A balanced submatrix merging algorithm for multiprocessor architectures (Q1185909)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: A balanced submatrix merging algorithm for multiprocessor architectures |
scientific article; zbMATH DE number 35977
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A balanced submatrix merging algorithm for multiprocessor architectures |
scientific article; zbMATH DE number 35977 |
Statements
A balanced submatrix merging algorithm for multiprocessor architectures (English)
0 references
28 June 1992
0 references
The authors design parallel algorithms for merging two \(k\times n\) (\(k\leq n\)) upper trapezoidal submatrices on a pair of directly connected local- memory processors or two clusters of tightly-coupled processors. It is shown that in both environments the work load is evenly distributed, communication can be well masked by computation, and the optimal speedup may be achieved.
0 references
Givens rotations
0 references
merging algorithm
0 references
multiprocessor machines
0 references
large scale least squares computations
0 references
parallel algorithms
0 references
