Microprogrammable parallel computer: MUNAP and its applications
Microprogrammable parallel computer: MUNAP and its applications
Interprocessor Traffic Scheduling Algorithm for Multiple-Processor Networks
IEEE Transactions on Computers
A Mapping Strategy for Parallel Processing
IEEE Transactions on Computers
Nearest-neighbor mapping of finite element graphs onto processor meshes
IEEE Transactions on Computers
On the Communication Complexity of Generalized 2-D Convolution on Array Processors
IEEE Transactions on Computers
On the Number of Acceptable Task Assignments in Distributed Computing Systems
IEEE Transactions on Computers
A parallel object-oriented total architecture: A–NET
Proceedings of the 1990 ACM/IEEE conference on Supercomputing
PACS: a parallel microprocessor array for scientific calculations
ACM Transactions on Computer Systems (TOCS)
Computer Architecture and Parallel Processing
Computer Architecture and Parallel Processing
A parallel object-oriented total architecture: A–NET
Proceedings of the 1990 ACM/IEEE conference on Supercomputing
The Journal of Supercomputing
Topology-aware task mapping for reducing communication contention on large parallel machines
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Hi-index | 0.00 |
A network-topology, independent practical task allocation strategy has been designed and implemented for parallel computers. For mapping a task graph to a processor graph, this strategy evaluates several functions that represent some intuitively feasible properties of the graphs. Several strategies are defined to guide the mapping process, utilizing the indicated values.An allocation system has been designed and implemented based on this strategy. The experimental results indicate the following: 1) the system can yield 2.14 times better allocation than an arbitrary allocation, 2) it is difficult to select a single strategy capable of providing the best solutions for a wide range of task-processor combinations, and 3) the computation time of the allocator is reasonable.The effect of task and processor topology combinations on the allocation results is also discussed.