Challenges on Porting Lattice Boltzmann Method on Accelerators

2018 ◽  
pp. 30-53 ◽  
Author(s):  
Claudio Schepke ◽  
João V. F. Lima ◽  
Matheus S. Serpa
Keyword(s):  
Lattice Boltzmann Method ◽  
Lattice Boltzmann ◽  
High Performance ◽  
Three Dimensional ◽  
Fluid Flows ◽  
Xeon Phi ◽  
Performance Impact ◽  
Operation Rules ◽  
Dimensional Version ◽  
Boltzmann Method

Currently NVIDIA GPUs and Intel Xeon Phi accelerators are alternatives of computational architectures to provide high performance. This chapter investigates the performance impact of these architectures on the lattice Boltzmann method. This method is an alternative to simulate fluid flows iteratively using discrete representations. It can be adopted for a large number of flows simulations using simple operation rules. In the experiments, it was considered a three-dimensional version of the method, with 19 discrete directions of propagation (D3Q19). Performance evaluation compare three modern GPUs: K20M, K80, and Titan X; and two architectures of Xeon Phi: Knights Corner (KNC) and Knights Landing (KNL). Titan X provides the fastest execution time of all hardware considered. The results show that GPUs offer better processing time for the application. A KNL cache implementation presents the best results for Xeon Phi architectures and the new Xeon Phi (KNL) is two times faster than the previous model (KNC).

scholarly journals Performance and Energy Assessment of a Lattice Boltzmann Method Based Application on the Skylake Processor

Computation ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 44
Author(s):  
Ivan Girotto ◽  
Sebastiano Fabio Schifano ◽  
Enrico Calore ◽  
Gianluca Di Staso ◽  
Federico Toschi
Keyword(s):  
Energy Efficiency ◽  
Lattice Boltzmann Method ◽  
Lattice Boltzmann ◽  
High Performance ◽  
Three Dimensional ◽  
Scientific Application ◽  
Energy Assessment ◽  
Boltzmann Method ◽  
The Impact ◽  
Data Layouts

This paper presents the performance analysis for both the computing performance and the energy efficiency of a Lattice Boltzmann Method (LBM) based application, used to simulate three-dimensional multicomponent turbulent systems on massively parallel architectures for high-performance computing. Extending results reported in previous works, the analysis is meant to demonstrate the impact of using optimized data layouts designed for LBM based applications on high-end computer platforms. A particular focus is given to the Intel Skylake processor and to compare the target architecture with other models of the Intel processor family. We introduce the main motivations of the presented work as well as the relevance of its scientific application. We analyse the measured performances of the implemented data layouts on the Skylake processor while scaling the number of threads per socket. We compare the results obtained on several CPU generations of the Intel processor family and we make an analysis of energy efficiency on the Skylake processor compared with the Intel Xeon Phi processor, finally adding our interpretation of the presented results.

Simulation of Hypersonic Viscous Flow Past a 2D Circular Cylinder Using Lattice Boltzmann Method

2010 ◽  
Author(s):  
R. Kamali ◽  
A. H. Tabatabaee Frad
Keyword(s):  
Circular Cylinder ◽  
Lattice Boltzmann Method ◽  
Lattice Boltzmann ◽  
High Speed ◽  
Fluid Flows ◽  
Boltzmann Distribution ◽  
Equilibrium Distribution Function ◽  
Complex Flows ◽  
Compressible Viscous Flows ◽  
Boltzmann Method

It is known that the Lattice Boltzmann Method is not very effective when it is being used for the high speed compressible viscous flows; especially complex fluid flows around bodies. Different reasons have been reported for this unsuccessfulness; Lacking in required isotropy in the employed lattices and the restriction of having low Mach number in Taylor expansion of the Maxwell Boltzmann distribution as the equilibrium distribution function, might be mentioned as the most important ones. In present study, a new numerical method based on Li et al. scheme is introduced which enables the Lattice BoltzmannMethod to stably simulate the complex flows around a 2D circular cylinder. Furthermore, more stable implementation of boundary conditions in Lattice Boltzmann method is discussed.

Numerical Investigation of Flow Over an Airfoil by the Lattice Boltzmann Method

2013 ◽  
Author(s):  
Felipe A. Valenzuela ◽  
Amador M. Guzmán ◽  
Andrés J. Díaz
Keyword(s):  
Lattice Boltzmann Method ◽  
Lattice Boltzmann ◽  
Preliminary Investigation ◽  
Computational Cost ◽  
Fluid Flows ◽  
Laminar Flows ◽  
Navier Stokes ◽  
Laminar Separation ◽  
Refinement Method ◽  
Boltzmann Method

During the last years the aerodynamics characteristics of airfoils have been studied solving numerically the Navier-Stokes (NS) equations. These calculations require a significant computational cost due to both the second order and the nonlinear characteristics of the NS partial differential equations. Therefore, efforts have been devoted to reduce this cost and increase the accuracy of the numerical methods. The Lattice-Boltzmann Method (LBM) has become a great alternative to simulate this problem and a variety of fluid flows. In this method, the convective operator is linear and the pressure is calculated directly by the equation of state without implementing iterative methods. This work represents a preliminary investigation of a laminar flow over airfoils under low Reynolds number conditions (Re = 500). Solutions are obtained using a Multi-Block mesh refinement method. In order to validate the computational code, calculations are performed on a SD7003 airfoil at an angle of attack of 4° and 30°, which corresponds to the available numerical and experimental results. The results of this study agree well with previous experimental and numerical studies demonstrating the capabilities of the LBM to simulate accurately laminar flows over airfoils as well as capturing and predicting the laminar separation bubbles.

Sign in / Sign up

Export Citation Format

Share Document