Implementing lattice Boltzmann computation on graphics hardware

Li, Wei; Wei, Xiaoming; Kaufman, Arie

doi:10.1007/s00371-003-0210-6

Cited by 152 publications

(83 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Beside many interesting features, such as the ability to easily handle complex geometries, the LBM reduces to a regular data-parallel algorithm and therefore, is well-suited to efficient HPC implementations. As a matter of fact, numerous successful attempts to implement the LBM for the GPU have been reported in the recent years, starting with the seminal work of Li et al in 2003 [10].…”

Section: Introductionmentioning

confidence: 99%

Scalable lattice Boltzmann solvers for CUDA GPU clusters

et al. 2013

View full text Add to dashboard Cite

The lattice Boltzmann method (LBM) is an innovative and promising approach in computational fluid dynamics. From an algorithmic standpoint it reduces to a regular data parallel procedure and is therefore well-suited to high performance computations. Numerous works report efficient implementations of the LBM for the GPU, but very few mention multi-GPU versions and even fewer GPU cluster implementations. Yet, to be of practical interest, GPU LBM solvers need to be able to perform large scale simulations. In the present contribution, we describe an efficient LBM implementation for CUDA GPU clusters. Our solver consists of a set of MPI communication routines and a CUDA kernel specifically designed to handle three-dimensional partitioning of the computation domain. Performance measurement were carried out on a small cluster. We show that the results are satisfying, both in terms of data throughput and parallelisation efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

Scalable lattice Boltzmann solvers for CUDA GPU clusters

et al. 2013

View full text Add to dashboard Cite

show abstract

“…(e.g. [18]) In the domain of solvers for partial differential equations, Finite-Difference Time-Domain (FDTD) methods are a natural fit to graphics processors and obtained high performance with relative ease (e.g., [15]). Finite Element solvers were also brought onto GPUs relatively early on (e.g., [9]), but often failed to reach the same impressive speed gains observed for the simpler FD methods.…”

mentioning

confidence: 99%

High-Order Discontinuous Galerkin Methods by GPU Metaprogramming

Klöckner

Warburton

Hesthaven

2013

Lecture Notes in Earth System Sciences

View full text Add to dashboard Cite

Discontinuous Galerkin (DG) methods for the numerical solution of partial differential equations have enjoyed considerable success because they are both flexible and robust: They allow arbitrary unstructured geometries and easy control of accuracy without compromising simulation stability. In a recent publication, we have shown that DG methods also adapt readily to execution on modern, massively parallel graphics processors (GPUs). A number of qualities of the method contribute to this suitability, reaching from locality of reference, through regularity of access patterns, to high arithmetic intensity. In this article, we illuminate a few of the more practical aspects of bringing DG onto a GPU, including the use of a Python-based metaprogramming infrastructure that was created specifically to support DG, but has found many uses across all disciplines of computational science. IntroductionDiscontinuous Galerkin methods [5,10,17,24] are, at first glance, a rather curious combination of ideas from Finite-Volume and Spectral Element methods. Up close, they are very much high-order methods by design. But instead of perpetuating the order increase like conventional global methods, at a certain level of detail, they switch over to a decomposition into computational elements and couple these el-

show abstract

“…Another increasingly popular method for simulating fluids is the LatticeBoltzmann Method (LBM), which was first used for computer graphics in 2003 by Li et al [43] and Wei et al [88]. The LBM is an Eulerian model just like NavierStokes simulations, but focuses on fluid interactions at a molecular scale rather than a continuum scale.…”

Section: The Lattice-boltzmann Methodsmentioning

confidence: 99%

“…Before Li et al [43] and Wei et al [88] were published, the LBM had been already used for many years in physics applications such as [22], [9], [17], and [52] but was restricted to supercomputers due to its computational complexity [43].…”

Section: The Lattice-boltzmann Methodsmentioning

confidence: 99%

“…However, Li et al [43] created an LBM implementation that exploited the massively parallel and vector-optimized processors available on commodity graphics processing units (GPUs) that are inexpensive and widely accessible to the public. This allowed LBM simulations to run on commodity hardware and greatly increased its popularity.…”

Section: The Lattice-boltzmann Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Boundless Fluids Using the Lattice-Boltzmann Method

Haughey¹

View full text Add to dashboard Cite

Boundless Fluids Using the Lattice-Boltzmann Method by Kyle Joseph HaugheyComputer-generated imagery is ubiquitous in today's society, appearing in advertisements, video games, and computer-animated movies among other places.Much of this imagery needs to be as realistic as possible, and animators have turned to techniques such as fluid simulation to create scenes involving substances like smoke, fire, and water. The Lattice-Boltzmann Method (LBM) is one fluid simulation technique that has gained recent popularity due to its relatively simple basic algorithm and the ease with which it can be distributed across multiple processors. Unfortunately, current LBM simulations also suffer from high memory usage and restrict free surface fluids to domains of fixed size. This thesis modifies the LBM to utilize a recursive run-length-encoded (RLE) grid data structure instead of the standard fixed array of grid cells, which reduces the amount of memory required for LBM simulations as well as allowing the domain to grow and shrink as necessary to accomodate a liquid surface. The modified LBM is implemented within the open-source 3D animation package Blender and compared to Blender's current LBM simulator using the metrics of memory usage and time required to complete a given simulation. Results show that, although the RLE-based simulator can take several times longer than the current simulator to complete a given simulation, the memory usage is significantly reduced, making an RLE-based simulation preferable in a few specific circumstances.iv

show abstract

Implementing lattice Boltzmann computation on graphics hardware

Cited by 152 publications

References 13 publications

Scalable lattice Boltzmann solvers for CUDA GPU clusters

Scalable lattice Boltzmann solvers for CUDA GPU clusters

High-Order Discontinuous Galerkin Methods by GPU Metaprogramming

Boundless Fluids Using the Lattice-Boltzmann Method

Contact Info

Product

Resources

About