Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores

DOI10.1016/J.COMPFLUID.2018.03.005zbMath1410.76307arXiv1710.09995OpenAlexW2766598878WikidataQ130161762 ScholiaQ130161762MaRDI QIDQ1615515

Yu Zhuang, Yong-Xian Wang, Li-Lun Zhang, Wei Liu, Xing-Hua Cheng, Anthony Theodore Chronopoulos

Publication date: 31 October 2018

Published in: Computers and Fluids (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.09995

zbMATH Keywords

parallel computingcomputational fluid dynamicsCPU+MIC heterogeneous computingTianhe-2 supercomputer

Mathematics Subject Classification ID

Finite difference methods applied to problems in fluid mechanics (76M20) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Numerical algorithms for specific classes of architectures (65Y10) Compressible fluids and gas dynamics (76Nxx)

Related Items (2)

Parallel performance analysis of coupled heat and fluid flow in parallel plate channel using CUDA ⋮ Sensitivity of computational fluid dynamics simulations against soft errors

Uses Software

• HOSTA

Cites Work

• High order strong stability preserving time discretizations
• Geometric conservation law and applications to high-order finite difference schemes with stationary grids
• Compact high-order accurate nonlinear schemes
• Running unstructured grid-based CFD solvers on modern graphics hardware

This page was built for publication: Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores