- Timestamp:
- Aug 13, 2022, 4:53:26 PM (2 years ago)
- Branches:
- ADT, ast-experimental, master, pthread-emulation
- Children:
- e378c730
- Parents:
- 175eba6
- Location:
- doc/theses/thierry_delisle_PhD/thesis/text
- Files:
-
- 4 edited
Legend:
- Unmodified
- Added
- Removed
-
doc/theses/thierry_delisle_PhD/thesis/text/core.tex
r175eba6 r111d993 208 208 The alternative is to do it the other way around. 209 209 210 \section{Work Stealing++} 210 \section{Work Stealing++}\label{helping} 211 211 To add stronger fairness guarantees to work stealing a few changes are needed. 212 212 First, the relaxed-FIFO algorithm has fundamentally better fairness because each \proc always monitors all subqueues. … … 261 261 The good news is that this problem can be mitigated 262 262 263 \subsection{Redundant Timestamps} 263 \subsection{Redundant Timestamps}\ref{relaxedtimes} 264 264 The problem with polling remote subqueues is that correctness is critical. 265 265 There must be a consensus among \procs on which subqueues hold which \ats, as the \ats are in constant motion. -
doc/theses/thierry_delisle_PhD/thesis/text/intro.tex
r175eba6 r111d993 22 22 Chapter~\ref{intro} defines scheduling and its general goals. 23 23 Chapter~\ref{existing} discusses how scheduler implementations attempt to achieve these goals, but all implementations optimize some workloads better than others. 24 Chapter~\ref{ s:CFARuntime} presents the relevant aspects of the \CFA runtime system that have a significant affect on the new scheduler design and implementation.24 Chapter~\ref{cfaruntime} presents the relevant aspects of the \CFA runtime system that have a significant affect on the new scheduler design and implementation. 25 25 Chapter~\ref{core} analyses different scheduler approaches, while looking for scheduler mechanisms that provide both performance and fairness. 26 Chapter~\ref{ s:UserLevelIO} covers the complex mechanisms that must be used to achieve nonblocking I/O to prevent the blocking of \glspl{kthrd}.26 Chapter~\ref{userio} covers the complex mechanisms that must be used to achieve nonblocking I/O to prevent the blocking of \glspl{kthrd}. 27 27 Chapter~\ref{practice} presents the mechanisms needed to adjust the amount of parallelism, both manually and automatically. 28 28 Chapters~\ref{microbench} and~\ref{macrobench} present micro and macro benchmarks used to evaluate and compare the new scheduler with similar schedulers. -
doc/theses/thierry_delisle_PhD/thesis/text/io.tex
r175eba6 r111d993 1 \chapter{User Level \io}\label{ s:UserLevelIO}1 \chapter{User Level \io}\label{userio} 2 2 As mentioned in Section~\ref{prev:io}, user-level \io requires multiplexing the \io operations of many \glspl{thrd} onto fewer \glspl{proc} using asynchronous \io operations. 3 3 Different operating systems offer various forms of asynchronous operations and, as mentioned in Chapter~\ref{intro}, this work is exclusively focused on the Linux operating-system. -
doc/theses/thierry_delisle_PhD/thesis/text/runtime.tex
r175eba6 r111d993 1 \chapter{\CFA Runtime}\label{ s:CFARuntime}1 \chapter{\CFA Runtime}\label{cfaruntime} 2 2 This chapter presents an overview of the capabilities of the \CFA runtime prior to this thesis work. 3 3
Note: See TracChangeset
for help on using the changeset viewer.