to keep putting more cores into a processor when we still don't have a decent parallel programming paradigm.

    80 cores is an absurd number, with the parallelism level that we have in today programs, most of the cores should be idle most of the time.

    1. Re:Not usefull yet.. by drinkypoo · · Score: 1, Funny

      80 cores is an absurd number, with the parallelism level that we have in today programs, most of the cores should be idle most of the time.

      Depends on the task. It might be useful for a webserver or something. Besides, most single CPUs are idle most of the time (unless people are running folding@home, or are part of a really complex botnet)

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    2. Re:Not usefull yet.. by Crazy+Taco · · Score: 1

      In addition, mathematical models show that more than 16 cores actually HURT performance in most applications. This chip would likely only be useful if we had a better parallel programming paradigm (maybe Intel built the chip so they could study that) and we had a specific application it was useful for (something that could use tons of parallel processors). For most applications, 80 cores will probably hurt performance, and at the very least will be idling and wasting power doing NOPs most of the time.

      --
      Beware of bugs in the above code; I have only proved it correct, not tried it.
    3. Re:Not usefull yet.. by ciroknight · · Score: 1

      I really don't understand this idea that we "can't use multiple cores yet" because we don't have some magical, mythical necessary programming model that will make this come alive instantly. The fact is, we've had the necessary models for decades now. Adding multiple cores doesn't necessarily mean we need to change our programs at all, but rather it means we need to change our Operating Systems.

      To the point: right now, we typically schedule applications to run on time-slices, to virtually expand one processor to every single process we have running. With multi-core, we need to change the way we schedule to be more granular, and to assign better core affinity (to the point where we can address specific cores directly from the operating system, always running the same application on the same core). Every task gets its own core, and can then use threading (or spawning another process) to request/force more core-time if necessary.

      Ordinary desktops have been parallel for a long, long time, we've just hidden it from the users and from the programmers because it's hideously complex when it comes to timing and scheduling. The whole idea of the Operating System was to hide this complexity from the users to begin with, and to put it instead on the shoulders of smarter, better software that has been combed over and refined. To the point: our OSes have emulated parallel machines because we didn't have parallel machines, real-time (or at least near-real-time) multitasking would be impossible without it. Now, we have parallel machines, and we can stop emulating it or at least minimize our need to.

      --
      "Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
    4. Re:Not usefull yet.. by ciroknight · · Score: 1

      "For most applications, 80 cores will probably hurt performance, and at the very least will be idling and wasting power doing NOPs most of the time."

      We can throw away the whole idea of NOPs when it comes to this chip and the technologies we have today. If we're not using the core, simply turn the core off, it's just going to be wasting energy, and you can turn the core back on pretty damn quick (~100's of ns) if you need it. Since these cores are virtually cache-less already, there's no huge to-memory penalty we get with today's enormous cores when they shut down to lower energy states, and it makes sense to have an on-chip load balancer which will make sure no one core gets over taxed and is on more than any other core.

      Lastly, we don't need to change the apps as much as people think we do. For the applications that make sense to parallelize, great, do it. For the ones that don't, don't. It's not going to hurt anything if you don't. You still get N.mGHz speeds on your mono-core app, and to be truthful, it's highly likely that's more than your app will ever need, especially ones that spend most of their time I/O bound (word processors (keyboard), web browsers(network)).

      --
      "Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
    5. Re:Not usefull yet.. by skiflyer · · Score: 1

      I like the claim that mathematical models show more than 16 cores hurt performance in most applications.

      Likewise, I bet there are models that show more than 14 cores hurt performance in a super-plurality of applications. Could've you been more vague? What models, what types of applications, and most importantly why? You can use Amdahl's law to show the theoretical maximum speedup for different types of programs, and guess what, none of them go down after 16, you just flatten (essentially diminishing returns). It's true you do have communication and combination issues which can outweigh computation issues, so if you program like an idiot you can certainly hurt performance... but then just don't code like an idiot, use extra cores when you need the parallel computation, not just cause they're there.

      What "most applications" are you referring to? Do multiple cores hurt word processing, or matrix multiplication, maybe prime factoring or photoshop?

    6. Re:Not usefull yet.. by Bastard+of+Subhumani · · Score: 1

      80 cores is an absurd number
      Eight of these processors ought to be enough for anyone.

      "He never really said that" posts in 5,4,3...
      --
      Only three things are certain; death, taxes, and apocryphal quotations - Ben Franklin.
    7. Re:Not usefull yet.. by Jeff+DeMaagd · · Score: 1

      idling and wasting power doing NOPs most of the time.

      What twit is programming NOPs into modern programs? An idle core doesn't consume much power.

      I would like to see a source for your 16 core claim.

    8. Re:Not usefull yet.. by Eli+Gottlieb · · Score: 1

      Read this to get a handle on other possibilities for OS-level parallelism support.

    9. Re:Not usefull yet.. by bvankuik · · Score: 1

      I'm in the middle of putting together a machine for virtualization purposes and I can tell you, the more cores the better. Although I agree that in this case these cores are not really general purpose cores as we know them.

  23. Isn't this just by Colin+Smith · · Score: 1

    A transputer which was around in the 80s?

    Hmm has it really taken 20 years of research or ... Wonders... 20 years later... Patents...?

    --
    Deleted
  24. look closer by icebones · · Score: 1

    the article says that it won't run x86, i.e.: no XP/Vista, but if you look very closly at the picture of the what they showed at the demo, the XP taskbar appears to be at the bottom of the monitor. Hmmm.

    --
    Life is pain. Anyone who says differently is selling something.
    1. Re:look closer by CogDissident · · Score: 1

      You do know, XP has a dual-core OS (XP 64 bit edition), and simply expanding it to allow it to run on more than 2 doesn't sound like too much of a trick. Fully utilizing all of those, different issue, but getting it to simply "run" a 64bit program doesnt seem impossible.

    2. Re:look closer by DaveV1.0 · · Score: 1

      One word: Emulation.

      --
      There is no "-1 offended" or "-1 you don't agree with me" mod options for a reason.
    3. Re:look closer by icebones · · Score: 1

      umm, it has nothing to do with XP being able to run on multiple cores. Go back and RTFA. It said the instruction sets on the chip couldn't run x86 programs. It specifically mentioned XP and Vista.

      --
      Life is pain. Anyone who says differently is selling something.
    4. Re:look closer by icebones · · Score: 1

      So they've already made a windows emulator for this new chip that doesn't have the instruction sets to run windows? Didn't see that in the article.

      --
      Life is pain. Anyone who says differently is selling something.
    5. Re:look closer by icebones · · Score: 1

      quite possibly, but it was just ironic that the article made a point of saying that the CPU didn't have the instruction sets to to run x86 programs and specifically mentioned xp/vista, but that was on the monitor.

      --
      Life is pain. Anyone who says differently is selling something.
    6. Re:look closer by DaveV1.0 · · Score: 1

      They don't have to emulate windows. They only have to emulate x86 arch.

      --
      There is no "-1 offended" or "-1 you don't agree with me" mod options for a reason.
  25. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  26. Gillette Fusion by The+New+Andy · · Score: 1

    The onion is wrong - they actually went to 6 blades. And no I'm not kidding. Yes, I am bending the truth a bit (the 6th blade is on the back of the razor, to try to slice your hand when you change the blades)

    1. Re:Gillette Fusion by Tony+Hoyle · · Score: 1

      Coming soon...

      Fusion Turbo

      Fusion Power

      Fusion Power Turbo

      Then we start all over again with 10 blades or something, ~doubling the price at each iteration.

    2. Re:Gillette Fusion by ArsonSmith · · Score: 1

      Can I get that chick as a replacement for clippy?

      --
      Paying taxes to buy civilization is like paying a hooker to buy love.
  27. Core count competition? by Cctoide · · Score: 1

    No, mine's bigger!

    --
    "Let's face it, it's a good story. Accuracy would kill it."
  28. Hey I've got a program it can run by mstahl · · Score: 1

    perl -e 'fork while 1;'


    There ya go. Think of it as a benchmark. How long can the 80-core processor run that without dying?

    1. Re:Hey I've got a program it can run by InfiniteWisdom · · Score: 1

      The death comes from process tables filling up, so I suspect the 80 core processor will die faster.

    2. Re:Hey I've got a program it can run by autocracy · · Score: 1

      How fast can it die, or how long does it remain responsive? It is, after all, memory that leads to the eventual death ;)

      --
      SIG: HUP
  29. It's possible... by mbessey · · Score: 3, Informative

    I thought that was a little weird, too. But the 80-core chip could simply have more wires (and therefore, fewer transistors). Given that they mention that there are routing elements between the cores, it's possible that a lot of the chip's real estate is taken up by massive busses between adjacent cores.

    Another explanation might be that they didn't want to waste the time/expense to come up with an optimized layout, or that they intentionally spaced things out to make testing easier.

    1. Re:It's possible... by arunkv · · Score: 1

      The Intel presentation clarifies this to some extent. Look at slide 7. The core is simply a compute element with a router. They have put stacked memory as future implementation. Also here's Intel's Teraflop site.

  30. Re:You are right, but... by 91degrees · · Score: 1

    Well, I don't think there's ever been an elecronic computer that took more than a second to manage a floating point operation. Hence, just say how many FLOPS you have. A trillion flops makes more sense to more people anyway. Not everyone knows the SI prefixes. Outside of electronics, even the Mega prefix is unusual.

  31. Cool! A Minnie Driver/Anne Hathaway love scene. by Impy+the+Impiuos+Imp · · Score: 1

    "64 processors is enough for anybody!" >:(

    --
    (-1: Post disagrees with my already-settled worldview) is not a valid mod option.
  32. Wafer scale by flyingfsck · · Score: 1

    I guess that eventually they'll just fire up a whole 300mm wafer. It'll be cookin...

    --
    Excuse me, but please get off my Pennisetum Clandestinum, eh!
  33. Kind of like the chip itself. by twitter · · Score: 1

    my pedantry is limitted.

    The average user won't notice. There's a threshold for everything, beyond which limits are meaningless.

    --

    Friends don't help friends install M$ junk.

  34. Dude.... by avronius · · Score: 1

    If intel called the 80 cpu beast "Grendel", could it still be part of a Beowulf cluster? Or would it end up in a perpetual battle - cpu versus os - until the very fabric of the universe itself crumbled around us?

    1. Re:Dude.... by jollyreaper · · Score: 3, Interesting

      If intel called the 80 cpu beast "Grendel", could it still be part of a Beowulf cluster? Or would it end up in a perpetual battle - cpu versus os - until the very fabric of the universe itself crumbled around us? If you could work Grendel's mom into a Beowulf cluster of Grendels, you might just have aced the German pr0n market. For Japan, add tentacles. And if you can reverse the expected subject/verb/object order, you might have a market in Soviet Russia to boot.
      --
      Kwisatz Haderach
      Sell the spice to CHOAM
      This Mahdi took Shaddam's Throne
  35. We Did It in 1990 by Doc+Ruby · · Score: 1

    [a teraflop is] a level of performance that required 2,500 square feet of large computers a decade ago.

    Over a decade and a half ago, in 1990, I programmed parallel AT&T DSP32C boards (multiple DSPs per ISA board in an 80386 host). Up to 5 25GFLOPS chips on a 125GFLOPS board, up to 8 boards in a 1TFLOPS host PC. That PC, nearly double the "decade ago", had over 1TFLOPS (including its FPGA glue) in about 3 square feet.

    And it actually ran applications (commercial image processing) in the field. This Intel chip might be smaller than 3'^2, but it still needs to run in the same size PC, and it doesn't run any commercial apps. Even 17 years later, on twice the cores we had in 1990.

    Sure, the past 17 years hasn't seen our parallelism innovations become common (though finally digital cameras are catching up to our 16Mpxl, but not at 40bit color). Because the same problem we didn't solve in general, parallel programming semantics and debugging that reuse existing codebase and techniques, is still hard. But if we'd discarded the uniprocessor codebase then, or just ignored it as we built a new, parallel codebase, we'd have 17 years of code now that would be "legacy" which didn't largely lock us, and our thinking, out of simple multiprocessing development.

    So I hope that Intel's multicore development is really just a platform for developing parallel coding systems. I'd love to see all that Intel money and brains put behind "executable UML", or some other flow "language", by inventing "lossless" lexical/graphical interconverters and expression standards. But they'll probably spend it all on marketing and emulating an 80386 to run Windows. Because that's the part of our 1990 platform that can be reinvented and resold as "brand new", just like it was back then, without taking much of a risk.
    --

    --
    make install -not war

  36. Missing part by Valtor · · Score: 1

    ...Beowulf cluster of these...

    --
    "Sockets are the standard networking API, also useful for stopping your eyes from falling onto your cheeks" zeromq.org
  37. 80 cores but is it still on the FSB? by Joe+The+Dragon · · Score: 1

    also does it have a ram controller build in?

  38. transistor density? by twitter · · Score: 2, Informative

    80 cores means there are probably quite a lot of on-chip interconnects between the cores.

    There has to be a typo hiding in there, but the whole thing is an empty set. It's hard to believe they can make 80 cores with 100E6 transistors when it take 261E6 transistors to make two. Each core would have less than a million transistors in the 80 core model. You have to go all the way back to the 486 to see that kind of count from Intel. It's possible because the cores are not x86, there's no "ability to use memory" and ... it's vapor ware. For the practical significance, they might as well have photographed a box of Pentiums and called it useful because Open Mosix does auto clustering and there are live CD versions. You've got a better chance of computing something with the box of Pentiums.

    Bus space is not likely to be an issue either. It does not show up in this image of the cell processor.

    --

    Friends don't help friends install M$ junk.

    1. Re:transistor density? by FireFury03 · · Score: 1

      There has to be a typo hiding in there, but the whole thing is an empty set. It's hard to believe they can make 80 cores with 100E6 transistors when it take 261E6 transistors to make two.

      Yeah, when I read it I thought it must be a typo (especially given that the die area is bigger). Although, the article says it's VLIW (it isn't specific, but I guess it'll be IA64 based), which means you can throw away a shed-load of transistors from the scheduler that would have to be present on an OOE superscalar device.

    2. Re:transistor density? by timeOday · · Score: 1

      You have to go all the way back to the 486 to see that kind of count from Intel.
      That might not be a terrible idea. Since the utility of this chip assumes fine-grained parallelism anyways, the new metric would have to be flops per transistor. Implement the 486 design with modern process technology, thus allowing you to put 250 of them on a single chip runing at 100x the original clock speed of 33mhz, and you might get something very nice. Or is that even possible?
    3. Re:transistor density? by modecx · · Score: 1

      You have to go all the way back to the 486 to see that kind of count from Intel.

      It could be more or less exactly what they did.

      --
      Constitutional rights may be respected, repealed, or modified; but they must never be ignored.
    4. Re:transistor density? by Hal_Porter · · Score: 1

      Each core would have less than a million transistors in the 80 core model. You have to go all the way back to the 486 to see that kind of count from Intel.

      You can do in order cores very small - 486 is probably quite a good model for this. AMD considered using '486 like' cores, 12 per chip. 18 if you share the FPU.

      http://groups.google.com/group/comp.arch/msg/991ff 1390b277b98?&hl=en

      ARM cores can be smaller and you could probably brew up a really stripped down in order risc chip much smaller.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
  39. Bandwidth by Nom+du+Keyboard · · Score: 1
    My concern isn't that they can cram 80 processors of some capability onto a single chip (how many i486 processors could you put on the current Core 2 Duo die and transistor budget at 65/45nm?), but how can you feed enough data on and back off the chip to keep these processors running at near full speed? 8000 processors on a chip are worthless if they can't get to their data.

    And I'm not impressed by the Flop rate. Not with the Cell Processor already out for a year.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  40. Finally by DrYak · · Score: 1

    80 different distributions at once.


    Intel has found a useful argument they could give to illustrate their newest
    " s/number of GHz/numer bor cores/ "
    marketing propaganda.
    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
  41. I'm getting tired of the ancient computer comparis by dj42 · · Score: 3, Funny

    Well, those shitty, basic computers that took up big rooms, remember those? No? Ok, well, if those were still here, this thing would be like 90239820 times smaller, cool huh? How many of those are we going to have to hear before we come up with some new kind of comparison. You know how fast a woman can plot a route around a detour using a map in a big city? Yeah? Well, this shit is like 939203902093902093092093 times faster.

    --
    We are one consciousness experiencing itself subjectively. Back to you with the weather, Bob!
  42. How Well does it Scale? by nbritton · · Score: 1

    I'd love to know how they managed to scale up to 80way x86? IIRC anything passed 8way was diminishing returns?

  43. how fast does it make toast? by peter303 · · Score: 1

    With high end processor power consumption approaching the better part of a kilowatt, perhaps toasting speed could be a measure.

  44. That's why we need 80 cores. by jd · · Score: 2, Funny

    Clearly, there is a demonstrable need for news sites to process dupes faster and in parallel with other dupes. The reason this one took so long is because there isn't a high-speed dupe instruction on the older generations of processors.

    --
    It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
  45. Yeah, but by WindBourne · · Score: 1

    do you remember the 80286 (which had an extra year wait)? There are some of us here that do. Even the z80 was a bit late by making it a better 8080. I was not waiting for it (but coded on it), but I would guess that 1 or 2 ppl here did.

    --
    I prefer the "u" in honour as it seems to be missing these days.
  46. Just I suspected... by Assassin+bug · · Score: 1

    Of course we won't see an 80-core processor any day soon! Intel will produce "new chips" every couple years and just add cores. I suspect they have done this all along (e.g, the Pentium series). That is it makes sense from a capitalist standpoint to throttle your technology to generate or maintain a certain level of demand. I have no evidence for this, but as cynical as it sounds it sure makes sense.

    1. Re:Just I suspected... by geekoid · · Score: 1

      They would release it right now if they could. You only need to throttle when there is an end game, and you don't have competition.

      The issue is the fab and the die. How many bad die's did they go through to get to this prototype? I would wager they had many more bad dies then good ones.

      --
      The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
  47. Imagine a Octodecalog Array by WillAffleckUW · · Score: 1

    of cheap 80-core Linux computers, all working together to solve problems.

    We could model the weather patterns in the increased storms we're seeing ...

    --
    -- Tigger warning: This post may contain tiggers! --
  48. 640k cores by rrohbeck · · Score: 1

    ought to be enough for anybody.

    Seriously, why don't we put the cores into the memory DIMMs? It's been tried before but now it seems that a CPU core is just a little commodity thing, and memory bandwidth is where the bottleneck is.

  49. How many AMPs? by Skapare · · Score: 1

    At 3.16GHz and with 0.95 volts applied to the processor, it can hit 1 teraflop of performance while consuming 62 watts of power.

    Yikes, that's over 65 amps! Well, OK, it's less than 1 amp per core.

    --
    now we need to go OSS in diesel cars
  50. Here's the sad part... by Khyber · · Score: 1

    Nobody believed me when I mentioned in a previous story comment that I was playing with an 8-core HP test system. Everyone went "No Wai!" and this was about three months or so ago. Lookie here - 80 fucking cores.

    Guess who's laughing now?

    --
    Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
  51. monster computer by Klanglor · · Score: 1

    its funny when you think about it. computer do evolves really fast. we always hear things like years ago a computer used to take up a huge space. now that i read this, i think i will be able to say to my kids (when i'll have some).. you know.. when daddy was young, we used to have Server Rooms with tones and tones of computers working to getter to crunch numbers, now you little gizmo's is 10time more powerful.

  52. I need an 80 core processor... by mrraven · · Score: 1

    ...to keep up with Sladot's dupes.

    Thank you I'll be here all week.

    --
    Tired of all the isms, don't exploit people as an employer, or a government, mmmmK?
  53. We need to abandon FLOPS anyway. by grimdawg · · Score: 1

    This article proves that the FLOPS is a useless unit anyway.

    I call for a move to the (ft)^2.DOC - that's the "square foot of decade old computer".

    Certainly a more suitable unit for today's LoC-savvy audience.

    --
    There are 10 kinds of people in this world: those who understand binary, and nine other kinds of people.