Ignore:
Timestamp:
Jul 3, 2022, 10:10:27 AM (2 years ago)
Author:
Peter A. Buhr <pabuhr@…>
Branches:
ADT, ast-experimental, master, pthread-emulation, qualifiedEnum
Children:
9c6443e
Parents:
aa60460
Message:

add bridge at end of chapter 4 to chapter 5

File:
1 edited

Legend:

Unmodified
Added
Removed
  • doc/theses/thierry_delisle_PhD/thesis/text/core.tex

    raa60460 r3e3bee2  
    309309\subsection{Topological Work Stealing}
    310310
    311 The approach used in the \CFA scheduler is to have per-\proc subqueues, but have an explicit data-structure track which cache substructure each subqueue is tied to.
     311Therefore, the approach used in the \CFA scheduler is to have per-\proc subqueues, but have an explicit data-structure track which cache substructure each subqueue is tied to.
    312312This tracking requires some finesse because reading this data structure must lead to fewer cache misses than not having the data structure in the first place.
    313313A key element however is that, like the timestamps for helping, reading the cache instance mapping only needs to give the correct result \emph{often enough}.
     
    316316To avoid unnecessary cache line invalidation, the map is only written to if the mapping changes.
    317317
     318This scheduler is used in the remainder of the thesis for managing CPU execution, but additional scheduling is needed to handle long-term blocking and unblocking, such as I/O.
     319
Note: See TracChangeset for help on using the changeset viewer.