new

[book_gpu.git] / BookGPU / Chapters / chapter6 / PartieAsync.tex

diff --git a/BookGPU/Chapters/chapter6/PartieAsync.tex b/BookGPU/Chapters/chapter6/PartieAsync.tex
index 9edbe8dce065e6dc88be03de3a3c13f02f5b6547..1617ffb3c89cd2eee005f1f56be2fdca122d1981 100644 (file)
--- a/BookGPU/Chapters/chapter6/PartieAsync.tex
+++ b/BookGPU/Chapters/chapter6/PartieAsync.tex
@@ -139,7 +139,7 @@ communication libraries such as MPI are not systematically performed in parallel
 the computations~\cite{ChVCV13,Hoefler08a}.  So, the logical and classical way
 to implement such an overlap is to use three threads: one for
 computing, one for sending, and one for receiving. Moreover, since
 the computations~\cite{ChVCV13,Hoefler08a}.  So, the logical and classical way
 to implement such an overlap is to use three threads: one for
 computing, one for sending, and one for receiving. Moreover, since

-the communication is performed by threads, blocking synchronous communications\index{MPI!communication!blocking}\index{MPI!communication!synchronous}
+the communication is performed by threads, blocking synchronous communications\index{MPI!blocking}\index{MPI!synchronous}

 can be used without deteriorating the overall performance.
 
 In this basic version, the termination\index{termination} of the global process is performed
 can be used without deteriorating the overall performance.
 
 In this basic version, the termination\index{termination} of the global process is performed


@@ -621,7 +621,7 @@ execution. They are similar to the mechanism used for managing the end messages
 at the end of the entire process.  Line~23 directly updates the
 number of other nodes that are in local convergence by adding the
 received state of the source node. This is possible due to the encoding that is used to
 at the end of the entire process.  Line~23 directly updates the
 number of other nodes that are in local convergence by adding the
 received state of the source node. This is possible due to the encoding that is used to

-represent the local convergence (1) and the non convergence (0).
+represent the local convergence (1) and the nonconvergence (0).

 
 %\begin{algorithm}[H]
 %  \caption{Reception function in the synchronized scheme.}
 
 %\begin{algorithm}[H]
 %  \caption{Reception function in the synchronized scheme.}


@@ -648,7 +648,7 @@ while(!Finished){
       case tagState: // Management of local state messages
        // Actual reception of the message
        MPI_Recv(&recvdState, 1, MPI_CHAR, status.MPI_SOURCE, tagState, MPI_COMM_WORLD, &status); 
       case tagState: // Management of local state messages
        // Actual reception of the message
        MPI_Recv(&recvdState, 1, MPI_CHAR, status.MPI_SOURCE, tagState, MPI_COMM_WORLD, &status); 

-       // Updates of numbers of stabilized nodes and received state msgs 
+       // Updates of numbers of stabilized nodes and recvd state msgs 

        nbOtherCVs += recvdState;
        nbStateMsg++;
        // Unlocking of the computing thread when states of all other 
        nbOtherCVs += recvdState;
        nbStateMsg++;
        // Unlocking of the computing thread when states of all other 


@@ -1174,7 +1174,7 @@ account in  the main computations  when it is  relevant. So, the  Newton process
 should be  accelerated a little bit.
 
 We  compare the  performance obtained  with overlapped  Jacobian  updatings and
 should be  accelerated a little bit.
 
 We  compare the  performance obtained  with overlapped  Jacobian  updatings and

-non overlapped ones for several problem sizes (see~\Fig{fig:ch6p2aux}).
+nonoverlapped ones for several problem sizes (see~\Fig{fig:ch6p2aux}).

 \begin{figure}[h]
   \centering
   \includegraphics[width=.75\columnwidth]{Chapters/chapter6/curves/recouvs.pdf}
 \begin{figure}[h]
   \centering
   \includegraphics[width=.75\columnwidth]{Chapters/chapter6/curves/recouvs.pdf}