1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

News Intel announces Internet of Things Platform

Discussion in 'Article Discussion' started by Gareth Halfacree, 10 Dec 2014.

  1. Gareth Halfacree

    Gareth Halfacree WIIGII! Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    4 Dec 2007
    Posts:
    17,066
    Likes Received:
    6,610
  2. PCBuilderSven

    PCBuilderSven Minimodder

    Joined:
    3 Oct 2010
    Posts:
    130
    Likes Received:
    1
    I'm not going to pretend I actually know anything about the F00F bug but while reading up what it is, i came across this:

    What does this then mean for the presence of the F00F bug on the quark, I can hardly see Intel restoring a bug they had previously fixed?
     
  3. Corky42

    Corky42 Where's walle?

    Joined:
    30 Oct 2012
    Posts:
    9,648
    Likes Received:
    388
    Going on what i read, no it doesn't.
    The F00F bug affected all Pentiums from model 0 through 8, Quark is model 9.
    I think it maybe thought that the bug still exists because Linux picks up the Quark as a Pentium, so thinks/reports that the bug is present.
     
  4. Gareth Halfacree

    Gareth Halfacree WIIGII! Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    4 Dec 2007
    Posts:
    17,066
    Likes Received:
    6,610
    As far as I'm aware, the Linux kernel detects the F00F bug correctly in the Quark, and works around it automatically and invisibly. That's my understanding, anyway: I've got a Galileo 'ere with Quark chip on-board, and the kernel activates its F00F workaround. If the bug (sorry, Intel, 'erratum') isn't present on the Quark, then the Linux kernel is suffering from a false positive and activating a workaround where it isn't required. As I say, though, as far as I'm aware that isn't the case: I understand the bug is present, as the Quark is nothing more than a die-shrink of the faulty Pentium microarchitecture.

    I've got an Edison on the way, which uses a newer Quark chip and a designed-by-Intel Linux variant; once that's arrived, I'll do some more investigation to see if the bug really is present or not.
     
  5. Corky42

    Corky42 Where's walle?

    Joined:
    30 Oct 2012
    Posts:
    9,648
    Likes Received:
    388
    Yea, I mean i can't pretend i know one way or the other, i was just repeating what i read, specifically here, and here.
     
  6. Gareth Halfacree

    Gareth Halfacree WIIGII! Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    4 Dec 2007
    Posts:
    17,066
    Likes Received:
    6,610
    Oh, I'm perfectly prepared to be wrong! If it turns out the Quark doesn't have F00F, then I'll submit a bug report to the Linux kernel warning of a false positive; if it does have F00F, I'll do a smug little grin and maybe treat myself to a bottle of beer for being a clever-clogs.
     
  7. Corky42

    Corky42 Where's walle?

    Joined:
    30 Oct 2012
    Posts:
    9,648
    Likes Received:
    388
    I would be interested in the result either way, if/when you have the time/resources to find out.
     

Share This Page