An accelerated topology change algorithm for the contour advection method

Authors

  • P.B. Bogdanov
  • A.A. Efremov
  • S.A. Sukov
  • A.V. Gorobets

Keywords:

gas dynamics
scheduler
parallel computing
GPU
OpenCL
MPI PDF (in Russian) (1.19MB) PDF. zip (in Russian) (1.13MB)

Abstract

An optimization of communications within multi-level parallelization based on a combination of MPI, OpenMP and OpenCL is proposed to fit all kinds of modern supercomputer architectures including hybrid systems with GPU and Intel Xeon Phi accelerators. A general-purpose scheduler that simplifies a heterogeneous implementation is discussed. The scheduler controls queues of computing and communication OpenCL tasks. It uses an interdependency graph of a target computing algorithm as input. The use of the scheduler is demonstrated on an example of a finite-volume CFD algorithm for unstructured meshes. In particular, the scheduler has been used to simplify an implementation of an overlapped communication scheme. The implementation of the CFD algorithm with MPI and CPU-GPU communications overlapped with computations is described and its parallel efficiency is demonstrated.

New computational technologies

Downloads

Published

2013-12-03

Issue

Vol. 14 (2013): Issue 4.

Section

Section 2. Programming

Author Biographies

P.B. Bogdanov

Scientific Research Institute for System Analysis of RAS (SRISA RAS)
• Researcher

A.A. Efremov

Scientific Research Institute for System Analysis of RAS (SRISA RAS)
• Junior Researcher

S.A. Sukov

Keldysh Institute of Applied Mathematics of RAS
• Senior Researcher

A.V. Gorobets

Keldysh Institute of Applied Mathematics of RAS
• Senior Researcher

References

  1. Waugh D.W., Plumb R.A. Contour advection with surgery: a technique for investigating finescale structure in tracer transport // Journal of the Atmospheric Sciences. 1994. 51, N 4. 530-540.
  2. Dritschel D.G., Ambaum M.H. P. A contour-advective semi-Lagrangian numerical algorithm for simulating fine-scale conservative dynamical fields // Quarterly Journal of the Royal Meteorological Society. 1997. 123, N 540. 1097-1130.
  3. Zabusky N.J., Hughes M.H., Roberts K.V. Contour dynamics for the Euler equations in two dimensions // Journal of Computational Physics. 1979. 30, N 1. 96-106.
  4. Соколовский М.А., Веррон Ж. Динамика вихревых структур в стратифицированной вращающейся жидкости. М.-Ижевск: Ижевский институт компьютерных исследований, 2011.
  5. Козлов В.Ф. Метод контурной динамики в модельных задачах о топографическом циклогенезе в океане // Изв. АН СССР. Физика атмосферы и океана. 1983. 19, № 8. 845-854.
  6. Козлов В.Ф. Метод контурной динамики в океанологических исследованиях: результаты и перспективы // Морской гидрофизический журнал. 1985. № 4. 10-14.
  7. Dritschel D.G. Contour dynamics and contour surgery: numerical algorithms for extended, high-resolution modelling of vortex dynamics in two-dimensional, inviscid, incompressible flows // Computer Physics Reports. 1989. 10, N 3. 77-146.
  8. Dritschel D.G. Contour Surgery: A Topological reconnection scheme for extended integrations using contour dynamics // Journal of Computational Physics. 1988. 77, N 1. 240-266.
  9. Макаров В.Г. Вычислительный алгоритм метода контурной динамики с изменяемой топологией исследуемых областей // Моделирование в механике. 1991. T. 5(22), № 4. 83-95.
  10. Schaerf T.M., Macaskill C. On contour crossings in contour-advective simulations. Part 1. Algorithm for detection and quantification // Journal of Computational Physics. 2012. 231, N 2. 465-480.
  11. Schaerf T.M., Macaskill C. On contour crossings in contour-advective simulations. Part 2. Analysis of crossing errors and methods for their prevention // Journal of Computational Physics. 2012. 231, N 2. 481-504.
  12. Ласло М. Вычислительная геометрия и компьютерная графика на C++. М.: БИНОМ, 1997.
  13. Мелешко В.В., Краснопольская Т.С. Смешивание вязких жидкостей // Нелинейная динамика. 2005. 1, № 1. 69-109.