umu.sePublications
Change search
ReferencesLink to record
Permanent link

Direct link
Recursive Blocked Algorithms and Hybrid Data Structures for Dense Matrix Library Software
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science. Umeå University, Faculty of Science and Technology, High Performance Compting Center North (HPC2N).
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science. Umeå University, Faculty of Science and Technology, High Performance Compting Center North (HPC2N).
2004 (English)In: SIAM Review, Vol. 46, no 1, 3-45 p.Article in journal (Refereed) Published
Abstract [en]

Matrix computations are both fundamental and ubiquitous in computational science and its vast application areas. Along with the development of more advanced computer systems with complex memory hierarchies, there is a continuing demand for new algorithms and library software that efficiently utilize and adapt to new architecture features. This article reviews and details some of the recent advances made by applying the paradigm of recursion to dense matrix computations on today's memory-tiered computer systems. Recursion allows for efficient utilization of a memory hierarchy and generalizes existing fixed blocking by introducing automatic variable blocking that has the potential of matching every level of a deep memory hierarchy. Novel recursive blocked algorithms offer new ways to compute factorizations such as Cholesky and QR and to solve matrix equations. In fact, the whole gamut of existing dense linear algebra factorization is beginning to be reexamined in view of the recursive paradigm. Use of recursion has led to using new hybrid data structures and optimized superscalar kernels. The results we survey include new algorithms and library software implementations for level 3 kernels, matrix factorizations, and the solution of general systems of linear equations and several common matrix equations. The software implementations we survey are robust and show impressive performance on today's high performance computing systems.

Place, publisher, year, edition, pages
2004. Vol. 46, no 1, 3-45 p.
Identifiers
URN: urn:nbn:se:umu:diva-21922ISBN: 0036-1445OAI: oai:DiVA.org:umu-21922DiVA: diva2:212177
Available from: 2009-04-21 Created: 2009-04-21 Last updated: 2011-02-22

Open Access in DiVA

No full text

Other links

<Go to ISI>://000189355500001

Search in DiVA

By author/editor
Elmroth, ErikKågström, Bo
By organisation
Department of Computing ScienceHigh Performance Compting Center North (HPC2N)

Search outside of DiVA

GoogleGoogle Scholar

Total: 51 hits
ReferencesLink to record
Permanent link

Direct link