petites modifs

[loba-papers.git] / loba-besteffort / loba-besteffort.tex

diff --git a/loba-besteffort/loba-besteffort.tex b/loba-besteffort/loba-besteffort.tex
index 2d0f414fd365ec501a0ea2249e627a4454fde86f..e966c402212b5dcb376ca9744b12cc5b71073e20 100644 (file)
--- a/loba-besteffort/loba-besteffort.tex
+++ b/loba-besteffort/loba-besteffort.tex
@@ -653,7 +653,7 @@ With these constraints in mind, we defined the following metrics:
 \label{sec.results}
 
 In this section, the results for the different simulations will be presented,
 \label{sec.results}
 
 In this section, the results for the different simulations will be presented,

-and we'll try to explain our observations.
+and we will try to explain our observations.

 
 \subsubsection{Cluster vs grid platforms}
 
 
 \subsubsection{Cluster vs grid platforms}
 


@@ -727,20 +727,33 @@ allocated time, or because we simply decided not to run it.
 \subsubsection{The \besteffort{} strategy with the load initially on only one
   node}
 
 \subsubsection{The \besteffort{} strategy with the load initially on only one
   node}
 

-Before looking at the different variations, we'll first show that the plain
-\besteffort{} strategy is valuable, and may be as good as the \makhoul{}
-strategy.  On the graphs from the figure~\ref{fig.results1}, these strategies
-are respectively labeled ``b'' and ``a''.
+Before looking  at the different variations,  we will first show  that the plain
+\besteffort{}  strategy  is valuable,  and  may be  as  good  as the  \makhoul{}
+strategy.  On  the graphs  from the figure~\ref{fig.results1},  these strategies
+(with virtual load feature) are respectively labeled ``b'' and ``a''.

 
 

-twice faster on lines
-almost equivalent on torus
-worse on hcubes
+We  can  see  that  the  relative  performance of  these  strategies  is  mainly
+influenced by  the application topology.  It  is for the line  topology that the
+difference is the  more important.  In this case,  the \besteffort{} strategy is
+nearly twice as  fast as the \makhoul{} strategy.  This can  be explained by the
+fact that the \besteffort{} strategy tries to distribute the load faitly between
+all the nodes  and with the line topology,  it is easy to load  balance the load
+fairly.

 
 

--> interconnection
+On the contrary, for the hypercube topology, the \besteffort{} strategy performs
+worse than the \makhoul{} strategy. In this case, the \makhoul{} strategy which
+tries to give more load to few neighbors reaches the equilibrum faster.
+
+For the torus  topology, for which the  number of links is between  the line and
+the hypercube, the \makhoul{} strategy  is slightly better but the difference is
+more nuanced.
+
+Globally   the  number  of   interconnection  is   very  important.    The  more
+interconnection links there are, the  faster the \makhoul{} strategy is because
+it distributes quickly significant amount of load even if this is unfair between
+all the  neighbors.  In opposition,  the \besteffort{} strategy  distributes the
+load fairly so this strategy is better for low connected strategy.

 
 

-plus c'est connecté, moins bon est BE car à vouloir trop bien équilibrer
-localement, le processeurs se perturbent mutuellement.  Du coup, makhoul qui
-équilibre moins bien localement est moins perturbé par ces interférences.

 
 \subsubsection{With the virtual load extension with the load initially on only
   one node}
 
 \subsubsection{With the virtual load extension with the load initially on only
   one node}


@@ -763,6 +776,7 @@ Soit c'est équivalent, soit on gagne -> surtout quand les comms coutent cher et
 qu'il y a beaucoup de voisins.
 
 \subsubsection{The $k$ parameter}
 qu'il y a beaucoup de voisins.
 
 \subsubsection{The $k$ parameter}

+\label{results-k}

 
 Dans le cas où les comms coutent cher et ou BE se fait avoir, on peut ameliorer
 les perfs avec le param k.
 
 Dans le cas où les comms coutent cher et ou BE se fait avoir, on peut ameliorer
 les perfs avec le param k.


@@ -845,4 +859,6 @@ Mésocentre de calcul de Franche-Comté.
 % LocalWords:  SimGrid DASUD Comté asynchronism ji ik isend irecv Cortés et al
 % LocalWords:  chan ctrl fifo Makhoul GFlop xml pre FEMTO Makhoul's fca bdee
 % LocalWords:  cdde Contassot Vivier underlaid du de Maréchal Juin cedex calcul
 % LocalWords:  SimGrid DASUD Comté asynchronism ji ik isend irecv Cortés et al
 % LocalWords:  chan ctrl fifo Makhoul GFlop xml pre FEMTO Makhoul's fca bdee
 % LocalWords:  cdde Contassot Vivier underlaid du de Maréchal Juin cedex calcul

-% LocalWords:  biblio
+% LocalWords:  biblio Institut UMR Université UFC Centre Scientifique CNRS des
+% LocalWords:  École Nationale Supérieure Mécanique Microtechniques ENSMM UTBM
+% LocalWords:  Technologie Bahi