An optimized D2Q37 Lattice Boltzmann code on GP-GPUs

L. Biferale; F. Mantovani; M. Pivanti; F. Pozzati; M. Sbragaglia; Andrea Scagliarini; S.F. Schifano; F. Toschi

doi:10.1016/j.compfluid.2012.06.003

An optimized D2Q37 Lattice Boltzmann code on GP-GPUs

L. Biferale
, F. Mantovani
, M. Pivanti
, F. Pozzati
, M. Sbragaglia
, Andrea Scagliarini
, S.F. Schifano
, F. Toschi

Research output: Contribution to journal › Article › Academic › peer-review

25 Citations (Scopus)

2 Downloads (Pure)

Abstract

We describe the implementation of a thermal compressible Lattice Boltzmann algorithm on an NVIDIA Tesla C2050 system based on the Fermi GP-GPU. We consider two different versions, including and not including reactive effects. We describe the overall organization of the algorithm and give details on its implementations. Efficiency ranges from 25% to 31% of the double precision peak performance of the GP-GPU. We compare our results with a different implementation of the same algorithm, developed and optimized for many-core Intel Westmere CPUs.

Original language	English
Pages (from-to)	55-62
Journal	Computers & Fluids
Volume	80
DOIs	https://doi.org/10.1016/j.compfluid.2012.06.003
Publication status	Published - 2013

Access to Document

10.1016/j.compfluid.2012.06.003

Cite this

@article{ee2b96f467f24d67827a6e192a5c22ae,

title = "An optimized D2Q37 Lattice Boltzmann code on GP-GPUs",

abstract = "We describe the implementation of a thermal compressible Lattice Boltzmann algorithm on an NVIDIA Tesla C2050 system based on the Fermi GP-GPU. We consider two different versions, including and not including reactive effects. We describe the overall organization of the algorithm and give details on its implementations. Efficiency ranges from 25\% to 31\% of the double precision peak performance of the GP-GPU. We compare our results with a different implementation of the same algorithm, developed and optimized for many-core Intel Westmere CPUs.",

author = "L. Biferale and F. Mantovani and M. Pivanti and F. Pozzati and M. Sbragaglia and Andrea Scagliarini and S.F. Schifano and F. Toschi",

year = "2013",

doi = "10.1016/j.compfluid.2012.06.003",

language = "English",

volume = "80",

pages = "55--62",

journal = "Computers \& Fluids",

issn = "0045-7930",

publisher = "Elsevier",

}

TY - JOUR

T1 - An optimized D2Q37 Lattice Boltzmann code on GP-GPUs

AU - Biferale, L.

AU - Mantovani, F.

AU - Pivanti, M.

AU - Pozzati, F.

AU - Sbragaglia, M.

AU - Scagliarini, Andrea

AU - Schifano, S.F.

AU - Toschi, F.

PY - 2013

Y1 - 2013

N2 - We describe the implementation of a thermal compressible Lattice Boltzmann algorithm on an NVIDIA Tesla C2050 system based on the Fermi GP-GPU. We consider two different versions, including and not including reactive effects. We describe the overall organization of the algorithm and give details on its implementations. Efficiency ranges from 25% to 31% of the double precision peak performance of the GP-GPU. We compare our results with a different implementation of the same algorithm, developed and optimized for many-core Intel Westmere CPUs.

AB - We describe the implementation of a thermal compressible Lattice Boltzmann algorithm on an NVIDIA Tesla C2050 system based on the Fermi GP-GPU. We consider two different versions, including and not including reactive effects. We describe the overall organization of the algorithm and give details on its implementations. Efficiency ranges from 25% to 31% of the double precision peak performance of the GP-GPU. We compare our results with a different implementation of the same algorithm, developed and optimized for many-core Intel Westmere CPUs.

U2 - 10.1016/j.compfluid.2012.06.003

DO - 10.1016/j.compfluid.2012.06.003

M3 - Article

SN - 0045-7930

VL - 80

SP - 55

EP - 62

JO - Computers & Fluids

JF - Computers & Fluids

ER -

An optimized D2Q37 Lattice Boltzmann code on GP-GPUs

Abstract

Access to Document

Fingerprint

Cite this