CS267: Lecture 12, Feb 25 1999

Sources of Parallelism and Locality in Simulation - III

Tricks with Trees

Abstract

First, we conclude our discussion of parallelism arising in solving PDEs.

Second, we show how to use trees to accelerate a large number of different calculations, from matrix inversion to expression evaluation.

Lecture Notes

  • Power Point version
  • Postscript version
  • Primary Readings

  • Notes from Lecture 13 from CS267, Spring 1996, on PDEs
  • Notes from Lecture 10 from CS267, Spring 1996, on Fast Algorithms using Trees
  • Secondary Readings

  • Triangle, a 2D mesh generator written by Jonathan Shewchuk.
  • PETSc, a Portable, Extensible Toolkit for Scientific Computation (an object oriented parallel PDE solver)
  • ParMetis, a parallel graph partitioner, by George Karypis
  • Prometheus a multigrid-based solver for finite element problems on irregular meshes, by Mark Adams
  • Example of Adaptive Mesh Refinement at LBL, by John Bell and Phil Colella
  • SuperLU_MT is a parallel implementation of sparse Gaussian elimination for SMPs, by Xiaoye Li. The following paper describes a distributed memory version about to be released.