In this work, a parallel adaptive algorithm for the computa- tion of a multidimensional integral on heterogeneous GPU and multicore based systems is described. Two dierent strategies have been combined together in the algorithm: a rst procedure is responsible for the load balancing among the threads on the multicore CPU and a second one is responsible for an ecient execution on the GPU of the computa- tional kernel. The performance is analyzed and experimental results on a system with a quad-core CPUs and two GPUs have been achieved.
A study on adaptive algorithms for numerical quadrature on heterogeneous GPU and multicore based systems / Laccetti, Giuliano; Lapegna, Marco; Mele, Valeria; Diego, Romano. - 8384:(2014), pp. 704-713. (Intervento presentato al convegno International Conference on Parallel Processing and Applied Mathematics tenutosi a 8-11 / 9 / 2013 nel Varsavia (Polonia)) [10.1007/978-3-642-55224-3_66].
A study on adaptive algorithms for numerical quadrature on heterogeneous GPU and multicore based systems
LACCETTI, GIULIANO;LAPEGNA, MARCO;MELE, VALERIA;
2014
Abstract
In this work, a parallel adaptive algorithm for the computa- tion of a multidimensional integral on heterogeneous GPU and multicore based systems is described. Two dierent strategies have been combined together in the algorithm: a rst procedure is responsible for the load balancing among the threads on the multicore CPU and a second one is responsible for an ecient execution on the GPU of the computa- tional kernel. The performance is analyzed and experimental results on a system with a quad-core CPUs and two GPUs have been achieved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
