共 50 条
Optimization of flexible neighbors lists in Smoothed Particle Hydrodynamics on GPU
被引:1
|作者:
Bilotta, Giuseppe
[1
]
Zago, Vito
[2
,3
]
Herault, Alexis
[1
]
Cappello, Annalisa
[1
]
Ganci, Gaetana
[1
]
van Ettinger, Hendrik D.
[4
]
Dalrymple, Robert A.
[2
]
机构:
[1] Ist Nazl Geofis & Vulcanol, Osservatorio Etneo, Catania, Italy
[2] Northwestern Univ, Dept Civil & Environm Engn, 2145 Sheridan Rd, Evanston, IL 60208 USA
[3] Conservatoire Natl Arts & Metiers, Lab Modelisat Math & numer, 292 Rue St Martin, F-75003 Paris, France
[4] Surf Loch, San Diego, CA USA
关键词:
GPUSPH;
SPH;
CUDA;
Optimizations;
Compilers;
Neighbors list;
NUMERICAL-SIMULATION;
BOUNDARY-CONDITIONS;
SPH;
FLOWS;
SOLVER;
VISCOSITY;
TREE;
D O I:
10.1016/j.advengsoft.2024.103711
中图分类号:
TP39 [计算机的应用];
学科分类号:
081203 ;
0835 ;
摘要:
Recent refactoring of the GPUSPH codebase have uncovered some of the limitations of the official CUDA compiler (nvcc) offered by NVIDIA when dealing with some C++ constructs, which has shed some new light on the relative importance of the neighbors list construction and traversal in SPH codes, presenting new possibility of optimization with surprising performance gains. We present our solution for high-performance neighbors list construction and traversal, and show that a 4x speedup can be achieved in industrial applications.
引用
收藏
页数:18
相关论文