@inbook{43aec89be3cb459f8086dda9d6a57b60,
title = "A performance model for openMP memory bound applications in multisocket systems",
abstract = "The performance of OpenMP applications executed in multisocket multicore processors can be limited by the memory interface. In a multisocket environment, each multicore processor can present a performance degradation in memory-bound parallel regions when sharing the same Last Level Cache (LLC). We propose a characterization of the performance of parallel regions to estimate cache misses and execution time. This model is used to select the number of threads and affinity distribution for each parallel region. The model is applied for SP and MG benchmarks from the NAS Parallel Benchmark Suite using different workloads on two different multicore, multisocket systems. The results shown that the estimation preserves the behavior shown in measured executions for the affinity configurations evaluated. Estimated execution time is used to select a set of configurations in order to minimize the impact of memory contention, achieving significant improvements compared with a default configuration using all threads.",
keywords = "Memory bound applications, Multicore, Multisocket, OpenMP, Performance model",
author = "C{\'e}sar Allande and Josep Jorba and Anna Sikora and Eduardo C{\'e}sar",
note = "Funding Information: This research has been supported by the MICINN-Spain under contract TIN2011-28689. The authors thankfully acknowledge the resources and technical assistance provided by Munich Network Management Team (MNM-Team) and the Leibniz Supercomputing Centre.",
year = "2014",
month = may,
day = "1",
doi = "10.1016/j.procs.2014.05.206",
language = "English",
isbn = "978-1-4799-5833-7",
volume = "29",
series = "Procedia Computer Science",
publisher = "Elsevier",
pages = "2208--2218",
booktitle = "IEEE International conference on computational science 2014 (ICCS 2014)",
edition = "1",
}