Parallel simulation of equation-based models on CUDA-enabled GPUs

Östlund, Per; Stavåker, Kristian; Fritzson, Peter

doi:10.1145/2039312.2039317

Cited by 7 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many numerical methods for CUDA to solve ODE. This article uses the most common Runge-Kutta-Merson method, interested can refer to [44][45][46][47].…”

Section: Using Matlab/cuda To Accelerate the Best Solutionmentioning

confidence: 99%

Study on Consulting Air Combat Simulation of Cluster UAV Based on Mixed Parallel Computing Framework of Graphics Processing Unit

Kung¹

2018

Electronics

View full text Add to dashboard Cite

This paper combines matrix game theory with negotiating theory and uses U-solution to study the framework of the consulting air combat of UAV cluster. The processes to determine the optimal strategy in this paper follow three points: first, the UAV cluster are grouped into fleets; second, the best paring for the joint operations of the fleet member with the enemy fleet members are calculated; thirdly, consultations within the fleet are conducted to discuss the problems of optimal tactic, roles of main/assistance, and situational assessment within the fleet. In order to improve the computing efficiency of the framework, this article explores the use of the NVIDIA graphics processor programmed through MATLAB mixed C++/CUDA toolkit to accelerate the calculations of equations of motion of unmanned aerial vehicles, the prediction of superiority values and U values, computations of consultation, the evaluation of situational assessment and the optimal strategies. The effectiveness evaluation of GPGPU and CPU can be observed by the simulation results. When the number of team air combat is small, the CPU alone has better efficiency; however, when the number of air combat clusters exceeds 6 to 6, the architecture presented in this article can provide higher performance improvements and run faster than optimized CPU-only code.

show abstract

“…There are many numerical methods for CUDA to solve ODE. This article uses the most common Runge-Kutta-Merson method, interested can refer to [44][45][46][47].…”

Section: Using Matlab/cuda To Accelerate the Best Solutionmentioning

confidence: 99%

Study on Consulting Air Combat Simulation of Cluster UAV Based on Mixed Parallel Computing Framework of Graphics Processing Unit

Kung¹

2018

Electronics

View full text Add to dashboard Cite

show abstract

“…A parallel extension to OpenModelica using explicit language constructs has also been developed [64]. Several authors have pointed out that ODE solvers for continuous-time and time-invariant systems without algebraic loops can be run in parallel on GPU cards [65][66] [67]. Another use of GPU technology is array computations [68].…”

Section: Parallel Simulation In Modelicamentioning

confidence: 99%

Distributed System Simulation Methods : For Model-Based Product Development

Braun

2015

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

With the current trend towards multi-core processors and computer grids, parallelism in system simulation is becoming inevitable. Performing multiple tasks concurrently can save both time and money. However, this also puts higher demands on simulation software. This thesis investigates how simulation-based product development can benefit from distributed simulation.One parallelization method is to cut apart models for simulation with distributed solvers by using time delays. The transmission line element method (TLM) is used, which eliminates numerical errors by introducing physically motivated time delays. Results show that linear speed-ups can be obtained for large models with balanced workloads. Different task scheduling techniques are tested. It is found that a fork-join algorithm with implicit synchronization performs best for models with a large total workload. On the other hand, a task-pool implementation with lock-based synchronization works better with smaller workloads.The distributed solver method virtually equals co-simulation between different simulation tools. Co-simulation also induces time delays at the interface variables, which makes TLM a useful method. An emerging standard for coupling of simulation tools is the Functional Mock-up Interface (FMI). Experiments show that FMI works well together with TLM, even when connecting different simulation domains such as system simulation and multi-body mechanics. Combining FMI with TLM enables a framework for tool-independent co-simulation with distributed solvers and time steps.When introducing distributed solvers, it can be suitable to maintain the same structure that was used in the modelling process. A popular object-oriented equation-based modelling language is Modelica. Instead of flattening the model for simulation with a centralized solver, TLM makes it possible to use different solvers for different objects in the model. Two approaches are investigated. First, Modelica support is implemented in the Hopsan TLM tool with a code generator. Second, Modelica models are imported to Hopsan through the FMI interface. Both methods are feasible. While the first requires less overhead i work, the second makes it possible to mix models from different Modelica tools and to use all the features of each individual tool. Depending on the number of TLM elements and their locations, model structures with different granularities can be achieved.Parallelism can be introduced at different levels. The distributed solver approach results in parallelism at the model-level. It is also possible to parallelize equation solvers, or to run several simulations in parallel. The latter is especially useful for simulation-based design optimization. An algorithm for profile-based scheduling of parallel optimization jobs is proposed that takes parallelism at both model-level and optimization level into account. Parallel optimizations can then be executed on either homogeneous or heterogeneous computer grids. This makes it possible to utilize the large amount of unused co...

show abstract

“…in (Sahlin et al 2004). On the other hand, new challenges involving parallel architectures in the context of equation-based approach are promising research fields (Ostlund et al 2010).…”

Section: State Of the Artmentioning

confidence: 99%

Sub-zonal computational fluid dynamics in an object-oriented modelling framework

2014

View full text Add to dashboard Cite

Airflow modelling is of fundamental importance for evaluating ventilation performance and energy consumption in buildings, and various approaches to the problem-starting from purely empirical up to the CFD ones-have been proposed and evaluated in the past years. Moreover, since the ultimate goal is whole building modelling, airflow simulation needs coupling with Energy Simulation (ES), in order to assess the overall energy performance. Due to the substantial differences between the software employed for airflow and ES, co-simulation is very often felt as the only way to handle such a problem. For example, in recent years a lot of effort has been spent in to couple ES and CFD tools. This paper proposes an alternative, in the form of an approach for solving the Navier-Stokes equations in a general multi-domain modelling framework. Since co-simulation is not involved, the correctness of the numerical solution relies on a single solver, thus being really transparent to the analyst. This is a first step towards a whole building simulation tool embedded in a unique framework capable of performing energy analysis, computing airflows, and representing control systems.

show abstract

Parallel simulation of equation-based models on CUDA-enabled GPUs

Cited by 7 publications

References 5 publications

Study on Consulting Air Combat Simulation of Cluster UAV Based on Mixed Parallel Computing Framework of Graphics Processing Unit

Study on Consulting Air Combat Simulation of Cluster UAV Based on Mixed Parallel Computing Framework of Graphics Processing Unit

Distributed System Simulation Methods : For Model-Based Product Development

Sub-zonal computational fluid dynamics in an object-oriented modelling framework

Contact Info

Product

Resources

About