From: Arnaud Giersch Date: Wed, 25 Apr 2012 20:38:58 +0000 (+0200) Subject: More details on experimental context. X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/loba-papers.git/commitdiff_plain/616eff22be6d742dbc218943c6901dd2f7a2a9dc More details on experimental context. --- diff --git a/supercomp11/supercomp11.tex b/supercomp11/supercomp11.tex index 37e8ef4..cb1c983 100644 --- a/supercomp11/supercomp11.tex +++ b/supercomp11/supercomp11.tex @@ -450,12 +450,31 @@ available at \textbf{FIXME URL}. \subsection{Experimental contexts} \label{Contexts} -\textbf{FIXME once the experimentation is done!} +\paragraph{Configurations} \begin{description} -\item[platforms] homogeneous (cluster) ; heterogeneous (subset of Grid5000) -\item[topologies] -\item[algorithms] -\item[etc.] +\item[\textbf{platforms}] homogeneous (cluster); heterogeneous (subset + of Grid5000) +\item[\textbf{platform size}] platforms with 16, 64, 256, and 1024 nodes +\item[\textbf{topologies}] line; torus; hypercube +\item[\textbf{initial load distribution}] initially on a only node; + initially on all nodes +\item[\textbf{comp/comm ratio}] $10/1$, $1/1$, $1/10$ +\end{description} + +\paragraph{Algorithms} +\begin{description} +\item[\textbf{strategies}] makhoul; besteffort with $k\in \{1,2,4\}$ +\item[\textbf{variants}] with, and without virtual load (bookkeeping) +\item[\textbf{domain}] real load, and integer load +\end{description} + +\paragraph{Metrics} + +\begin{description} +\item[\textbf{average idle time}] +\item[\textbf{average convergence date}] +\item[\textbf{maximum convergence date}] +\item[\textbf{data transfer amount}] relative to the total data amount \end{description} \subsection{Validation of our approaches}