Global Memory Access Modelling for Efficient Implementation of the Lattice Boltzmann Method on Graphics Processing Units

被引：0

作者：

Obrecht, Christian ^{[1
]}

Kuznik, Frederic ^{[1
]}

Tourancheau, Bernard ^{[2
]}

Roux, Jean-Jacques ^{[1
]}

机构：

[1] Univ Lyon, INSA Lyon, CNRS,Ctr Thermique Lyon, UMR 5008, Bat Sadi Carnot,9 Rue Phys, F-69621 Villeurbanne, France

[2] UCB Lyon 1, UMR 5668,ENS Lyon, INRIA, Lab Informat Parallelisme,CNRS, Lyon 63964, France

来源：

HIGH PERFORMANCE COMPUTING FOR COMPUTATIONAL SCIENCE - VECPAR 2010 | 2011年 / 6449卷

关键词：

GPU computing; CUDA; lattice Boltzmann method; CFD;

D O I：

暂无

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

In this work, we investigate the global memory access mechanism on recent GPUs. For the purpose of this study, we created specific benchmark programs, which allowed us to explore the scheduling of global memory transactions. Thus, we formulate a model capable of estimating the execution time for a large class of applications. Our main goal is to facilitate optimisation of regular data-parallel applications on GPUs. As an example, we finally describe our CUDA implementations of LBM flow solvers on which our model was able to estimate performance with less than 5% relative error.

引用

页码：151 / +

页数：2

共 50 条

[21] A graphic processing unit implementation for the moment representation of the lattice Boltzmann method
Ferrari, Marco A. A.
de Oliveira Jr, Waine B. B.
Lugarini, Alan
Franco, Admilson T. T.
Hegele Jr, Luiz A. A.
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, 2023, 95 (07) : 1076 - 1089
[22] ON THE OPTIMIZATION OF MEMORY ACCESS TO INCREASE THE PERFORMANCE OF SPATIAL PREPROCESSING TECHNIQUES ON GRAPHICS PROCESSING UNITS
Delgado, J.
Martin, G.
Plaza, J.
Jimenez, L. I.
Plaza, A.
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 6541 - 6544
[23] Simulating Lattice Spin Models on Graphics Processing Units
Levy, Tal
Cohen, Guy
Rabani, Eran
JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2010, 6 (11) : 3293 - 3301
[24] Efficient motion estimation and discrete cosine transform implementation using the graphics processing units
Agha, Shahrukh
Jan, Farmanullah
Khan, Haroon Ahmed
Kaleem, Muhammad
Khan, Mansoor
PLOS ONE, 2024, 19 (08):
[25] Fast deterministic solution of the full Boltzmann equation on Graphics Processing Units
Jaiswal, Shashank
Hu, Jingwei
Alexeenko, Alina A.
31ST INTERNATIONAL SYMPOSIUM ON RAREFIED GAS DYNAMICS (RGD31), 2019, 2132
[26] Robustness and Efficiency of Poisson-Boltzmann Modeling on Graphics Processing Units
Qi, Ruxi
Luo, Ray
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2019, 59 (01) : 409 - 420
[27] Impact of Memory Bottleneck on the Performance of Graphics Processing Units
Son, Dong Oh
Choi, Hong Jun
Kim, Jong Myon
Kim, Cheol Hong
SEVENTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2015), 2015, 9817
[28] A Framework for Memory Oversubscription Management in Graphics Processing Units
Li, Chen
Ausavarungnirun, Rachata
Rossbach, Christopher J.
Zhang, Youtao
Mutlu, Onur
Guo, Yang
Yang, Jun
TWENTY-FOURTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS (ASPLOS XXIV), 2019, : 49 - 63
[29] Optimized Parallel Implementation of Gillespie's First Reaction Method on Graphics Processing Units
Dittamo, Cristian
Cangelosi, Davide
2009 INTERNATIONAL CONFERENCE ON COMPUTER MODELING AND SIMULATION, PROCEEDINGS, 2009, : 156 - 161
[30] Memory-efficient Lattice Boltzmann Method for low Reynolds number flows
Matyka, Maciej
Dzikowski, Michal
Computer Physics Communications, 2021, 267

← 1 2 3 4 5 →