Acceleration of large-scale FDTD simulations on high performance GPU clusters

Acceleware's GPU cluster solution offers many features, enabling realistic large-scale simulations up to 3 GCells in size, with performance throughput of up to 13 GCells/s. FDTD computations on Acceleware's G80 GPU cluster are 25 to 29 times faster than equivalent node count CPU implementation. The GPU cluster achieves scaling efficiency of 80 % for 4-node and 60 % for 16-node configurations.

[1]  M.M. Okoniewski,et al.  Acceleration of finite-difference time-domain (FDTD) using graphics processor units (GPU) , 2004, 2004 IEEE MTT-S International Microwave Symposium Digest (IEEE Cat. No.04CH37535).

[2]  Arie E. Kaufman,et al.  GPU Cluster for High Performance Computing , 2004, Proceedings of the ACM/IEEE SC2004 Conference.

[3]  M. Mrozowski,et al.  Optimization of a FDTD code for graphical processing units , 2008, MIKON 2008 - 17th International Conference on Microwaves, Radar and Wireless Communications.