Fine Granularity Sparse QR Factorization for Multicore Based Systems
The advent of multicore processors represents a disruptive event in the history of computer science as conventional parallel programming paradigms are proving incapable of fully exploiting their potential for concurrent computations. The need for different or new programming models clearly arises from recent studies which identify fine-granularity and dynamic execution as the keys to achieve high efficiency on multicore systems. This work presents an implementation of the sparse, multifrontal QR factorization capable of achieving high efficiency on multicore systems through using a fine-grained, dataflow parallel programming model.
KeywordsMultifrontal Sparse QR Least-Squares Multicore
Unable to display preview. Download preview PDF.
- 5.Davis, T.A.: University of Florida sparse matrix collection (2002), http://www.cise.ufl.edu/research/sparse/matrices
- 7.Davis, T.A.: Multifrontal multithreaded rank-revealing sparse QR factorization. Accepted for Publication on ACM Transactions on Mathematical Software (2009)Google Scholar
- 11.Hogg, J., Reid, J.K., Scott, J.A.: A DAG-based sparse Cholesky solver for multicore architectures. Technical Report RAL-TR-2009-004, Rutherford Appleton Laboratory (2009)Google Scholar
- 14.Matstoms, P.: Parallel sparse QR factorization on shared memory architectures. Technical Report LiTH-MAT-R-1993-18, Department of Mathematics (1993)Google Scholar
- 15.Rice, J.R.: PARVEC workshop on very large least squares problems and supercomputers. Technical Report CSD-TR 464, Purdue University, IN (1983)Google Scholar
- 17.Silc, J., Robic, B., Ungerer, T.: Asynchrony in parallel computing: From dataflow to multithreading. Journal of Parallel and Distributed Computing Practices 1, 1–33 (1998)Google Scholar