Fast vortex method calculation using a special-purpose computer

Sheel, Tarun Kumar; Yasuoka, Kenji; Obi, Shinnosuke

doi:10.1016/j.compfluid.2007.01.006

Cited by 12 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The equations that govern the pair wise interaction of vortex elements are more complex than those of the gravitational and molecular dynamics calculations. This complicates the implementation on special-purpose computers (MDGRAPE) [25,26], but allows a more efficient implementation on GPUs because it is easier to hide the memory latency.…”

Section: Introductionmentioning

confidence: 99%

Fast multipole methods on a cluster of GPUs for the meshless simulation of turbulence

Yokota

Narumi

Sakamaki

et al. 2009

Computer Physics Communications

Self Cite

View full text Add to dashboard Cite

Recent advances in the parallelizability of fast N-body algorithms, and the programmability of graphics processing units (GPUs) have opened a new path for particle based simulations. For the simulation of turbulence, vortex methods can now be considered as an interesting alternative to finite difference and spectral methods. The present study focuses on the efficient implementation of the fast multipole method and pseudo-particle method on a cluster of NVIDIA GeForce 8800 GT GPUs, and applies this to a vortex method calculation of homogeneous isotropic turbulence. The results of the present vortex method agree quantitatively with that of the reference calculation using a spectral method. We achieved a maximum speed of 7.48 TFlops using 64 GPUs, and the cost performance was near $9.4/GFlops. The calculation of the present vortex method on 64 GPUs took 4120 s, while the spectral method on 32 CPUs took 4910 s.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast multipole methods on a cluster of GPUs for the meshless simulation of turbulence

Yokota

Narumi

Sakamaki

et al. 2009

Computer Physics Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…(16) and (17)) is created prior to calculation and read during calculation. The domain of the function g (w) is set to w min ≤ w ≤ w max where (w max /w min ) ≤ 2 32 according to hardware specifications, for details see in [6,12]. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…We considered inclined collisions according to [6] to check and validate our new scheme. Here we assumed that the initial radius of the vortex rings was R = 1 while the cross-section radius r = 0.05 (see Fig.…”

Section: Calculation Conditionsmentioning

confidence: 99%

“…The vortex method has been used on the second model MDGRAPE-2 by the present author [6] for calculating the collision of vortex rings. The present study focuses on the simultaneous use of the FMM and MDGRAPE-3 for the same flow field.…”

Section: Fmm On Mdgrape-3mentioning

confidence: 99%

“…The long computation time due to the above-mentioned O(N 2 ) problem has been reduced 50 times when we apply a specialpurpose computer, MDGRPAE-2 shown in [6]. Although it can speed up velocity calculation significantly, the calculation cost is still proportional with N 2 for direct summation algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Acceleration of Vortex Methods Calculation Using FMM and Mdgrape-3

Sheel¹

2011

PIER B

View full text Add to dashboard Cite

Abstract-The present study discusses some numerical techniques on the simultaneous use of the Fast Multipole Method (FMM) and special-purpose computer (MDGRAPE-3) to make the impractically expensive calculation feasible without the loss of numerical accuracy. In the present calculations, the impingement of two identical inclined vortex rings has been studied, and the computation time has been reduced by a factor of 1000 at N = 1.18×10 6 where N is the number of vortex elements. The direct and MDGRAPE-3 calculations both have a scaling of O(N 2 ), and the use of the FMM brings them both down to O(N ). The global kinetic energy, enstrophy and energy spectra have been investigated to address the numerical accuracy and have good agreement with other similar works.

show abstract

High-performance computing techniques for vortex method calculations

Sheel¹,

Obi²

2009

Iutam Bookseries

View full text Add to dashboard Cite

Fast vortex method calculation using a special-purpose computer

Cited by 12 publications

References 15 publications

Fast multipole methods on a cluster of GPUs for the meshless simulation of turbulence

Fast multipole methods on a cluster of GPUs for the meshless simulation of turbulence

Acceleration of Vortex Methods Calculation Using FMM and Mdgrape-3

High-performance computing techniques for vortex method calculations

Contact Info

Product

Resources

About