Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Integer k-matching preclusion of some interconnection networks
AbstractFor a positive integer k, a k-matching of a graph G is a function f: E ( G ) → { 0 , 1 , … , k } such that ∑ e ∈ Γ ( v ) f ( e ) ≤ k for every vertex v of G, where Γ ( v ) represents the set of all edges incident to v. The (strong) k-matching ...
- ArticleDecember 2021
Completely Independent Spanning Trees in the Line Graphs of Torus Networks
Algorithms and Architectures for Parallel ProcessingPages 540–553https://doi.org/10.1007/978-3-030-95391-1_34AbstractDue to the application in reliable information transmission, parallel transmission and safe distribution of information, and parallel diagnosis algorithm for faulty servers, completely independent spanning trees (CISTs) play important roles in the ...
- articleApril 2017
Topology mapping of irregular parallel applications on torus-connected supercomputers
The Journal of Supercomputing (JSCO), Volume 73, Issue 4Pages 1691–1714https://doi.org/10.1007/s11227-016-1876-7Supercomputers with ever increasing computing power are being built for scientific applications. As the system size scales up, so does the size of interconnect network. As a result, communication in supercomputers becomes increasingly expensive due to ...
- articleMay 2015
Hierarchical task mapping for parallel applications on supercomputers
The Journal of Supercomputing (JSCO), Volume 71, Issue 5Pages 1776–1802https://doi.org/10.1007/s11227-014-1324-5As the scale of supercomputers grows, so does the size of the interconnect network. Topology-aware task mapping, which maps parallel application processes onto processors to reduce communication cost, becomes increasingly important. Previous works ...
- ArticleFebruary 2014
The Multi-level Communication: Minimal Deadlock-Free and Storage Efficient Routing for Torus Networks
PDP '14: Proceedings of the 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based ProcessingPages 44–51https://doi.org/10.1109/PDP.2014.12In this paper, we recall the methodology, proposed in [7], for constructing correct and efficient routing strategies for distributed memory multicomputers. As the methodology is based on a primary communication scheme, we choose routing by Eulerian ...
- articleMay 2013
The design of ultra scalable MPI collective communication on the K computer
- Tomoya Adachi,
- Naoyuki Shida,
- Kenichi Miura,
- Shinji Sumimoto,
- Atsuya Uno,
- Motoyoshi Kurokawa,
- Fumiyoshi Shoji,
- Mitsuo Yokokawa
Computer Science - Research and Development (SPCS), Volume 28, Issue 2-3Pages 147–155https://doi.org/10.1007/s00450-012-0211-7This paper proposes the design of ultra scalable MPI collective communication for the K computer, which consists of 82,944 computing nodes and is the world's first system over 10 PFLOPS. The nodes are connected by a Tofu interconnect that introduces six ...
- articleFebruary 2011
Broadcastings and digit tilings on three-dimensional torus networks
Theoretical Computer Science (TCSC), Volume 412, Issue 4-5Pages 307–319https://doi.org/10.1016/j.tcs.2010.09.028A tiling in a finite abelian group H is a pair (T,L) of subsets of H such that any h@?H can be uniquely represented as t+l where t@?T and l@?L. This paper studies a finite analogue of self-affine tilings in Euclidean spaces and applies it to a problem ...
- articleApril 2009
Edge-disjoint spanners in tori
Discrete Mathematics (DMAT), Volume 309, Issue 8Pages 2239–2249https://doi.org/10.1016/j.disc.2008.04.063A spanning subgraph S=(V,E^') of a connected graph G=(V,E) is an (x+c)-spanner if for any pair of vertices u and v, d"S(u,v)@?d"G(u,v)+c where d"G and d"S are the usual distance functions in G and S, respectively. The parameter c is called the delay of ...