On partitioning and mapping for hypercube computing
Journal Article
·
· International Journal of Parallel Programming; (USA)
- Michigan State Univ., East Lansing (USA)
- New Jersey Institute of Technology, Newark (USA)
Designing efficient parallel algorithms in a message-based parallel computer should consider both time-space tradeoffs and computation-communication tradeoffs. In order to balance these tradeoffs and achieve the optimal performance of an algorithm, one has to consider various design parameters such as the number of processors required and the size of partitions. In this paper, the authors demonstrate that, for certain data parallel algorithms, it is possible to determine these design parameters analytically. To serve as a basis for the discussions that follow, a simple model for the NCUBE hypercube computer is introduced. Using this model, they use two examples, array summation and matrix multiplication, to illustrate how their performance can be modeled. By optimizing these expressions, one is able to determine optimal design parameters which arrive at efficient execution. Experiments on a 64-node NCUBE verified the accuracy of the analytic results and are used to further support the discussions.
- OSTI ID:
- 6389121
- Journal Information:
- International Journal of Parallel Programming; (USA), Journal Name: International Journal of Parallel Programming; (USA) Vol. 17:6; ISSN IJPPE; ISSN 0885-7458
- Country of Publication:
- United States
- Language:
- English
Similar Records
Computing the Hough transform on an MIMD hypercube
Large-grain pipelining on hypercube multiprocessors
On mapping systolic algorithms onto the hypercube
Conference
·
Sat Dec 31 23:00:00 EST 1988
·
OSTI ID:5970445
Large-grain pipelining on hypercube multiprocessors
Conference
·
Thu Dec 31 23:00:00 EST 1987
·
OSTI ID:6792166
On mapping systolic algorithms onto the hypercube
Journal Article
·
Sun Dec 31 23:00:00 EST 1989
· IEEE Transactions on Parallel and Distributed Systems; (USA)
·
OSTI ID:6541103
Related Subjects
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ALGORITHMS
ARRAY PROCESSORS
COMMUNICATIONS
COMPUTER ARCHITECTURE
COMPUTERS
DATA PROCESSING
DATA TRANSMISSION
DESIGN
DIGITAL COMPUTERS
EFFICIENCY
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
MEMORY DEVICES
OPTIMIZATION
PARALLEL PROCESSING
PARAMETRIC ANALYSIS
PERFORMANCE
PERFORMANCE TESTING
PLANNING
PROCESSING
PROGRAMMING
SUPERCOMPUTERS
TASK SCHEDULING
TESTING
TIMING PROPERTIES
990200* -- Mathematics & Computers
ALGORITHMS
ARRAY PROCESSORS
COMMUNICATIONS
COMPUTER ARCHITECTURE
COMPUTERS
DATA PROCESSING
DATA TRANSMISSION
DESIGN
DIGITAL COMPUTERS
EFFICIENCY
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
MEMORY DEVICES
OPTIMIZATION
PARALLEL PROCESSING
PARAMETRIC ANALYSIS
PERFORMANCE
PERFORMANCE TESTING
PLANNING
PROCESSING
PROGRAMMING
SUPERCOMPUTERS
TASK SCHEDULING
TESTING
TIMING PROPERTIES