From 0aa640af7dcb1e33350b4ade113575ce81bb0d81 Mon Sep 17 00:00:00 2001
From: Arnaud Giersch <arnaud.giersch@univ-fcomte.fr>
Date: Thu, 17 Apr 2014 10:56:46 +0200
Subject: [PATCH] Put floating figures and tables on top (IEEE style).

---
 hpcc.tex | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/hpcc.tex b/hpcc.tex
index 4322e6e..2c7d65d 100644
--- a/hpcc.tex
+++ b/hpcc.tex
@@ -179,7 +179,7 @@ convergence is generally greater than for the two former classes. But, and as de
 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 } 
@@ -269,7 +269,7 @@ Y_l = B_l - \displaystyle\sum_{\substack{m=1\\ m\neq l}}^{L}A_{lm}X_m
 \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]
@@ -310,7 +310,7 @@ clusters (lines $6$ and $7$ in Figure~\ref{algo:01}). The shared vector
 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.}
@@ -363,7 +363,7 @@ Table~\ref{tab.cluster.2x50} with a matrix size ranging from $N_x = N_y = N_z =
 62 \text{ to } 171$ elements or from $62^{3} = \np{238328}$ to $171^{3} =
 \np{5211000}$ entries.
 
-\begin{table}
+\begin{table}[!t]
   \centering
   \caption{2 clusters, each with 50 nodes}
   \label{tab.cluster.2x50}
@@ -388,7 +388,7 @@ clusters. In the same way as above, a judicious choice of key parameters has
 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, each with 33 nodes}
   \label{tab.cluster.3x33}
@@ -413,7 +413,7 @@ 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, each with 66 nodes}
   \label{tab.cluster.3x67}
-- 
2.39.5