X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/book_gpu.git/blobdiff_plain/1874c46934f4ba7e8c2013d3829f65309456d292..b231a0489d9378f3ea1c2014902e9e55966907ff:/BookGPU/Chapters/chapter4/ch4.tex

diff --git a/BookGPU/Chapters/chapter4/ch4.tex b/BookGPU/Chapters/chapter4/ch4.tex
index 805de25..ed3f531 100644
--- a/BookGPU/Chapters/chapter4/ch4.tex
+++ b/BookGPU/Chapters/chapter4/ch4.tex
@@ -20,7 +20,7 @@ to $I$ as an $H\times L$ pixel gray-level image and to $I(x,y)$ as the gray-leve
 value of each pixel of coordinates $(x,y)$.
 
 
-
+\clearpage
 \section{Definition}
 Within a digital image $I$, the convolution operation is performed between
 image $I$ and convolution mask \emph{h} (To avoid confusion with other
@@ -113,7 +113,7 @@ $\mathbf{2048\times 2048}$&1.178&1549 &\bf 3.265&\bf 875 &6.398&529 \\\hline
 $\mathbf{4096\times 4096}$&4.700&1585 &13.05&533     &25.56&533 \\\hline
 \end{tabular}
 }  
-\caption[Timings (time) and throughput values (TP in MP/s) of one register-only non-separable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a C2070 card.]{Timings (time) and throughput values (TP in MPx/s) of one register-only non-separable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a C2070 card (fermi architecture). Data transfer duration are those of Table \ref{tab:memcpy1}. The bold value points out the result obtained in the reference situation.}
+\caption[Timings (time) and throughput values (TP in MP/s) of one register-only nonseparable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a C2070 card.]{Timings (time) and throughput values (TP in MPx/s) of one register-only nonseparable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a C2070 card (fermi architecture). Data transfer duration are those of Table \ref{tab:memcpy1}. The bold value points out the result obtained in the reference situation.}
 \label{tab:convoNonSepReg1}
 \end{table} 
 
@@ -142,7 +142,7 @@ $\mathbf{2048\times 2048}$&0.801&1092 &\bf 2.189&\bf 802 &4.278&573 \\\hline
 $\mathbf{4096\times 4096}$&3.171&1075 &8.720&793 &17.076&569 \\\hline
 \end{tabular}
 }  
-\caption[Timings (time) and throughput values (TP in MP/s) of one register-only non-separable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a GTX280.]{Timings (time) and throughput values (TP in MP/s) of one register-only non-separable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a GTX280 (GT200 architecture). Data transfer duration are those of Table \ref{tab:memcpy1}. The bold value points out the result obtained in the reference situation.}
+\caption[Timings (time) and throughput values (TP in MP/s) of one register-only nonseparable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a GTX280.]{Timings (time) and throughput values (TP in MP/s) of one register-only nonseparable convolution kernel, for small mask sizes of $3\times 3$, $5\times 5$, and $7\times 7$ pixels, on a GTX280 (GT200 architecture). Data transfer duration are those of Table \ref{tab:memcpy1}. The bold value points out the result obtained in the reference situation.}
 \label{tab:convoNonSepReg3}
 \end{table}
 
@@ -240,7 +240,7 @@ However, our technique requires writing one kernel per mask size, which can be s
 \lstinputlisting[label={lst:convoGene8x8pL3},caption=CUDA kernel achieving a $3\times 3$ convolution operation with the mask in symbol memory and direct data fetches in texture memory]{Chapters/chapter4/code/convoGene8x8pL3.cu}
 
 \subsection{Using shared memory to store prefetched data\index{prefetching}.}
- \index{memory~hierarchy!shared~memory}
+ \index{memory hierarchy!shared memory}
 A more convenient way of coding a convolution kernel is to use shared memory to perform a prefetching stage of the whole halo before computing the convolution sums.
 This proves to be quite efficient and more versatile, but it obviously generates some overhead because 
 \begin{itemize}