Scientific modeling with massively parallel SIMD computers

Wilding, Nigel B.; Trew, Arthur; Hawick, K. A.; Pawley, G. S.

doi:10.1109/5.92050

Cited by 33 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To numerically simulate the CH equation, the rate of change in concentration must be calculated for each cell according to Equation (2). This value can then be used to integrate the total change in each cell's value over a discrete time step.…”

Section: Cahn-hilliard Equation Simulationmentioning

confidence: 99%

“…Each thread within the simulation is responsible for calculating the change in concentration for a single cell according to the discrete CH equation (2). This formula uses the Laplace and operators: ᭞ 2 and ᭞ 4 .…”

Section: Memory Accessmentioning

confidence: 99%

“…That era saw a great many scientific applications ported to the then important massively parallel and data-parallel supercomputer architectures such as the AMT DAP [2] and the surprising variations that arise from the nature of a practical simulation rather than a carefully chosen toy or benchmark scenario.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting graphical processing units for data‐parallel scientific applications

Leist

Playne

Hawick

2009

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYGraphical processing units (GPUs) have recently attracted attention for scientific applications such as particle simulations. This is partially driven by low commodity pricing of GPUs but also by recent toolkit and library developments that make them more accessible to scientific programmers. We discuss the application of GPU programming to two significantly different paradigms-regular mesh field equations with unusual boundary conditions and graph analysis algorithms. The differing optimization techniques required for these two paradigms cover many of the challenges faced when developing GPU applications. We discuss the relevance of these application paradigms to simulation engines and games. GPUs were aimed primarily at the accelerated graphics market but since this is often closely coupled to advanced game products it is interesting to speculate about the future of fully integrated accelerator hardware for both visualization and simulation combined. As well as reporting the speed-up performance on selected simulation paradigms, we discuss suitable data-parallel algorithms and present code examples for exploiting GPU features like large numbers of threads and localized texture memory. We find a surprising variation in the performance that can be achieved on GPUs for our applications and discuss how these findings relate to past known effects in parallel computing such as memory speed-related super-linear speed up.

show abstract

Section: Cahn-hilliard Equation Simulationmentioning

confidence: 99%

Section: Memory Accessmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting graphical processing units for data‐parallel scientific applications

Leist

Playne

Hawick

2009

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Models based on CA lead to algorithms, which are fast when implemented on serial computers, because they exploit the inherent parallelism of the CA structure. These algorithms are also appropriate for implementation on massively parallel computers (Spezzano et al 1996), such as the Cellular Automaton Machine (CAM) (Wilding et al 1991) or Field Programmable Gate Arrays (FPGAs) (Dourvas et al forthcoming;Georgoudas et al 2010;Jendrsczok, Ediger, and Hoffmann 2009;Kalogeropoulos, Sirakoulis, and Karafyllidis 2013;Mardiris et al 2008;Progias and Sirakoulis 2013).…”

Section: Ca Theorymentioning

confidence: 98%

Cellular automaton model of crowd evacuation inspired by slime mould

Kalogeiton

Papadopoulos

Georgilas

et al. 2015

International Journal of General Systems

View full text Add to dashboard Cite

In all the living organisms, the self-preservation behaviour is almost universal. Even the most simple of living organisms, like slime mould, is typically under intense selective pressure to evolve a response to ensure their evolution and safety in the best possible way. On the other hand, evacuation of a place can be easily characterized as one of the most stressful situations for the individuals taking part on it. Taking inspiration from the slime mould behaviour, we are introducing a computational bio-inspired model crowd evacuation model. Cellular Automata (CA) were selected as a fully parallel advanced computation tool able to mimic the Physarum's behaviour. In particular, the proposed CA model takes into account while mimicking the Physarum foraging process, the food diffusion, the organism's growth, the creation of tubes for each organism, the selection of optimum tube for each human in correspondence to the crowd evacuation under study and finally, the movement of all humans at each time step towards near exit. To test the model's efficiency and robustness, several simulation scenarios were proposed both in virtual and real-life indoor environments (namely, the first floor of office building B of the Department of Electrical and Computer Engineering of Democritus University of Thrace). The proposed model is further evaluated in a purely quantitative way by comparing the simulation results with the corresponding ones from the bibliography taken by real data. The examined fundamental diagrams of velocity-density and flow-density are found in full agreement with many of the already published corresponding results proving the adequacy, the fitness and the resulting dynamics of the model. Finally, several real Physarum experiments were conducted in an archetype of the aforementioned real-life environment proving at last that the proposed model succeeded in reproducing sufficiently the Physarum's recorded behaviour derived from observation of the aforementioned biological laboratory experiments.

show abstract

“…Some significant examples are the simulation of physical systems [24,25], biological modeling involving models for self-reproduction, biological structures and DNA sequences [27,28], image processing [29,30], language recognition [31], crowd evacuation [32][33][34], traffic [35,36], computer architectures [37,38], fractals and chaos [39,40], cryptography [41], computer networks [42] and Quantum CAs [43].…”

Section: Introductionmentioning

confidence: 99%

Hardware Acceleration of Cellular Automata Physarum polycephalum Model

Dourvas

Tsompanas

Sirakoulis

et al. 2015

Parallel Process. Lett.

View full text Add to dashboard Cite

During the past decades, computer science experts were inspired from the study of biological organisms. Moreover, bio-inspired algorithms were produced that many times can give excellent solutions with low computational cost in complex engineering problems. In our case, the plasmodium of Physarum polycephalum is capable of finding the shortest path solution between two points in a labyrinth. In this study, we implement a Cellular Automata (CA) model in hardware, which attempts to describe and, moreover, mimic the behavior of the plasmodium in a maze. Beyond the successful implementation of the CA-based Physarum model in software, in order to take full advantage of the inherent parallelism of CA, we focus on a Field Programmable Gate Array (FPGA) implementation of the proposed model. Namely, two different implementations were considered here. Their difference is on the desired precision produced by the numerical representation of CA model parameters. Based on the corresponding results of the shortest path in the labyrinth,the modeling efficiency of both approaches was compared depending on the resulting error propagation. The presented FPGA implementations succeed to take advantage of the CA's inherit parallelism and improve the performance of the CA algorithm when compared with software in terms of computational speed and power consumption. As a result, the implementations presented here, can also be considered as a preliminary CA-based Physarum polycephalum IP core which produces a biological inspired solution to the shortest-path problem.

show abstract

Scientific modeling with massively parallel SIMD computers

Cited by 33 publications

References 14 publications

Exploiting graphical processing units for data‐parallel scientific applications

Exploiting graphical processing units for data‐parallel scientific applications

Cellular automaton model of crowd evacuation inspired by slime mould

Hardware Acceleration of Cellular Automata Physarum polycephalum Model

Contact Info

Product

Resources

About