From: couturie Date: Fri, 10 May 2013 11:39:05 +0000 (+0200) Subject: new X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/book_gpu.git/commitdiff_plain/8fd941eeeeccad914f5e2b833bc00c9d2401efd6?ds=sidebyside;hp=ac699bb490942cea02be7b088a0cfa4e0dcdd105 new --- diff --git a/BookGPU/Chapters/chapter1/ch1.tex b/BookGPU/Chapters/chapter1/ch1.tex index 6c3f1f1..17a7e47 100755 --- 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} diff --git a/BookGPU/Chapters/chapter12/ch12.tex b/BookGPU/Chapters/chapter12/ch12.tex index 7f97864..576a0cd 100755 --- a/BookGPU/Chapters/chapter12/ch12.tex +++ b/BookGPU/Chapters/chapter12/ch12.tex @@ -5,9 +5,9 @@ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %\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} diff --git a/BookGPU/Chapters/chapter2/ch2.tex b/BookGPU/Chapters/chapter2/ch2.tex index 2eba230..2f4f4ea 100755 --- 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} diff --git a/BookGPU/Chapters/chapter3/ch3.aux b/BookGPU/Chapters/chapter3/ch3.aux index 58d4a58..0f932fd 100644 --- 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}{\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{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}} @@ -127,7 +127,7 @@ \setcounter{subparagraph}{0} \setcounter{figure}{11} \setcounter{table}{3} -\setcounter{numauthors}{1} +\setcounter{numauthors}{0} \setcounter{parentequation}{0} \setcounter{subfigure}{0} \setcounter{lofdepth}{1} diff --git a/BookGPU/Chapters/chapter3/ch3.tex b/BookGPU/Chapters/chapter3/ch3.tex index 1a991e2..8cd1767 100755 --- 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/}} @@ -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. +\chapterauthor{Gilles Perrot}{Femto-ST Institute, University of Franche-Comte, France} + \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. diff --git a/BookGPU/Chapters/chapter4/ch4.tex b/BookGPU/Chapters/chapter4/ch4.tex index d618753..e3dbfd5 100644 --- 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}} @@ -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, -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 diff --git a/BookGPU/sunil.cls b/BookGPU/sunil.cls index bc2fad6..754c025 100755 --- a/BookGPU/sunil.cls +++ b/BookGPU/sunil.cls @@ -1407,7 +1407,7 @@ \@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