We present a new implementation of the numerical integration of the classical, gravitational, N-body problem based on a high order Hermite's integration scheme with block time steps, with a direct evaluation of the particle-particle forces. The main innovation of this code (called HiGPUs) is its full parallelization, exploiting both OpenMP and MPI in the use of the multicore Central Processing Units as well as either Compute Unified Device Architecture (CUDA) or OpenCL for the hosted Graphic Processing Units. We tested both performance and accuracy of the code using up to 256 GPUs in the supercomputer IBM iDataPlex DX360M3 Linux Infiniband Cluster provided by the Italian supercomputing consortium CINECA, for values of N <= 8 millions. We were able to follow the evolution of a system of 8 million bodies for few crossing times, task previously unreached by direct summation codes. (c) 2012 Elsevier Inc. All rights reserved.
A fully parallel, high precision, N-body code running on hybrid computing platforms / CAPUZZO DOLCETTA, Roberto Angelo; Spera, Mario; Punzo, Davide. - In: JOURNAL OF COMPUTATIONAL PHYSICS. - ISSN 0021-9991. - STAMPA. - 236:(2013), pp. 580-593. [10.1016/j.jcp.2012.11.013]
A fully parallel, high precision, N-body code running on hybrid computing platforms
Roberto Angelo Capuzzo Dolcetta
Conceptualization
;Mario SperaSoftware
;Davide PunzoSoftware
2013
Abstract
We present a new implementation of the numerical integration of the classical, gravitational, N-body problem based on a high order Hermite's integration scheme with block time steps, with a direct evaluation of the particle-particle forces. The main innovation of this code (called HiGPUs) is its full parallelization, exploiting both OpenMP and MPI in the use of the multicore Central Processing Units as well as either Compute Unified Device Architecture (CUDA) or OpenCL for the hosted Graphic Processing Units. We tested both performance and accuracy of the code using up to 256 GPUs in the supercomputer IBM iDataPlex DX360M3 Linux Infiniband Cluster provided by the Italian supercomputing consortium CINECA, for values of N <= 8 millions. We were able to follow the evolution of a system of 8 million bodies for few crossing times, task previously unreached by direct summation codes. (c) 2012 Elsevier Inc. All rights reserved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
