A Particle-Mesh Integrator for Galactic Dynamics Powered by GPGPUs

Aubert, Dominique; Amini, Mehdi; David, Romaric

doi:10.1007/978-3-642-01970-8_88

Cited by 7 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this issue, we do not limit our experiments to the Polybench benchmarks, but we also include Stars-PM, a particle mesh cosmological N -body code. The sequential version was written in C at Observatoire Astronomique de Strasbourg and was rewritten and optimized by hand using cuda to target gpus [3]. …”

Section: Fully Automatic Approach: Par4allmentioning

confidence: 99%

Static Compilation Analysis for Host-Accelerator Communication Optimization

Amini

Coelho

Irigoin

et al. 2013

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

Abstract. We present an automatic, static program transformation that schedules and generates ecient memory transfers between a computer host and its hardware accelerator, addressing a well-known performance bottleneck. Our automatic approach uses two simple heuristics: to perform transfers to the accelerator as early as possible and to delay transfers back from the accelerator as late as possible. We implemented this transformation as a middle-end compilation pass in the pips/Par4All compiler. In the generated code, redundant communications due to data reuse between kernel executions are avoided. Instructions that initiate transfers are scheduled eectively at compile-time. We present experimental results obtained with the Polybench 2.0, some Rodinia benchmarks, and with a real numerical simulation. We obtain an average speedup of 4 to 5 when compared to a naïve parallelization using a modern gpu with Par4All, hmpp, and pgi, and 3.5 when compared to an OpenMP version using a 12-core multiprocessor.

show abstract

Section: Fully Automatic Approach: Par4allmentioning

confidence: 99%

Static Compilation Analysis for Host-Accelerator Communication Optimization

Amini

Coelho

Irigoin

et al. 2013

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then, it is easy to know how many particles are in each cell. This approach is classical in parallel PIC implementations (see for instance [1]). • we associate to each cell a work-item.…”

Section: A Pic Approximation Of Charged Particle Beamsmentioning

confidence: 99%

Numerical resolution of conservation laws with OpenCL

2013

View full text Add to dashboard Cite

We present several numerical simulations of conservation laws on recent multicore processors, such as GPUs, using the OpenCL programming framework. Depending on the chosen numerical method, different implementation strategies have to be considered, for achieving the best performance. We explain how to program efficiently three methods: a finite volume approach on a structured grid, a high order Discontinuous Galerkin (DG) method on an unstructured grid and a Particle-In-Cell (PIC) method. The three methods are respectively applied to a two-fluid computation, a Maxwell simulation and a Vlasov-Maxwell simulation.

show abstract

“…We then explain the consequences of such an architecture on our parallelized implementation. The consequences are different if we consider the Discontinuous Galerkin method [12] or the Particle-In-Cell algorithm [1].…”

Section: Implementation On Gpumentioning

confidence: 99%

“…The solution we have chosen is to first sort the particles according to their cell numbers [1]. This is done through an optimized radix sort algorithm described in [10].…”

Section: Current Computationmentioning

confidence: 99%

Resolution of the Vlasov-Maxwell system by PIC discontinuous Galerkin method on GPU with OpenCL

Crestetto¹,

Helluy²

2012

ESAIM: Proc.

View full text Add to dashboard Cite

Abstract. We present an implementation of a Vlasov-Maxwell solver for multicore processors. The Vlasov equation describes the evolution of charged particles in an electromagnetic field, solution of the Maxwell equations. The Vlasov equation is solved by a Particle-In-Cell method (PIC), while the Maxwell system is computed by a Discontinuous Galerkin method. We use the OpenCL framework, which allows our code to run on multicore processors or recent Graphic Processing Units (GPU). We present several numerical applications to two-dimensional test cases.

show abstract

A Particle-Mesh Integrator for Galactic Dynamics Powered by GPGPUs

Cited by 7 publications

References 13 publications

Static Compilation Analysis for Host-Accelerator Communication Optimization

Static Compilation Analysis for Host-Accelerator Communication Optimization

Numerical resolution of conservation laws with OpenCL

Resolution of the Vlasov-Maxwell system by PIC discontinuous Galerkin method on GPU with OpenCL

Contact Info

Product

Resources

About