Microwave Journal
www.microwavejournal.com/articles/15262-xstream-v-3-0-gpu-computing-technology

XStream® V 3.0 GPU Computing Technology

January 17, 2011


Utilizing the ability of the GPU (Graphics Processing Unit) in modern computer graphics cards to stream floating point calculations, Remcom’s XFdtd full wave 3D EM solver achieves extremely fast calculation speeds via the XStream® Hardware FDTD option.

The new Version 3.0 of XStream® Hardware FDTD is now based on the NVIDIA FX 5600 GPU with 1.5 GBytes of accelerated memory. Calculation speed is comparable to an efficiently balanced computer cluster with between 16 and 64 nodes depending on problem size.

There are three versions of XStream® V 3.0 available from Remcom:

XStream® V 3.0
Single GPU with 1.5 GB of GPU memory for up to 50 Million FDTD cells fully-accelerated

XStream® MicroCluster V 3.0
Two XStream® V 3.0 GPUs in a Quadro Plex 1000 chassis with its own power supply provides 3 GB of GPU memory for up to 100 Million FDTD cells fully-accelerated

XStream MiniCluster® V 3.0
Four XStream® V 3.0 GPUs in two Quadro Plex 1000 chassis with their own power supplies provides 6 GB of GPU memory for up to 200 Million FDTD Cells fully-accelerated