\newcommand{\MI}{\mathit{MaxIter}}
-\usepackage{array}
-\usepackage{color, colortbl}
-\newcolumntype{M}[1]{>{\centering\arraybackslash}m{#1}}
-\newcolumntype{Z}[1]{>{\raggedleft}m{#1}}
-
\begin{document}
\title{Simulation of Asynchronous Iterative Numerical Algorithms Using SimGrid}
algorithms can significantly reduce overall execution times by suppressing idle times due to synchronizations especially
in a grid computing context.
-\begin{figure}[htbp]
+\begin{figure}[!t]
\centering
\includegraphics[width=8cm]{AIAC.pdf}
\caption{The Asynchronous Iterations - Asynchronous Communications model }
\end{equation}
is solved independently by a cluster and communications are required to update the right-hand side sub-vector $Y_l$, such that the sub-vectors $X_m$ represent the data dependencies between the clusters. As each sub-system (\ref{eq:4.1}) is solved in parallel by a cluster of processors, our multisplitting method uses an iterative method as an inner solver which is easier to parallelize and more scalable than a direct method. In this work, we use the parallel algorithm of GMRES method~\cite{ref1} which is one of the most used iterative method by many researchers.
-\begin{figure}
+\begin{figure}[!t]
%%% IEEE instructions forbid to use an algorithm environment here, use figure
%%% instead
\begin{algorithmic}[1]
elements of the solution $x$ are exchanged by message passing using MPI
non-blocking communication routines.
-\begin{figure}
+\begin{figure}[!t]
\centering
\includegraphics[width=60mm,keepaspectratio]{clustering}
\caption{Example of three clusters of processors interconnected by a virtual unidirectional ring network.}
62 \text{ to } 171$ elements or from $62^{3} = \np{238328}$ to $171^{3} =
\np{5211000}$ entries.
-\begin{table}
+\begin{table}[!t]
\centering
- \caption{2 Clusters x 50 nodes each}
+ \caption{2 clusters, each with 50 nodes}
\label{tab.cluster.2x50}
-
- \tiny
-
-\begin{tabular}{|Z{0.55cm}|Z{0.25cm}|Z{0.25cm}|M{0.25cm}|Z{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|M{0.25cm}|}
- \hline
- \bf bw & 5 &5 & 5 & 5 & 5 & 50 & 50 & 50 & 50 & 50 & 10 & 10\\
- \hline
- \bf lat & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.03 & 0.01\\
- \hline
- \bf power & 1 & 1 & 1 & 1.5 & 1.5 & 1.5 & 1.5 & 1.5 & 1.5 & 1.5 & 1 & 1.5\\ \hline \bf size & 62 & 62 & 62 & 100 & 100 & 110 & 120& 130 & 140 & 150 & 171 & 171\\ \hline
- \bf Prec/Eprec & 10$^{-5}$ & 10$^{-8}$ & 10$^{-9}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-11}$ & 10$^{-5}$ & 10$^{-5}$\\ \hline
- \bf speedup & 0.396 & 0.392 & 0.396 & 0.391 & 0.393 & 0.395 & 0.398 & 0.388 & 0.393 & 0.394 & 0.63 & 0.778\\ \hline
- \end{tabular}
-\end{table}
+ \renewcommand{\arraystretch}{1.3}
+
+ \begin{tabular}{|>{\bfseries}r|*{12}{c|}}
+ \hline
+ bw
+ & 5 & 5 & 5 & 5 & 5 & 50 \\
+ \hline
+ lat
+ & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 \\
+ \hline
+ power
+ & 1 & 1 & 1 & 1.5 & 1.5 & 1.5 \\
+ \hline
+ size
+ & 62 & 62 & 62 & 100 & 100 & 110 \\
+ \hline
+ Prec/Eprec
+ & \np{E-5} & \np{E-8} & \np{E-9} & \np{E-11} & \np{E-11} & \np{E-11} \\
+ \hline
+ speedup
+ & 0.396 & 0.392 & 0.396 & 0.391 & 0.393 & 0.395 \\
+ \hline
+ \end{tabular}
+
+ \smallskip
+
+ \begin{tabular}{|>{\bfseries}r|*{12}{c|}}
+ \hline
+ bw
+ & 50 & 50 & 50 & 50 & 10 & 10 \\
+ \hline
+ lat
+ & 0.02 & 0.02 & 0.02 & 0.02 & 0.03 & 0.01 \\
+ \hline
+ power
+ & 1.5 & 1.5 & 1.5 & 1.5 & 1 & 1.5 \\
+ \hline
+ size
+ & 120 & 130 & 140 & 150 & 171 & 171 \\
+ \hline
+ Prec/Eprec
+ & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-5} & \np{E-5} \\
+ \hline
+ speedup
+ & 0.398 & 0.388 & 0.393 & 0.394 & 0.63 & 0.778 \\
+ \hline
+ \end{tabular}
+\end{table}
Then we have changed the network configuration using three clusters containing
respectively 33, 33 and 34 hosts, or again by on hundred hosts for all the
permitted to get the results in Table~\ref{tab.cluster.3x33} which shows the
speedups less than 1 with a matrix size from 62 to 100 elements.
-\begin{table}
+\begin{table}[!t]
\centering
- \caption{3 Clusters x 33 nodes each}
+ \caption{3 clusters, each with 33 nodes}
\label{tab.cluster.3x33}
-
- \tiny
-
-\begin{tabular}{|Z{0.55cm}|Z{0.25cm}|Z{0.25cm}|M{0.25cm}|Z{0.25cm}|M{0.25cm}|M{0.25cm}|}
- \hline
- \bf bw & 10 &5 & 4 & 3 & 2 & 6\\ \hline
- \bf lat & 0.01 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02\\
- \hline
- \bf power & 1 & 1 & 1 & 1 & 1 & 1\\ \hline
- \bf size & 62 & 100 & 100 & 100 & 100 & 171\\ \hline
- \bf Prec/Eprec & 10$^{-5}$ & 10$^{-5}$ & 10$^{-5}$ & 10$^{-5}$ & 10$^{-5}$ & 10$^{-5}$\\ \hline
- \bf speedup & 0.997 & 0.99 & 0.93 & 0.84 & 0.78 & 0.99\\
- \hline
- \end{tabular}
-\end{table}
+ \renewcommand{\arraystretch}{1.3}
+
+ \begin{tabular}{|>{\bfseries}r|*{6}{c|}}
+ \hline
+ bw
+ & 10 & 5 & 4 & 3 & 2 & 6 \\
+ \hline
+ lat
+ & 0.01 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 \\
+ \hline
+ power
+ & 1 & 1 & 1 & 1 & 1 & 1 \\
+ \hline
+ size
+ & 62 & 100 & 100 & 100 & 100 & 171 \\
+ \hline
+ Prec/Eprec
+ & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} \\
+ \hline
+ speedup
+ & 0.997 & 0.99 & 0.93 & 0.84 & 0.78 & 0.99 \\
+ \hline
+ \end{tabular}
+\end{table}
In a final step, results of an execution attempt to scale up the three clustered
configuration but increasing by two hundreds hosts has been recorded in
Table~\ref{tab.cluster.3x67}.
-\begin{table}
+\begin{table}[!t]
\centering
- \caption{3 Clusters x 66 nodes each}
+ \caption{3 clusters, each with 66 nodes}
\label{tab.cluster.3x67}
-
- \tiny
-\begin{tabular}{|M{0.55cm}|M{0.25cm}|}
- \hline
- \bf bw & 1\\ \hline
- \bf lat & 0.02\\
- \hline
- \bf power & 1\\
- \hline
- \bf size & 62\\
- \hline
- \bf Prec/Eprec & 10$^{-5}$\\
- \hline
- \bf speedup & 0.9\\
- \hline
+ \renewcommand{\arraystretch}{1.3}
+
+ \begin{tabular}{|>{\bfseries}r|c|}
+ \hline
+ bw & 1 \\
+ \hline
+ lat & 0.02 \\
+ \hline
+ power & 1 \\
+ \hline
+ size & 62 \\
+ \hline
+ Prec/Eprec & \np{E-5} \\
+ \hline
+ speedup & 0.9 \\
+ \hline
\end{tabular}
-\end{table}
+\end{table}
Note that the program was run with the following parameters:
