new

diff --git a/BookGPU/Chapters/chapter10/ch10.tex b/BookGPU/Chapters/chapter10/ch10.tex
index c481bc415d9ccf0ba871159ab67c8b79298153c5..0c6a8bb82714713d56d4a48bd88cea13db313a6a 100644 (file)
--- a/BookGPU/Chapters/chapter10/ch10.tex
+++ b/BookGPU/Chapters/chapter10/ch10.tex
@@ -449,7 +449,7 @@ An optimized way of doing the reduction can be found in the examples\footnote{Av
 \begin{figure}[!h]
 \centering
 \includegraphics[width=10cm]{Chapters/chapter10/figures/Reduc3.pdf}
 \begin{figure}[!h]
 \centering
 \includegraphics[width=10cm]{Chapters/chapter10/figures/Reduc3.pdf}

-\caption{Example of a parallel reduction at block level (courtesy NVIDIA).}
+\caption{Example of a parallel reduction at block level. (Courtesy NVIDIA).}

 \label{chXXX:fig:reduc}
 \end{figure}
 
 \label{chXXX:fig:reduc}
 \end{figure}
 

diff --git a/BookGPU/Chapters/chapter19/ch19.tex b/BookGPU/Chapters/chapter19/ch19.tex
index 307b85158369587435bc683f010da49784ce500d..d0d59cd95e006d390e1b714d6d7db9ff1776b8e1 100755 (executable)
--- a/BookGPU/Chapters/chapter19/ch19.tex
+++ b/BookGPU/Chapters/chapter19/ch19.tex
@@ -130,7 +130,8 @@ For each nonzero, both its column and row indices are explicitly stored. The Cus
                                        *, *, *, 10, *,  *}
        \end{lstlisting}
 
                                        *, *, *, 10, *,  *}
        \end{lstlisting}
 

-       \subsubsection*{Hybrid (HYB)\index{compressed storage format!HYB}} The HYB format heuristically computes a value $K$ and stores $K$ nonzeros per rows in the ELL format. When a row has more than $K$ non-zeros, the trailing nonzeros are stored in COO. This design decreases the storage overhead due to ELL padding elements and thus improves the overall performance.
+       \subsubsection*{Hybrid (HYB)\index{compressed storage format!HYB}} The HYB format heuristically computes a value $K$ and stores $K$ nonzeros per rows in the ELL format. When a row has more than $K$ non zeros, the trailing nonzeros are stored in COO. This design decreases the storage overhead due to ELL padding elements and thus improves the overall performance.
+\pagebreak

        \begin{lstlisting}[caption={}]
        hyb.nnz_per_row   = 2
        hyb.ell.col_index = {2, 1, 1, 0, 2, 0, *, 4, 3, 2, *,  5}
        \begin{lstlisting}[caption={}]
        hyb.nnz_per_row   = 2
        hyb.ell.col_index = {2, 1, 1, 0, 2, 0, *, 4, 3, 2, *,  5}


@@ -203,7 +204,7 @@ As a preprocessing step, we reorder the rows of the matrix by their \emph{row we
        \begin{figure}[t]
        \centering
        \includegraphics[height=5cm]{Chapters/chapter19/fig/scoo.pdf} 
        \begin{figure}[t]
        \centering
        \includegraphics[height=5cm]{Chapters/chapter19/fig/scoo.pdf} 

-       \caption{Example of the memory access pattern for a $6 \times 6$ matrix stored in Sliced COO format (Slice Size = 3 rows).}
+       \caption{Example of the memory access pattern for a $6 \times 6$ matrix stored in sliced COO format (slice size = 3 rows).}

        \label{fig:scoo-1}
        \end{figure}
        
        \label{fig:scoo-1}
        \end{figure}
        


@@ -302,7 +303,7 @@ Max Memory bandwidth (GB/s)& 144 & 192 & 21 \\
 \hline
 \end{tabular}
 \end{center}
 \hline
 \end{tabular}
 \end{center}

-\caption{Overview of hardware used in the experiments}
+\caption{Overview of hardware used in the experiments.}

 \label{table:hardware}
 \end{table} 
 
 \label{table:hardware}
 \end{table} 
 


@@ -329,7 +330,7 @@ The speedups compared to the multithreaded CADO-NFS bucket implementation on an
 
        \hline
        \end{tabular}
 
        \hline
        \end{tabular}

-       \caption{Performance of SpMV on RSA-170 matrix}
+       \caption{Performance of SpMV on RSA-170 matrix.}

        \label{table:rsa170}
 \end{table}
                        
        \label{table:rsa170}
 \end{table}