@TechReport{	  it:2014-011,
  author	= {Martin Tillenius and Elisabeth Larsson and Erik Lehto and
		  Natasha Flyer},
  title		= {A Task Parallel Implementation of an {RBF}-generated
		  Finite Difference Method for the Shallow Water Equations on
		  the Sphere},
  institution	= {Department of Information Technology, Uppsala University},
  department	= {Division of Scientific Computing},
  year		= {2014},
  number	= {2014-011},
  month		= apr,
  abstract	= {Radial basis function-generated finite difference (RBF-FD)
		  methods have recently been proposed as very interesting for
		  global scale geophysical simulations, and have been shown
		  to outperform established pseudo-spectral and discontinuous
		  Galerkin methods for shallow water test problems. In order
		  to be competitive for very large scale simulations, the
		  implementation of the RBF-FD methods needs to be efficient
		  and adapted for modern multicore based computer
		  architectures. The main computational operations in the
		  method consist of unstructured sparse matrix-vector
		  multiplications, which are in general not well suited for
		  multicore-based computers. In this work, the method is
		  implemented for clusters of multicore computers using a
		  task-based parallel programming model. Performance
		  experiments showed that our implementation achieves 71\% of
		  theoretical speedup within one computational node, and
		  90~100\% of linear speedup between nodes. A speedup of 178
		  times compared with the original MATLAB implementation was
		  achieved for a global shallow water problem with a 30km
		  resolution. }
}