Title :
Parallel Computation of the Singular Value Decomposition on Tree Architectures
Author :
Zhou, B.B. ; Brent, R.P.
Author_Institution :
The Australian National University, Australia
Abstract :
We describe a new Jacobi ordering for parallel computation of SVD problems. The ordering uses the high bandwidth of a perfect binary fat-tree to minimise global interprocessor communication costs. It can thus be implemented efficiently on fat-tree architectures.
Keywords :
Bandwidth; Binary trees; Channel capacity; Computer architecture; Concurrent computing; Costs; Jacobian matrices; Laboratories; Matrix decomposition; Singular value decomposition;
Conference_Titel :
Parallel Processing, 1993. ICPP 1993. International Conference on
Conference_Location :
Syracuse, NY, USA
Print_ISBN :
0-8493-8983-6
DOI :
10.1109/ICPP.1993.135
