\item The message passing iterative programs consist of the communication and computation times.
This energy model is assumed that the dynamic power consumes during both these times.
While the processor during the communication times involved remain idle and only consumes the static
- power, for more details we refer to \cite{ref53}.
+ power, for more details see \cite{ref53}.
\item It is not well adapted to a heterogeneous architectures when there are different
\end{itemize}
Therefore, one of the more important goals of this work is to develop an energy models that
-taking into account the communication times in addition to computation times to modelize and measure the energy consumptions of the parallel iterative methods. These models are dedicated to all parallel architectures such as the homogeneous and heterogeneous platforms, which are local or distributed computing clusters.
+take into account the communication times in addition to computation times to modelize and measure the energy consumptions of the parallel iterative methods. These models are dedicated to all parallel architectures such as the homogeneous and heterogeneous platforms, which are local or distributed computing clusters.
\section{Conclusion}
\label{ch1:5}
-In this chapter, we are presented in general different types of parallelism levels that can be implemented in a software and hardware techniques. Furthermore, the types of the parallel architectures are demonstrated and classified according to how the computing units are connected to a memory model. Two parallel systems are classified to the shared and distributed platforms. Depending on these two types, we are categorized the parallel programming models. The parallel iterative methods are explained and its two types, the synchronous and asynchronous iterative methods, are described. The synchronous iterative methods are well implemented over local homogeneous cluster with a high speed network link, while the asynchronous iterative methods are more conventional to implement over the distributed heterogeneous clusters.
-Consequently, running these two types of the parallel iterative methods over distributed platforms is interested in this work. The energy consumption model for measuring the energy consumption of the parallel applications from the literature is described. This model cannot be used for all types of parallel architectures. The energy model is assumed to measure the dynamic power during both communication and computation times, while the processor involved remains idle during the communications time and only consumes static power. Moreover, it is not well adapted to the heterogeneous architectures.
+In this chapter, we have presented in general different types of parallelism levels that can be implemented in a software and hardware techniques. Furthermore, the types of the parallel architectures are demonstrated and classified according to how the computing units are connected to a memory model.
+The two parallel systems are described, which are the shared and distributed platforms. Depending on these two types, we have categorized the parallel programming models. The parallel iterative methods are explained and their two types, the synchronous and asynchronous iterative methods, are described. The synchronous iterative methods are well implemented over local homogeneous cluster with a high speed network link, while the asynchronous iterative methods are more conventional to implement over the distributed heterogeneous clusters.
+Consequently, running these two types of the parallel iterative methods over distributed platforms are interested in this work. The energy consumption model for measuring the energy consumption of the parallel applications from the related literature is described. This model cannot be used for all types of parallel architectures. The energy model is assumed to measure the dynamic power during both communication and computation times, while the processor involved remains idle during the communications time and only consumes static power. Moreover, it is not well adapted to the heterogeneous architectures.
However, in the coming chapters of this thesis a new energy consumption models are developed, use for modeling and measuring the energies consumed by a parallel iterative methods running on both homogeneous and heterogeneous architectures.
