Camil Demetrescu  over 8 years ago

Commit id: 0480315b6b3f24d8a610c99c6336e01e3fd544d9

deletions | additions      

       

% !TEX root = article.tex  \section{Experimental Evaluation}  \label{se:experiments} 

TinyVM is thus an ideal playground to exercise our OSR technique, and we use it to run performance measurements on the shootout test suite, also known as the Computer Language Benchmark Game~\cite{shootout}. The list of benchmarks and their description is reported in Table~\ref{tab:shootout}; four of them - namely {\tt b-trees}, {\tt mbrot}, {\tt n-body} and {\tt sp-norm} - are evaluated against two workloads of different size.  \begin{table}   \begin{small}  \begin{tabular}{ |c|c| }  \hline  {\em Benchmark} & {\em Description} \\  

\hline  \end{tabular}   \caption{\label{tab:shootout} Description of the shootout benchmarks}   \end{small}  \end{table}  \subsection{Setup} 

In this [...]  \begin{table}   \caption{\label{tab:sameFun}Average cost of an OSR transition to the same function.} \begin{footnotesize}  \begin{tabular}{ |c|c|c|c| }  \hline  Benchmark & Fired OSR transitions & Live values & Avg time (ns) \\  

sp-norm-large & 19\,360\,000\,000 & 2 & 0.756 \\  \hline  \end{tabular}   \end{footnotesize}  \caption{\label{tab:sameFun}Average cost of an OSR transition to the same function.}  \end{table}  % figure