GPGPU FDTD : Output of data

General Purpose GPU (GPGPU) devices, also known as accelerators, are gaining popularity in the scientific community for use in High Performance Computing (HPC) environments for the accelerated execution of highly parallelised and vectorised software applications. This is due to the Single Instruction, Multiple Threads (SIMT) architecture of accelerator devices, which makes them more suitable than CPU devices for use with highly parallelised tasks, where the same operation is applied to a large amount of data. As a result of the highly parallelised operation, such software achieve faster execution speeds on accelerators than equivalent software on CPU devices.