pycon logo

PyCon 2011 Atlanta

March 9th–17th

Log in or Sign Up

SOLVCON: Computational Fluid Dynamics, Supercomputing, and Python

log in to bookmark this presentaton

Experienced / Poster
Calculations of conservation laws, i.e., hyperbolic partial differential equations, have various applications in engineering, e.g., computational fluid dynamics. Supercomputers are needed for these calculations. Although legacy codes use pure FORTRAN or C for the highest-possible speed, mixing Python and C can delivers the same performance with a much more maintainable structure.

Abstract

SOLVCON (http://solvcon.net/) is an open-source, Python-based, multi-physics, supercomputing software framework for conservation laws. It has been applied to computational fluid dynamics and computational solid mechanics. Constructed as a framework, SOLVCON is able to regulate many supportive functionalities, which were duplicated in many legacy codes. Using Python as the fundamental tool for simulation codes is rare, but very attractive. Aided by mixing Python with other high-speed programming languages such as C or CUDA, modern techniques of software engineering can be used for simulation codes, without penalty for speed. Undoubtedly, Python will become the mainstream tool for numerical simulations.

This poster shows:

  1. the applications of SOLVCON for aerodynamics and propagating waves in solids, and
  2. essential sub-systems for supercomputing.