Coffeehouse Thread

41 posts

Forum Read Only

This forum has been made read only by the site admins. No new threads or comments can be added.

Where is my 128 GHz chip ?

Back to Forum: Coffeehouse
  • User profile image
    Proton2

    I like this prediction from 2000 :

    early 2001: 1 GHz
    mid 2002: 2 GHz
    early 2004: 4 GHz
    mid 2005: 8 GHz
    early 2007: 16 GHz
    mid 2008: 32 GHz
    early 2010: 64 GHz
    mid 2011: 128 GHz

    Intel predicts 10GHz chips by 2011

    http://www.geek.com/chips/intel-predicts-10ghz-chips-by-2011-564808/

    - - -

    I also like this comment by a reader in that article :

    "If 10 GHz is the best that Intel can do by 2011, AMD or somebody else is going to eat their lunch. Intel better pick up the pace if they want to remain dominant. Besides, I want it NOW.  What will I do with it.  Well, I also want the applications now.  I guess I've been spoiled by the industry and expect incredible improvements every year. - by Allen"

  • User profile image
    GoddersUK

    All seems a bit unnecessary when there's a world market for, maybe, five computers.

  • User profile image
    Dr Herbie

    @GoddersUK: ... especially when you can fit everything you need into 640K of memory.

  • User profile image
    spivonious

    Ha, that's a fun look back. I think we'd probably be there if multi-core hadn't replaced the "faster is better" mentality at Intel. We'd all be carrying around smartphones with liquid cooling systems.

  • User profile image
    Heywood_J

    I also like this comment by a reader in that article :

    "If 10 GHz is the best that Intel can do by 2011, AMD or somebody else is going to eat their lunch. Intel better pick up the pace if they want to remain dominant. Besides, I want it NOW.  What will I do with it.  Well, I also want the applications now.  I guess I've been spoiled by the industry and expect incredible improvements every year. - by Allen"

    Well, at least one person had the right idea:

     

    Why predict so far... (3:00pm EST Wed Jul 26 2000)
    Why predict so far in the future... They never predict things like this right... This is totally bogus - by Anon

  • User profile image
    fanbaby

    LOL - reading the comments from 2000. We'll look pretty silly ten years from now Wink

    An example: "Back in grad school I worked on computing with light and transistors that had ten states (0-9 or base 10) rather than 2 (0 and 1 or binary). Anybody who doesn't think that these types of technology won't be commercially available by 2011 is kidding themselves. "

     

  • User profile image
    Minh

    This is why I never bought Kurzweil's idea of the Singularity.

  • User profile image
    GoddersUK

    , fanbaby wrote

    LOL - reading the comments from 2000. We'll look pretty silly ten years from now Wink

    An example: "Back in grad school I worked on computing with light and transistors that had ten states (0-9 or base 10) rather than 2 (0 and 1 or binary). Anybody who doesn't think that these types of technology won't be commercially available by 2011 is kidding themselves."

    Actually, whether by poor English skills or by judgment, they got it right...

  • User profile image
    GoddersUK

    @fanbaby: This guy's pretty close to the mark of where things seem to be heading:

    What I'd like to know is if, by 2011, it will be necessary to have expansion cards (i.e. graphics cards, sound cards, or whatever) at all. The future computer I envision (and maybe it's just a coolaid trip) would be a box, with ports, that could be configured to do any number of functions, with the functionality added just-in-time... I'd like to see systems where _all_ resources could be dedicated to a specific task if the user so desired. The current model of dedicated components isn't terribly efficient. - by TropicalPunch

  • User profile image
    Minh

    , GoddersUK wrote

    @fanbaby: This guy's pretty close to the mark of where things seem to be heading:

    *snip*

    Kinda like this?

    Generic Forum Image

  • User profile image
    ScanIAm

    , Minh wrote

    This is why I never bought Kurzweil's idea of the Singularity.

    Kurzweil should stick to keyboards.

    On a side note, is 128GHz even possible?  At some point, electricity can't travel far enough in a single cycle to even make it through an instruction.

    This is the same reason that bandwidth speeds for Ethernet isn't improving much.

    Just because some guy names Moore spouted some nonsense 40 years ago, doesn't make it true.

  • User profile image
    Geoffreyk

    , spivonious wrote

     We'd all be carrying around smartphones with liquid cooling systems.

    I have had a couple of liquid cooled smartphones already. One cooled by a lake and another cooled by a bucked of water. My pocket is just too slippery.

  • User profile image
    kettch

    @Geoffreyk: You ought to get the type of silicone cover that I used to have. It was so sticky that I couldn't take it out of my pocket without practically turning the pocket inside out. I couldn't put it back in the pocket without looking like I was performing a lewd act.

  • User profile image
    evildictait​or

    , ScanIAm wrote

    This is the same reason that bandwidth speeds for Ethernet isn't improving much.

    ++

    My ping time to google.com is 25ms.

    The distance between New York and London multiplied by the speed of light = 18ms.

    Now, I'm no expert, but I pretty sure that latency isn't going to halve in the next 18 months without upsetting a whole ton of physicists.

  • User profile image
    ScanIAm

    By the same token, unless I did my math wrong, 128GHz allows an electron to move 2.342128mm. 

    That does seem like a long distance when you think about how small cpu circuits are, but it's not nearly enough to complete any meaningful computation. 

  • User profile image
    davewill

    At these numbers it is like capturing lightening in a bottle, only in silicon in this case.

  • User profile image
    evildictait​or

    , ScanIAm wrote

    By the same token, unless I did my math wrong, 128GHz allows an electron to move 2.342128mm. 

    That does seem like a long distance when you think about how small cpu circuits are, but it's not nearly enough to complete any meaningful computation. 

    The biggest problem is not to do with the CPU being unable to do computations at that speed - it's about being able to put the register banks and the L1 and L2 caches close enough to the CPU that the processor doesn't spend most of it's time waiting for data to process.

    There's no point being able to do a trillion operations a second if you can't load data onto the device or offload it fast enough to be able to make use of it.

    At that kind of speed you also need pretty ridiculous cooling systems in order to keep the chip from simply melting. 

  • User profile image
    kettch

    Chip manufacturers seem to be experimenting more with manufacturing processes and different materials these days.

    Generic Forum Image

Conversation locked

This conversation has been locked by the site admins. No new comments can be made.