|
|
@ -27,10 +27,10 @@ |
|
|
\todo{write this section} |
|
|
\todo{write this section} |
|
|
|
|
|
|
|
|
\begin{itemize} |
|
|
\begin{itemize} |
|
|
\item analyse whether prefetching yields better performance than hbm caching mode \cite{intel:xeonmaxbrief} |
|
|
|
|
|
|
|
|
\item evaluate performance with more complex query |
|
|
\item evaluate impact of lock contention and atomics on performance |
|
|
\item evaluate impact of lock contention and atomics on performance |
|
|
\item provide optimized use case specific versions with less locking |
|
|
|
|
|
\item extend the cache implementation use cases where data is not static |
|
|
|
|
|
|
|
|
\item implement direct dsa access to assess gains from using shared work queue |
|
|
|
|
|
\item improve the cache implementation for use cases where data is not static |
|
|
\end{itemize} |
|
|
\end{itemize} |
|
|
|
|
|
|
|
|
%%% Local Variables: |
|
|
%%% Local Variables: |
|
|
|
