@TechReport{	  it:2004-006,
  author	= {Henrik L{\"o}f and Markus Nord{\'e}n and Sverker Holmgren},
  title		= {Improving Geographical Locality of Data for Shared Memory
		  Implementations of {PDE} Solvers},
  institution	= {Department of Information Technology, Uppsala University},
  department	= {Division of Scientific Computing},
  year		= {2004},
  number	= {2004-006},
  month		= feb,
  abstract	= {On cc-NUMA multi-processors, the non-uniformity of main
		  memory latencies motivates the need for co-location of
		  threads and data. We call this special form of data
		  locality, \emph{geographical locality}, as the
		  non-uniformity is a consequence of the physical distance
		  between the cc-NUMA nodes. In this article, we compare the
		  well established method of exploiting the first-touch
		  strategy using parallel initialization of data to an
		  application-initiated page migration strategy as means of
		  increasing the geographical locality for a set of important
		  scientific applications.
		  
		  Four PDE solvers parallelized using OpenMP are studied; two
		  standard NAS NPB3.0-OMP benchmarks and two kernels from
		  industrial applications. The solvers employ both structured
		  and unstructured computational grids. The main conclusions
		  of the study are: (1) that geographical locality is
		  important for the performance of the applications, (2) that
		  application-initiated migration outperforms the first-touch
		  scheme in almost all cases, and in some cases even results
		  in performance which is close to what is obtained if all
		  threads and data are allocated on a single node. We also
		  suggest that such an application-initiated migration could
		  be made fully transparent by letting the OpenMP compiler
		  invoke it automatically.}
}