new

[kahina_paper2.git] / maj.tex

diff --git a/maj.tex b/maj.tex
index c9e308ca13e0d7b95a43c3ea340ceee05e433d87..d218adb20e02b64ae224564b4d7cd4d964721a95 100644 (file)
--- a/maj.tex
+++ b/maj.tex
@@ -9,7 +9,8 @@
 \usepackage[textsize=footnotesize]{todonotes}
 \usepackage{amsmath}
 \usepackage{amssymb}
 \usepackage[textsize=footnotesize]{todonotes}
 \usepackage{amsmath}
 \usepackage{amssymb}

-\usepackage{float} 
+\usepackage{float}
+\usepackage{listings}

 \newcommand{\LZK}[2][inline]{%
   \todo[color=red!10,#1]{\sffamily\textbf{LZK:} #2}\xspace}
 \newcommand{\RC}[2][inline]{%
 \newcommand{\LZK}[2][inline]{%
   \todo[color=red!10,#1]{\sffamily\textbf{LZK:} #2}\xspace}
 \newcommand{\RC}[2][inline]{%


@@ -326,13 +327,22 @@ Copy $P$, $P'$ and $Z$ from CPU to GPU\;
 Copy $Z$ from GPU to CPU\;
 \end{algorithm}
 
 Copy $Z$ from GPU to CPU\;
 \end{algorithm}
 

-\RC{A revoir (c'est de la blague en l'état) : Figure~\ref{fig:00} shows the second kernel code}
-\begin{figure}[htbp]
-\centering
-\includegraphics[angle=+0,width=0.4\textwidth]{code1}
-\caption{The Kernel Update code}
-\label{fig:00}
-\end{figure}
+Listing~\ref{lst:01} shows the a simplified version of second kernel
+code (some parameters in the kernels have been simplified in order to
+increase the readability). As can be seen this
+kernel calls multiple kernels, all the kernels for complex numbers and
+kernels for the evaluation of a polynomial are not detailed. 
+
+\begin{footnotesize}
+\lstinputlisting[label=lst:01,caption=Kernels to update the roots]{code.c}
+\end{footnotesize}
+
+%\begin{figure}[htbp]
+%\centering
+%\includegraphics[angle=+0,width=0.4\textwidth]{code}
+%\caption{The Kernel Update code}
+%\label{fig:00}
+%\end{figure}

 
 %We noticed that the code is executed by a large number of GPU threads organized as grid of to dimension (Number of block per grid (NbBlock), number of threads per block(Nbthread)), the Nbthread is fixed initially, the NbBlock is computed as fallow: 
 %$ NbBlocks= \frac{N+Nbthreads-1}{Nbthreads} where N: the number of root$
 
 %We noticed that the code is executed by a large number of GPU threads organized as grid of to dimension (Number of block per grid (NbBlock), number of threads per block(Nbthread)), the Nbthread is fixed initially, the NbBlock is computed as fallow: 
 %$ NbBlocks= \frac{N+Nbthreads-1}{Nbthreads} where N: the number of root$