We optimize codes implementing Monte Carlo simulations of spin-glass systems for some multi-core CPU and GPU architectures. We consider both the binary Ising and floating-point Heisenberg spin-glass models in 3 dimensions. We provide performance figures for the Intel Nehalem quad-core and the IBM Cell/BE CPUs and the Nvidia Tesla C1060 GPU; for the binary model we also draw a comparison with the performance of dedicated computers, such as the Janus machine. © 2012 Springer-Verlag.
Monte Carlo simulations of spin systems on multi-core processors / Marco, Guidetti; Maiorano, Andrea; Filippo, Mantovani; Marcello, Pivanti; Sebastiano F., Schifano; Raffaele, Tripiccione. - 7133 LNCS:1(2012), pp. 220-230. (Intervento presentato al convegno 10th International Conference on Applied Parallel and Scientific Computing, PARA 2010 tenutosi a Reykjavik nel 6 June 2010 through 9 June 2010) [10.1007/978-3-642-28151-8_22].
Monte Carlo simulations of spin systems on multi-core processors
MAIORANO, Andrea;
2012
Abstract
We optimize codes implementing Monte Carlo simulations of spin-glass systems for some multi-core CPU and GPU architectures. We consider both the binary Ising and floating-point Heisenberg spin-glass models in 3 dimensions. We provide performance figures for the Intel Nehalem quad-core and the IBM Cell/BE CPUs and the Nvidia Tesla C1060 GPU; for the binary model we also draw a comparison with the performance of dedicated computers, such as the Janus machine. © 2012 Springer-Verlag.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.