Improving Geographical Locality of Data for Shared Memory Implementations of PDE Solvers

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, 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 rst-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 scientic 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 rsttouch scheme in almost all cases,...

• Type: Conference
• Year: 2004
• Where: ICCS
• Authors: Henrik Löf, Markus Nordén, Sverker Holmgren
• Keywords: Data Locality, Geographical Locality, ICCS 2004, Main Memory Latencies