A GPU approach to FDTD for radio coverage prediction

Valcarce, Alvaro; Zhang, Jie

doi:10.1109/iccs.2008.4737450

Cited by 26 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such computations can run for a couple of hours to days on supercomputers [6], depending on the size and complexity of the grid size. Researchers have harnessed the capability of the GPGPUs massively parallel architecture and CUDA language extension to accelerate FDTD by several orders of magnitude greater than CPUs [7].…”

Section: Algorithm Typically Accelerated On Gpgpusmentioning

confidence: 99%

In Situ Power Analysis of General Purpose Graphical Processing Units

Shaikh

Gregoire

et al. 2011

2011 19th International Euromicro Conference on Parallel, Distributed and Network-Based Processing

View full text Add to dashboard Cite

In this paper, an in situ power analysis profiling over time for general purpose graphics processing units (GPGPU) is presented. Based on this method the power consumption of different modes of operations like data transfer between GPU and host CPU, basic single precision floating point arithmetic operations (addition, subtraction, multiplication) on the multiprocessor units and instructions for shared and global memory access can be measured. There is a factor of 2 difference in power dissipation between various instructions and mode of operations of the GPGPUs. These measurements provide data for an instruction based power estimation of GPU software. It turns out that the power profile over time also gives a good understanding on which section of the program is executed at a certain point in time. The experimental results have been derived from two GPU architectures, namely the GT200 and the GF100 architecture.

show abstract

Section: Algorithm Typically Accelerated On Gpgpusmentioning

confidence: 99%

In Situ Power Analysis of General Purpose Graphical Processing Units

Shaikh

Gregoire

et al. 2011

2011 19th International Euromicro Conference on Parallel, Distributed and Network-Based Processing

View full text Add to dashboard Cite

show abstract

“…This reason has stopped it from being more widely applied to urban coverage prediction. To overcome this issue, an approach has been recently proposed [10] that exploits the parallelizable characteristics of FDTD by implementing it on a GPU (Graphical Processing Unit) by means of the recently released CUDA (Compute Unified Device Architecture) from NVIDIA [11]. This implementation is aimed at 2D scenarios, being thus extremely suitable for flat or near-flat urban environments.…”

Section: Propagation Model For Femtocellsmentioning

confidence: 99%

Access methods to WiMAX femtocells: A downlink system-level case study

Liu

Valcarce

Liu

et al. 2008

2008 11th IEEE Singapore International Conference on Communication Systems

Self Cite

View full text Add to dashboard Cite

Over the last two years, GSM and UMTS femtocell access points have been proposed as a solution to the poor indoor coverage problem experienced in certain areas. Research on these devices has shown that femtocells will not only increase indoor system coverage, but also system capacity. Femtocells will allow new services and business models to be offered to indoor users. Almost parallely, the WiMAX standard has emerged as a potential candidate technology for the future wireless networks. WiMAX femtocells are currently under development and will therefore play an important role in the world of indoor broadband wireless access. However, several aspects of this new technology, such as the access method and interference avoidance techniques play a crucial role in the amount of interference caused to co-channel deployed macrocells. This paper provides a framework for the study of WiMAX macro-femtocell hybrid scenarios. An in-depth description of the necessary radio coverage prediction and system-level simulation for this kind of scenarios is introduced. Simulations and numerical results for two different types of access methods (public and private) in the downlink are also presented.

show abstract

“…A Dziekonski et al studied on GPU-based FEM with complex system, but only gained 4 times speed due to the expensive transfer cost between CPU and GPU [27]. Valcarce et al and M Unno et al simulated 2-D electromagnetic field using GPU-based FDM [28,29], which showed high performance. And an implementation of simulation of high-frequency electromagnetic field using Galerkin FEM based on GPU has been proposed by N Goedle et al [30].…”

Section: Introductionmentioning

confidence: 99%

2-D electromagnetic modelling by finite element method on GPU

Bai

et al. 2016

Optik

View full text Add to dashboard Cite

A GPU approach to FDTD for radio coverage prediction

Cited by 26 publications

References 11 publications

In Situ Power Analysis of General Purpose Graphical Processing Units

In Situ Power Analysis of General Purpose Graphical Processing Units

Access methods to WiMAX femtocells: A downlink system-level case study

2-D electromagnetic modelling by finite element method on GPU

Contact Info

Product

Resources

About