Ada: an advanced introduction
Communication effect basic linear algebra computations on hypercube architectures
Journal of Parallel and Distributed Computing
The efficient termination of Ada tasks in a multi-processor environment
ACM SIGAda Ada Letters
C3P Proceedings of the third conference on Hypercube concurrent computers and applications: Architecture, software, computer systems, and general issues - Volume 1
Performance of the Direct Binary n-Cube Network for Multiprocessors
IEEE Transactions on Computers
Task migration in hypercube multiprocessors
ISCA '89 Proceedings of the 16th annual international symposium on Computer architecture
Hi-index | 0.00 |
An important aspect of the efficient use of a hypercube computer to solve a given problem is the assignment of subtasks to processors in such a way that communication overhead is low. Without such strategies the gains in parallelism are negated by the increased communication costs. This paper presents strategies to assign tasks to subcubes of the Hypercube to decrease the communication distance between cooperating tasks of a hypercube computer running the Ada runtime system. Such allocation was not feasible previously because of the limitations imposed by the termination method employed. This paper (1) presents a new, more efficient termination method to solve this problem, (2) a static and (3) a dynamic method to allocate tasks to nodes of the hypercube.