new

[book_gpu.git] / BookGPU / Chapters / chapter9 / ch9.tex

diff --git a/BookGPU/Chapters/chapter9/ch9.tex b/BookGPU/Chapters/chapter9/ch9.tex
index 0fe38c4b794d7104273995088ebf7320c1d3132f..442c53a03ba02139a8b7ac7f8c68b084c9723823 100644 (file)
--- a/BookGPU/Chapters/chapter9/ch9.tex
+++ b/BookGPU/Chapters/chapter9/ch9.tex
@@ -99,7 +99,7 @@ solutions. The process is repeated until a stopping criterion is
 satisfied. \emph{Evolutionary algorithms}, \emph{swarm
 optimization}, and \emph{ant colonies} fall into this class.
 
 satisfied. \emph{Evolutionary algorithms}, \emph{swarm
 optimization}, and \emph{ant colonies} fall into this class.
 

-
+%\clearpage

 \section{Parallel models for metaheuristics}\label{ch8:sec:paraMeta}
 Optimization problems, whether real-life or academic, are more
 often NP-hard and CPU time and/or memory consuming. Metaheuristics
 \section{Parallel models for metaheuristics}\label{ch8:sec:paraMeta}
 Optimization problems, whether real-life or academic, are more
 often NP-hard and CPU time and/or memory consuming. Metaheuristics


@@ -187,8 +187,8 @@ consuming. Unlike the two previous parallel models, the
 solution-level\index{metaheuristics!solution-level parallelism}
 parallel model is problem-dependent.}
 \end{itemize}
 solution-level\index{metaheuristics!solution-level parallelism}
 parallel model is problem-dependent.}
 \end{itemize}

-\clearpage
-\section{Challenges for the design of GPU-based metaheuristics}
+%\clearpage
+\section[Challenges for the design of GPU-based  metaheuristics]{Challenges for the design of GPU-based\hfill\break  metaheuristics}

 \label{ch8:sec:challenges}
 
 Developing GPU-based parallel
 \label{ch8:sec:challenges}
 
 Developing GPU-based parallel


@@ -251,7 +251,7 @@ data (e.g., data for fitness evaluation that all threads
 concurrently access) on the constant memory, and the most accessed
 data structures (e.g., population of individuals for a CUDA thread
 block) on the shared memory.
 concurrently access) on the constant memory, and the most accessed
 data structures (e.g., population of individuals for a CUDA thread
 block) on the shared memory.

-
+\clearpage

 \subsection{Threads synchronization}
 \index{GPU!threads synchronization} The thread
 synchronization issue is caused by both the GPU architecture and
 \subsection{Threads synchronization}
 \index{GPU!threads synchronization} The thread
 synchronization issue is caused by both the GPU architecture and


@@ -501,7 +501,7 @@ QAPLIB~\cite{burkard1991qaplib}. Speedups up to $10 \times$ are
 achieved by the GPU implementation compared
 to the same sequential implementation on CPU using SA-matrix.
 
 achieved by the GPU implementation compared
 to the same sequential implementation on CPU using SA-matrix.
 

-\subsection[Implementing population-based metaheuristics\hfill\break on GPUs]{Implementing population-based metaheuristics on GPUs}
+\subsection[Implementing population-based metaheuristics on GPUs]{Implementing population-based metaheuristics on GPUs}

 
 State-of-the-art works dealing with the implementation of
 p-metaheuristics on GPUs generally rely on parallel models and
 
 State-of-the-art works dealing with the implementation of
 p-metaheuristics on GPUs generally rely on parallel models and