Details

Autor(en) / Beteiligte

• Buttari, Alfredo
• Dongarra, Jack
• Langou, Julie
• Langou, Julien
• Luszczek, Piotr
• Kurzak, Jakub

Titel

Mixed Precision Iterative Refinement Techniques for the Solution of Dense Linear Systems

Ist Teil von

• The international journal of high performance computing applications, 2007-11, Vol.21 (4), p.457-466

Ort / Verlag

London, England: Sage Publications

Erscheinungsjahr

2007

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• By using a combination of 32-bit and 64-bit floating point arithmetic, the performance of many dense and sparse linear algebra algorithms can be significantly enhanced while maintaining the 64-bit accuracy of the resulting solution. The approach presented here can apply not only to conventional processors but also to exotic technologies such as Field Programmable Gate Arrays (FPGA), Graphical Processing Units (GPU), and the Cell BE processor. Results on modern processor architectures and the Cell BE are presented.