Custom hardware implementation of the finite-difference time-domain (FDTD) method

Schneider, Ryan N.; Okoniewski, M.; Turner, L.E.

doi:10.1109/mwsym.2002.1011769

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hardware acceleration of FDTD has been successfully pursued in the past, using custom made hardware such as FPGAs [8]. What makes the case of GPU-based scientific computing particularly attractive is that graphics hardware is very fast, very cheap, and continues to be enriched at rates that outstrip those of general purpose CPUs and FPGAs.…”

Section: Introductionmentioning

confidence: 99%

Accelerated Implementation of the S-MRTD Technique Using Graphics Processor Units

Baron

Fiume

Sarris

2006

2006 IEEE MTT-S International Microwave Symposium Digest

View full text Add to dashboard Cite

Abstract-A Time-Domain electromagnetic modeling technique, namely a high-order Scaling Function based MRTD (S-MRTD), can be dramatically accelerated, through its implementation in commodity graphics hardware. This implementation is achieved by mapping the numerical operations of S-MRTD to graphics operations, optimally executed by a graphics card, along the lines of previous work in the area of general purpose computing in computer graphics. The sustained speed-ups achieved, for two-dimensional problems, reach a factor of 30, significantly higher than any speed-ups reported for FDTD so far.

show abstract

Section: Introductionmentioning

confidence: 99%