18.337 WebMeeting

Message from: Dongyi Liao (liaody@MIT.EDU)
About: Why should we use this method in PartII(c)?

Sat, 15 Feb 97 19:50:56 EST

  • Next message: Alan Edelman: "Why should we use this method in PartII(c)?"
    I was wondering why we should use that method in Part II(c)?

    We can simply use (a) to calculate total, use (b) to let
    every processor know the total, and then everyone substract
    the value of itself and left, right neighbor to get the
    value we are now calculating.

    Here is a comparation:
    Method(c) Method(a)+(b)
    Time scale log2P log2P
    Space scale(per proc) log2P 1
    Message per proc log2P 1

    Of course, the method used in (c) could be the best way in
    other cases, but who can tell me an example?
    (I am mainly dissatisfied by the non-const space scale, that
    means we must alloc memory dynamically if we don't want to
    waste)

    ----
    NOTE: This message was sent using a WWW form. The address liaody@mit.edu
    was typed manually, and may easily be incorrect.

    You may post a follow-up message or a new message. To send a reply directly to the author, you may click on the email address above.

    If you would like to submit a message using your own mail program, send it to: 18.337-wm@webmeet.mit.edu

    If you are following up this article, please include the following line at the beginning of your message: 
    In-Reply-To: 9702160050.AA21047@arachnophobia.MIT.EDU