Please use this identifier to cite or link to this item:
Title: Accelerating scientific computations with mixed precision algorithms
Authors: Baboulin, Marc 
Buttari, Alfredo 
Dongarra, Jack 
Kurzak, Jakub 
Langou, Julie 
Luszczek, Piotr 
Tomov, Stanimire 
Langou, Julien 
Issue Date: 2008
Publisher: Centro de Matemática da Universidade de Coimbra
Citation: Pré-Publicações DMUC. 08-44 (2008)
Abstract: On modern architectures, the performance of 32-bit operations is often at least twice as fast as the performance of 64-bit operations. By using a combination of 32-bit and 64-bit oating point arithmetic, the performance of many dense and sparse linear algebra algorithms can be signi cantly 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 other technologies such as Field Programmable Gate Arrays (FPGA), Graphical Processing Units (GPU), and the STI Cell BE processor. Results on modern processor architectures and the STI Cell BE are presented.
Rights: openAccess
Appears in Collections:FCTUC Matemática - Vários

Files in This Item:
File Description SizeFormat
Accelerating scientific computations with mixed precision algorithms.pdf207.11 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Aug 19, 2022

Download(s) 20

checked on Aug 19, 2022

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.