Changeset ddcaff6 for doc/theses/thierry_delisle_PhD/thesis/text/front.tex
- Timestamp:
- Nov 24, 2022, 3:41:44 PM (20 months ago)
- Branches:
- ADT, ast-experimental, master
- Children:
- dacd8e6e
- Parents:
- 82a90d4
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
doc/theses/thierry_delisle_PhD/thesis/text/front.tex
r82a90d4 rddcaff6 88 88 \\ 89 89 Internal Member: \> Martin Karsten \\ 90 \> AssociateProfessor, School of Computer Science \\90 \> Professor, School of Computer Science \\ 91 91 \> University of Waterloo \\ 92 92 \end{tabbing} … … 127 127 Indeed, over-partitioning into small work-units with user threading significantly eases load bal\-ancing, while simultaneously providing advanced synchronization and mutual exclusion capabilities. 128 128 To manage these high levels of concurrency, the underlying runtime must efficiently schedule many user threads across a few kernel threads; 129 which begs the question of how many kernel threads are needed and should the number be dynamically reevaluated.129 which raises the question of how many kernel threads are needed and should the number be dynamically reevaluated. 130 130 Furthermore, scheduling must prevent kernel threads from blocking, otherwise user-thread parallelism drops. 131 When user-threading parallelism does drop, how and when should idle \glspl{kthrd} be put to sleep to avoid wasting CPU resources .131 When user-threading parallelism does drop, how and when should idle \glspl{kthrd} be put to sleep to avoid wasting CPU resources? 132 132 Finally, the scheduling system must provide fairness to prevent a user thread from monopolizing a kernel thread; 133 133 otherwise, other user threads can experience short/long term starvation or kernel threads can deadlock waiting for events to occur on busy kernel threads.
Note: See TracChangeset
for help on using the changeset viewer.