Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Com 2007
DOI: 10.1109/snpd.2007.51
|View full text |Cite
|
Sign up to set email alerts
|

Matrix Multiplication on the Biswapped-Mesh Network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
4
0

Year Published

2008
2008
2018
2018

Publication Types

Select...
3
3
1

Relationship

3
4

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 21 publications
0
4
0
Order By: Relevance
“…In this paper, we develop deterministic algorithms of basic communication operation for parallel computation on the BSN, such as broadcast, prefix sum and data sum etc, and analyze time complexity of these algorithms. According to [4], we know BSN has better topological properties than OTIS, the basic communication operation algorithms on the BSN proposed by us, are more general and better than those on OTIS-Mesh. For example, in a 2n 2 processors BSN-Mesh, our broadcast algorithm's time complexity is 2 …”
Section: Introductionmentioning
confidence: 98%
See 1 more Smart Citation
“…In this paper, we develop deterministic algorithms of basic communication operation for parallel computation on the BSN, such as broadcast, prefix sum and data sum etc, and analyze time complexity of these algorithms. According to [4], we know BSN has better topological properties than OTIS, the basic communication operation algorithms on the BSN proposed by us, are more general and better than those on OTIS-Mesh. For example, in a 2n 2 processors BSN-Mesh, our broadcast algorithm's time complexity is 2 …”
Section: Introductionmentioning
confidence: 98%
“…BSN is built of 2n copies of an n-node basic network using a simple rule for connectivity that ensures its regularity, modularity, fault tolerance, and algorithmic efficiency. Some topological properties of BSN have been investigated [3], and some algorithms have been developed on the BSN such as sorting and matrix multiplication etc [4].…”
Section: Introductionmentioning
confidence: 99%
“…In particular, if the basic network is a Cayley digraph then so is the BSN, thus a systematic construction of large, scalable, modular, and robust parallel architectures are given, while maintaining many desirable attributes of the underlying basic network that comprises its clusters. Similar to OTIS network, some topological properties of BSN have been investigated [6], and lots of algorithms such as basic communication operations algorithms, matrix multiplication algorithm, parallel sorting algorithm and fault tolerance on the BSN have been developed [7][8][9][10].…”
Section: Introductionmentioning
confidence: 99%
“…In this paper, we first define the single-source-weighted mu lti-level graph model, and then by constructing a vectormatrix mu ltip le model [8] [9], d ividing into parallel tasks and setting data communication's method, we give a parallel algorith m to solve the shortest path problem of the singlesource multi-level g raph. Through pseudo-code, we analyze some impo rtant performance index of parallel algorith m in theory and make lots of experimental validation.…”
Section: Introductionmentioning
confidence: 99%