this is for holding javascript data
Xavier Andrade edited Parallelization.tex
over 9 years ago
Commit id: da721e83ee14ebcbec59acff38ca10583d673281
deletions | additions
diff --git a/Parallelization.tex b/Parallelization.tex
index 44ada09..73f2233 100644
--- a/Parallelization.tex
+++ b/Parallelization.tex
...
memory with the objective of using processor caches more efficiently
in finite-difference operators. We have found that by using space
filling curves~\cite{Peano_1890}, as shown in Fig.~\ref{fig:gridmaps},
in particular the Hilbert
curve~\cite{Hilbert_1891,Skilling2004} curve~\cite{Hilbert_1891,Skilling2004}, we can produce a significant improvement in the performance of semi-local operations. For
example example, in Fig.\ref{fig:gpu_laplacian} shows that a performance gain of around 50\% can be obtained for the finite-difference Laplacian operator running on a
GPU. GPU by using a Hilbert urve to map the grid into memory.