new

diff --git a/BookGPU/Chapters/chapter1/ch1.tex b/BookGPU/Chapters/chapter1/ch1.tex
index 6c3f1f1e6d67448a79c761f2d84bbe7905011f81..17a7e47f0c17a2b0df4c6d1f0b58f3f385112af9 100755 (executable)
--- a/BookGPU/Chapters/chapter1/ch1.tex
+++ b/BookGPU/Chapters/chapter1/ch1.tex
@@ -1,4 +1,4 @@
-\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte}
+\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte, France}

 
 
 \chapter{Presentation of the GPU architecture and of the Cuda environment}
 
 
 \chapter{Presentation of the GPU architecture and of the Cuda environment}

diff --git a/BookGPU/Chapters/chapter12/ch12.tex b/BookGPU/Chapters/chapter12/ch12.tex
index 7f97864a3b099bc85aca77cafca8c5fb2269040f..576a0cd5e5c4abfc64fc61f57c0112a7e7c1bf53 100755 (executable)
--- a/BookGPU/Chapters/chapter12/ch12.tex
+++ b/BookGPU/Chapters/chapter12/ch12.tex
@@ -5,9 +5,9 @@
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  
 %\chapterauthor{}{}
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  
 %\chapterauthor{}{}

-\chapterauthor{Lilia Ziane Khodja}{Femto-ST Institute, University of Franche-Comte, France}
-\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte, France}
-\chapterauthor{Jacques Bahi}{Femto-ST Institute, University of Franche-Comte, France}
+\chapterauthor{Lilia Ziane Khodja, Raphaël Couturier and Jacques Bahi}{Femto-ST Institute, University of Franche-Comte, France}
+%\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte, France}
+%\chapterauthor{Jacques Bahi}{Femto-ST Institute, University of Franche-Comte, France}

 
 \chapter[Solving linear systems with GMRES and CG methods on GPU clusters]{Solving sparse linear systems with GMRES and CG methods on GPU clusters}
 \label{ch12}
 
 \chapter[Solving linear systems with GMRES and CG methods on GPU clusters]{Solving sparse linear systems with GMRES and CG methods on GPU clusters}
 \label{ch12}

diff --git a/BookGPU/Chapters/chapter2/ch2.tex b/BookGPU/Chapters/chapter2/ch2.tex
index 2eba2307a6f3e0b7583b495fa33811c998faa92a..2f4f4eab09c00c7438ded1a86bf74fe947587f5a 100755 (executable)
--- a/BookGPU/Chapters/chapter2/ch2.tex
+++ b/BookGPU/Chapters/chapter2/ch2.tex
@@ -1,4 +1,4 @@
-\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte}
+\chapterauthor{Raphaël Couturier}{Femto-ST Institute, University of Franche-Comte, France}

 
 \chapter{Introduction to Cuda}
 \label{chapter2}
 
 \chapter{Introduction to Cuda}
 \label{chapter2}

diff --git a/BookGPU/Chapters/chapter3/ch3.aux b/BookGPU/Chapters/chapter3/ch3.aux
index 58d4a58bbd7b15bd78647ee1500ef873b79961aa..0f932fdccbcc4dfa0ef957ff2c074c8a0e475d3f 100644 (file)
--- a/BookGPU/Chapters/chapter3/ch3.aux
+++ b/BookGPU/Chapters/chapter3/ch3.aux
@@ -19,11 +19,11 @@
 \@writefile{toc}{\contentsline {section}{\numberline {3.2}Performance measurements}{28}}
 \newlabel{lst:chronos}{{3.4}{28}}
 \@writefile{lol}{\contentsline {lstlisting}{\numberline {3.4}Time measurement technique using cutil functions}{28}}
 \@writefile{toc}{\contentsline {section}{\numberline {3.2}Performance measurements}{28}}
 \newlabel{lst:chronos}{{3.4}{28}}
 \@writefile{lol}{\contentsline {lstlisting}{\numberline {3.4}Time measurement technique using cutil functions}{28}}

+\@writefile{toc}{\author{Gilles Perrot}{}}

 \@writefile{loa}{\addvspace {10\p@ }}
 \@writefile{toc}{\contentsline {chapter}{\numberline {4}Implementing a fast median filter}{31}}
 \@writefile{lof}{\addvspace {10\p@ }}
 \@writefile{lot}{\addvspace {10\p@ }}
 \@writefile{loa}{\addvspace {10\p@ }}
 \@writefile{toc}{\contentsline {chapter}{\numberline {4}Implementing a fast median filter}{31}}
 \@writefile{lof}{\addvspace {10\p@ }}
 \@writefile{lot}{\addvspace {10\p@ }}

-\@writefile{toc}{\author{Gilles Perrot}{}}

 \@writefile{toc}{\contentsline {section}{\numberline {4.1}Introduction}{31}}
 \@writefile{toc}{\contentsline {section}{\numberline {4.2}Median filtering}{32}}
 \@writefile{toc}{\contentsline {subsection}{\numberline {4.2.1}Basic principles}{32}}
 \@writefile{toc}{\contentsline {section}{\numberline {4.1}Introduction}{31}}
 \@writefile{toc}{\contentsline {section}{\numberline {4.2}Median filtering}{32}}
 \@writefile{toc}{\contentsline {subsection}{\numberline {4.2.1}Basic principles}{32}}


@@ -127,7 +127,7 @@
 \setcounter{subparagraph}{0}
 \setcounter{figure}{11}
 \setcounter{table}{3}
 \setcounter{subparagraph}{0}
 \setcounter{figure}{11}
 \setcounter{table}{3}

-\setcounter{numauthors}{1}
+\setcounter{numauthors}{0}

 \setcounter{parentequation}{0}
 \setcounter{subfigure}{0}
 \setcounter{lofdepth}{1}
 \setcounter{parentequation}{0}
 \setcounter{subfigure}{0}
 \setcounter{lofdepth}{1}

diff --git a/BookGPU/Chapters/chapter3/ch3.tex b/BookGPU/Chapters/chapter3/ch3.tex
index 1a991e2623d26b7bc5ae70688fd204183814e75b..8cd1767cb12b39dd3edebf49319d4b7bdfe0af26 100755 (executable)
--- a/BookGPU/Chapters/chapter3/ch3.tex
+++ b/BookGPU/Chapters/chapter3/ch3.tex
@@ -1,4 +1,4 @@
-\chapterauthor{Gilles Perrot}{FEMTO-ST Institute}
+\chapterauthor{Gilles Perrot}{Femto-ST Institute, University of Franche-Comte, France}

 %\graphicspath{{img/}}
 
 
 %\graphicspath{{img/}}
 
 


@@ -181,8 +181,9 @@ Last, like many authors, we chose to use the pixel throughput value of each proc
 In order to estimate the potential for improvement of each kernel, a reference throughput measurement, involving identity kernel of Listing \ref{lst:fkern1}, was performed. As this kernel only fetches input values from texture memory and outputs them to global memory without doing any computation, it represents the smallest, thus fastest, possible process and is taken as the reference throughput value (100\%). The same measurement was performed on CPU, with a maximum effective pixel throughput of 130~Mpixel per second. On GPU, depending on grid parameters it amounts to 800~MPixels/s on GTX280 and 1300~Mpixels/s on C2070.
 
 
 In order to estimate the potential for improvement of each kernel, a reference throughput measurement, involving identity kernel of Listing \ref{lst:fkern1}, was performed. As this kernel only fetches input values from texture memory and outputs them to global memory without doing any computation, it represents the smallest, thus fastest, possible process and is taken as the reference throughput value (100\%). The same measurement was performed on CPU, with a maximum effective pixel throughput of 130~Mpixel per second. On GPU, depending on grid parameters it amounts to 800~MPixels/s on GTX280 and 1300~Mpixels/s on C2070.
 
 

+\chapterauthor{Gilles Perrot}{Femto-ST Institute, University of Franche-Comte, France}
+

 \chapter{Implementing a fast median filter}
 \chapter{Implementing a fast median filter}

-\chapterauthor{Gilles Perrot}{FEMTO-ST Institute}

 \section{Introduction}
 Median filtering is a well-known method used in a wide range of application frameworks as well as a standalone filter especially for \textit{salt and pepper} denoising. It is able to highly reduce power of noise without blurring edges too much.
 
 \section{Introduction}
 Median filtering is a well-known method used in a wide range of application frameworks as well as a standalone filter especially for \textit{salt and pepper} denoising. It is able to highly reduce power of noise without blurring edges too much.
 

diff --git a/BookGPU/Chapters/chapter4/ch4.tex b/BookGPU/Chapters/chapter4/ch4.tex
index d618753ae9b6fe8a1cf4ab2797c536c8d4bbff1f..e3dbfd5c1fd87fef6ae39c74c9f8bf86b8964b10 100644 (file)
--- a/BookGPU/Chapters/chapter4/ch4.tex
+++ b/BookGPU/Chapters/chapter4/ch4.tex
@@ -1,4 +1,7 @@
-\chapterauthor{Gilles Perrot}{FEMTO-ST Institute}
+\chapterauthor{Gilles Perrot}{Femto-ST Institute, University of Franche-Comte, France}
+
+\chapter{Implementing an efficient convolution operation on GPU}
+

 
 %\newcommand{\kl}{\includegraphics[scale=0.6]{Chapters/chapter4/img/kernLeft.png}~}
 %\newcommand{\kr}{\includegraphics[scale=0.6]{Chapters/chapter4/img/kernRight.png}}
 
 %\newcommand{\kl}{\includegraphics[scale=0.6]{Chapters/chapter4/img/kernLeft.png}~}
 %\newcommand{\kr}{\includegraphics[scale=0.6]{Chapters/chapter4/img/kernRight.png}}


@@ -29,10 +32,10 @@
 %%   }
 
 
 %%   }
 
 

-\chapter{Implementing an efficient convolution \index{Convolution} operation on GPU}
+

 \section{Overview}
 In this chapter, after dealing with GPU median filter implementations,
 \section{Overview}
 In this chapter, after dealing with GPU median filter implementations,

-we propose to explore how convolutions can be implemented on modern
+we propose to explore how convolutions\index{Convolution}  can be implemented on modern

 GPUs. Widely used in digital image processing filters, the \emph{convolution
 operation} basically consists in taking the sum of products of elements
 from two 2-D functions, letting one of the two functions move over
 GPUs. Widely used in digital image processing filters, the \emph{convolution
 operation} basically consists in taking the sum of products of elements
 from two 2-D functions, letting one of the two functions move over

diff --git a/BookGPU/sunil.cls b/BookGPU/sunil.cls
index bc2fad682d0ef57c2e214b199ef5e9cb0ada105c..754c02588d7f4ea7d37d4dad5f445db8beb18c1b 100755 (executable)
--- a/BookGPU/sunil.cls
+++ b/BookGPU/sunil.cls
@@ -1407,7 +1407,7 @@
     \@starttoc{lof}%
     \if@restonecol\twocolumn\fi
     }
     \@starttoc{lof}%
     \if@restonecol\twocolumn\fi
     }

-\newcommand*\l@figure{\@dottedtocline{1}{1.5em}{2.3em}}
+\newcommand*\l@figure{\@dottedtocline{1}{1.5em}{2.8em}}

 \newcommand\listoftables{%
     \if@twocolumn
       \@restonecoltrue\onecolumn
 \newcommand\listoftables{%
     \if@twocolumn
       \@restonecoltrue\onecolumn