Proceedings Article10.1109/ICMTCE.2011.5915546
Accelerating FDTD algorithm using GPU computing
Zhang Bo,Xue Zheng-hui,Ren Wu,Li Wei-ming,Sheng Xin-qing +4 more
- 22 May 2011
- pp 410-413
24
TL;DR: This essay proposed a GPU FDTD programming model that is both efficient and accurate and simulated two projects, showing good agreement with CPU computing while simulation speedup is 20 at minimum, thus proves the efficiency and great potential of GPU accelerating in FDTD research.
read more
Abstract: Hardware acceleration of Finite-Difference Time-Domain (FDTD) algorithm has always been an important part of FDTD research. In this essay, we discussed the advantage and feasibility of accelerate FDTD algorithm using Graphics Processing Unit (GPU). With the implement of lattice-threads mapping and other techniques, we proposed a GPU FDTD programming model that is both efficient and accurate. Then we simulated two projects using proposed model, the result shows good agreement with CPU computing while simulation speedup is 20 at minimum, thus proves the efficiency and great potential of GPU accelerating in FDTD research.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Free-form optimization of nanophotonic devices: from classical methods to deep learning
Juho Park,Sanmun Kim,Daniel W Nam,Haejun Chung,Chan Y. Park,Min Seok Jang +5 more
TL;DR: Free-form nanophotonics: Free-form design schemes for photonic devices have been widely discussed in the literature as discussed by the authors , with a focus on free-form optimization of nanophotonic devices.
Cooperative Computing Techniques for a Deeply Fused and Heterogeneous Many-Core Processor Architecture
TL;DR: The DFMC processor can alleviate the memory wall problem by combining a series of cooperative computing techniques of CPEs, such as multi-pattern data stream transfer, efficient register-level communication mechanism, and fast hardware synchronization technique, to improve on-chip data reuse and optimize memory access performance.
50
Compact printable chipless RFID tags using polarization diversity
Md. Aminul Islam,Nemai Chandra Karmakar +1 more
- 01 Oct 2012
TL;DR: In this paper, two compact design concepts of fully printable slot-loaded chip less RFID tags are presented, which can be used in banknotes, ID cards, and also can be directly printed on the packets for item-level tagging.
16
Light scattering microscopy measurements of single nuclei compared with GPU-accelerated FDTD simulations.
TL;DR: It is shown that even for a qualitative comparison of experimental and theoretical data, the standard Mie model of a homogeneous sphere proves to be insufficient and an accelerated finite-difference time-domain method was implemented to analyze the experimental scattering patterns.
10
References
•Book
Computational Electrodynamics: The Finite-Difference Time-Domain Method
Allen Taflove
- 31 May 1995
TL;DR: This paper presents background history of space-grid time-domain techniques for Maxwell's equations scaling to very large problem sizes defense applications dual-use electromagnetics technology, and the proposed three-dimensional Yee algorithm for solving these equations.
Acceleration of finite-difference time-domain (FDTD) using graphics processor units (GPU)
S.E. Krakiwsky,L.E. Turner,Michal Okoniewski +2 more
- 06 Jun 2004
TL;DR: It is demonstrated that standard consumer Graphics Processor Units (GPUs) can be used to accelerate FDTD simulations by a factor of over seven, relative to an Intel CPU of similar technology generation.
114
Acceleration of the 3D ADI-FDTD method using graphics processor units
Tomasz P. Stefanski,Timothy D. Drysdale +1 more
- 07 Jun 2009
TL;DR: A satisfactory speedup of the method is obtained, indicating that GPUs represent an inexpensive source of computational power for accelerated ADI-FDTD simulations.
31