tick tock dead, P, A and O is go.

Discussion in 'Intel x86 CPUs and chipsets' started by NSanity, Mar 28, 2016.

  1. power

    power Member

    Joined:
    Apr 20, 2002
    Messages:
    66,692
    Location:
    brisbane
    could have maybe, but let's be honest Intel are the only gig in town so they can control pricing to an extent - and they are a premium product with pricing to match.
     
  2. nope

    nope Member

    Joined:
    May 8, 2012
    Messages:
    3,459
    Location:
    Tipshits
    i paid $350 in 2009 for a i7 920
    paid $300 for i5 4690

    Not much progress
     
  3. DudeLove

    DudeLove Member

    Joined:
    Jan 23, 2008
    Messages:
    135

    Inflation and weak Aussie dollar mate. Massive difference
     
  4. Triangulum

    Triangulum Member

    Joined:
    Dec 23, 2014
    Messages:
    20
  5. OP
    OP
    NSanity

    NSanity Member

    Joined:
    Mar 11, 2002
    Messages:
    18,361
    Location:
    Canberra
    You do realise that the biggest thing that scares Intel now isn't AMD, but Arm?

    An Arm processor isn't far off doing basic office drone tasks (and small servers) - does it at a much smaller power envelope, and costs pennies compared to Intel.

    Intel is busy trying to get x86 smaller, whilst Arm is busy trying to get bigger.

    AMD is a non-event.
     
  6. adamsleath

    adamsleath Member

    Joined:
    Oct 17, 2006
    Messages:
    19,178
    Location:
    Sunnybank Q 4109
  7. DudeLove

    DudeLove Member

    Joined:
    Jan 23, 2008
    Messages:
    135


    Yeah Tarj. ;-)

    My point was any monopoly by its very nature stifles competition and reducing prices and getting better products.

    That's why oligopolies in the form of amd or arm are good and why the prices haven't fallen or tech not improved much or new invented fast enough.


    I'm well aware of the fact you can't shrink and atom ;-)

    But how about cpus based on light rather than electricity ect ...

    Ps. Yes I have a degree in computer science so don't miss interpret my abstract exaggerated examples as ignorance. I'm just on the train typing this on my phone. :)
     
  8. Pookey

    Pookey Member

    Joined:
    Dec 24, 2009
    Messages:
    1,862
    Location:
    Sydney
    Moore's Law is actually that transistor density will double every 24 months. It's up to the manufacturer what they do with that extra density and in Intel's case, they have been focusing on improving power efficiency and multi-thread performance (partly because higher clocks mean more heat and rapidly rising inefficiency).

    Intel has been holding true to the doubling of transistor density every 24 months until they stumbled with the Broadwell delays and now Kaby Lake. We have known that the roadblock was approaching for many years, there's a limit to how small they can take the silicon without getting excessive electron leakage and we're fast approaching that point. Intel's new approach will in all likelihood spell the death knell for Moore's Law and move us to a doubling in density every ~3 years. Even so, there is still a hard limit in the next 10-20 years and returns will continue to diminish.
     
  9. adamsleath

    adamsleath Member

    Joined:
    Oct 17, 2006
    Messages:
    19,178
    Location:
    Sunnybank Q 4109
    http://www.extremetech.com/extreme/203490-moores-law-is-dead-long-live-moores-law



    look at the graph : specifically note the performance per clock flat-line

    coding for multi-core cpus - if it is possible - and im guessing that a new technology (spintronics already used in storage) quantum tech.

    ? :p

    http://fossbytes.com/intel-moore-law-dead-chip-tick-tock/ - see thread title
    http://www.multicore-association.org/ - mmmmmmm MultiCore

    [​IMG]
     
    Last edited: Apr 25, 2016

Share This Page

Advertisement: