PLAPACK: Parallel Linear Algebra Package

Overview and Purpose

Coding parallel algorithms is generally regarded as a formidable task. The Parallel Linear Algebra Package (PLAPACK), an infrastructure for coding such algorithms at a high level of abstraction, has been developed to make this task manageable in the arena of linear algebra algorithms. It is often believed that by raising the level of abstraction in this fashion, performance is sacrificed. But tby coding at a higher level of abstraction, more sophisticated algorithms can be implemented, which allows high levels of performance to be regained.

Autors of the Library:

Dr. Robert A. van de Geijn, Associate Professor of Computer Sciences
Department of Computer Sciences and Texas Institute for Computational and Applied Mathematics The University of Texas at Austin
Austin, TX 78712
Office: Taylor 4.115C
Phone: (512) 471-9720
Fax: (512) 471-8885

Dr. Greg Morrow Postdoctoral Fellow
John Gunnels Ph.D. Student in Computer Sciences
Jay Howard Ph.D. Student in Computer Sciences
Thierry Joffrain Undergraduate Student in Computer Sciences
James Overfelt Ph.D. Student in Computational and Applied Mathematics
Beatrice Rivier Ph.D. Student in Computational and Applied Mathematics

Supported Platforms at LRZ:

Platform Processor Type Location of the Library
Hitachi SR8000   /usr/local/lib/
LINUX Cluster Intel Pentium /usr/local/lib/

Contact Point at LRZ

For questions concerning the usage of the PLAPACK library at LRZ contact:

  • Dr. Matthias Brehm, , Phone: (089) 35831-8773

Further Information