Results 1 to 2 of 2

Thread: Flat combining: new, much faster approach to concurrent data structure locking

  1. #1
    Member
    Join Date
    Feb 2010
    Location
    Nordic
    Posts
    200
    Thanks
    41
    Thanked 36 Times in 12 Posts

    Flat combining: new, much faster approach to concurrent data structure locking


  2. #2
    Administrator Shelwien's Avatar
    Join Date
    May 2008
    Location
    Kharkov, Ukraine
    Posts
    3,134
    Thanks
    179
    Thanked 921 Times in 469 Posts
    Thanks, the idea itself seems obvious (letting one thread to handle all accesses to data structure),
    and not necessarily efficient (as they pointed out themselves, eg. with tree search),
    but there're many interesting details mentioned.

    I wonder if we can use this approach in compression; eg. parallel CM processing of bits in bytes.
    Somehow I implied that each thread needs its own sync checks (like when one thread
    updates a counter and another already reads it), but having a dedicated thread for memory
    i/o starts making sense now, taking into account cache invalidation.

Similar Threads

  1. My concurrent block sorter (QRotSort)
    By Piotr Tarsa in forum Data Compression
    Replies: 16
    Last Post: 21st August 2011, 14:19
  2. New data structure for bitwise CM
    By Shelwien in forum Data Compression
    Replies: 5
    Last Post: 27th November 2010, 17:35
  3. GCC 4.6 faster than previous GCC, faster than LLVM
    By willvarfar in forum The Off-Topic Lounge
    Replies: 2
    Last Post: 15th November 2010, 16:09
  4. A new approach?
    By Kaw in forum Data Compression
    Replies: 28
    Last Post: 12th May 2009, 23:17
  5. Faster PAQ7/8
    By LovePimple in forum Forum Archive
    Replies: 6
    Last Post: 8th February 2007, 14:04

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •