deletions | additions       diff --git a/artifact/session2.tex b/artifact/session2.tex  index c5cdd09..0752938 100644  --- a/artifact/session2.tex  +++ b/artifact/session2.tex 
...
\end{verbatim}  \end{small}  \noindent which loads the IR code, performs a warm-up execution of the benchmark, and then 10 repetitions. The experiment duration is was  $\approx1$m, with a time per trial of  $\approx5.725$s. The benchmark with the hottest loop instrumented with a never-firing OSR can be run as follows: 
...
\end{verbatim}  \end{small}  \noindent The experiment duration is $\approx1$m with Note that the second line inserts  a time per trial: $\approx5.673$s. The ratio $5.673/5.725=0.990$ for never-firing open OSR point at instruction labeled with  {\tt n-body} is slightly smaller than the one reported in \ref{fig:code-quality-base} on the Intel Xeon. The experiment for building \ref{fig:code-quality-O1} uses scripts 8} (actually {\tt :8})  in function  {\tt bench-O1} and bench} of file  {\tt codeQuality-O1}. shootout/n-body/bench.ll}, using branch weight of 5\% as a hint for the LLVM native code generation back-end that OSR firing is very unlikely.  The experiment duration was $\approx1$m with a time per trial: $\approx5.673$s. The ratio $5.673/5.725=0.990$ for {\tt n-body} is slightly smaller than the one reported in \ref{fig:code-quality-base} on the Intel Xeon. The experiment for building \ref{fig:code-quality-O1} uses scripts in {\tt bench-O1} and {\tt codeQuality-O1}.  \paragraph{Question Q2.} This experiment assesses the run-time overhead of an OSR transition by measuring the duration of an always-firing OSR execution and of a never-firing OSR execution, and reporting the difference averaged over the number of fired OSRs. The script always-firing OSR execution  for this is: {\tt n-body} (unoptimized) is as follows:  \begin{small}  \begin{verbatim}  tinyvm$ $  tinyvm shootout/scripts/bench/n-body shootout/scripts/finalAlwaysFire/n-body  \end{verbatim}  \end{small}  \noindent which runs:  \begin{small}  \begin{verbatim}  LOAD_IR shootout/n-body/finalAlwaysFire.ll  INSERT_OSR 95 ALWAYS SLVD UPDATE IN advance AT   %entry TO advance AT %entry AS advance_OSR  bench(50000000)  REPEAT 10 bench(50000000)  QUIT  \end{verbatim}  \end{small}  \noindent The second line inserts an always-firing resolved OSR point at instruction labeled with {\tt \%entry} in function {\tt advance} of file {\tt shootout/n-body/finalAlwaysFire.ll}, generating a continuation function called {\tt advance\_OSR}. A branch weight of 95\% is given as a hint for the LLVM native code generation back-end that OSR firing is a high-probability event. The time per trial was $\approx5.876$s.  The never-firing OSR execution used as baseline is as follows:  \begin{small}  \begin{verbatim}  $ tinyvm shootout/scripts/finalAlwaysFire/  baseline/n-body  \end{verbatim}  \end{small}  \noindent with a time per trial of $\approx5.669$s. The average time per OSR transition is therefore $(5.876-5.669)/50000000=4.14\cdot 10^{-9}$s. Compare this with the result of \ref{tab:sameFun}.  \paragraph{Question Q3.}