X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/book_gpu.git/blobdiff_plain/11f93a2e8880680f6b192298e5ce0697d2596a31..refs/heads/master:/BookGPU/Chapters/chapter6/PartieSync.tex

diff --git a/BookGPU/Chapters/chapter6/PartieSync.tex b/BookGPU/Chapters/chapter6/PartieSync.tex
index bc08557..7fdaace 100755
--- a/BookGPU/Chapters/chapter6/PartieSync.tex
+++ b/BookGPU/Chapters/chapter6/PartieSync.tex
@@ -97,7 +97,7 @@ parallel programming schemes on a GPU cluster:
 Using CUDA\index{CUDA}, GPU kernel executions are nonblocking, and GPU/CPU data
 transfers\index{CUDA!data transfer}
 are blocking or nonblocking operations. All GPU kernel executions and CPU/GPU
-data transfers are associated to "streams,"\index{CUDA!stream} and all operations on a same stream
+data transfers are associated to ``streams'',\index{CUDA!stream} and all operations on a same stream
 are serialized. When transferring data from the CPU to the GPU, then running GPU
 computations, and finally transferring results from the GPU to the CPU, there is
 a natural synchronization and serialization if these operations are achieved on
@@ -210,7 +210,7 @@ achieved serially and not overlapped.
 
 When CPU/GPU data transfers are not negligible compared to GPU computations, it
 can be interesting to overlap internode CPU computations with a \emph{GPU
-  sequence}\index{GPU sequence} including CPU/GPU data transfers and GPU computations (see
+  sequence}\index{GPU!sequence} including CPU/GPU data transfers and GPU computations (see
 \Fig{fig:ch6p1overlapseqsequence}). Algorithmic issues of this approach are basic,
 but their implementation requires explicit CPU multithreading and
 synchronization, and CPU data buffer duplication. We need to implement two
@@ -367,7 +367,7 @@ of the code.
 
 \Lst{algo:ch6p1overlapstreamsequence} introduces the generic MPI+OpenMP+CUDA
 code,  explicitly overlapping MPI communications with
-streamed GPU sequences\index{GPU sequence!streamed}.
+streamed GPU sequences\index{GPU!streamed sequence}.
 
 %\begin{algorithm}
 %  \caption{Generic scheme explicitly overlapping MPI communications with streamed sequences of CUDA
@@ -489,7 +489,7 @@ working on  independent subsets of  data.  \Lst{algo:ch6p1overlapstreamsequence}
 is not so generic as \Lst{algo:ch6p1overlapseqsequence}.
 
 
-\subsection{Interleaved communications-transfers-computations\\overlapping}
+\subsection{Interleaved communications-transfers-computations overlapping}
 
 Many algorithms do not support splitting data transfers and kernel calls, and
 cannot exploit CUDA streams, for example, when each GPU thread requires access to
@@ -506,7 +506,8 @@ and twice as many GPU buffers.
 \begin{figure}[t]
   \centering
   \includegraphics{Chapters/chapter6/figures/Sync-CompleteInterleaveOverlap.pdf}
-  \caption{Complete overlap of internode CPU communications, CPU/GPU data transfers, and GPU
+  \caption[Complete overlap of internode CPU communications,\break\hfill CPU/GPU data transfers, and GPU
+  computations, interleaving computation-communication iterations.]{Complete overlap of internode CPU communications, CPU/GPU data transfers, and GPU
   computations, interleaving computation-communication iterations.}
   \label{fig:ch6p1overlapinterleaved}
 \end{figure}