Abstract
Say that a parallel algorithm that uses p processors and N (>p) shared memory locations is given. The problem of simulating this algorithm by p processors and only p shared memory locations without increasing the running time by more than a constant factor is considered. A solution for a family of such parallel algorithms is given. The solution utilizes the idea of dynamically changing locations of the addresses of the algorithm throughout the simulation.
Original language | English |
---|---|
Pages (from-to) | 174-182 |
Number of pages | 9 |
Journal | Information and control |
Volume | 56 |
Issue number | 3 |
DOIs | |
State | Published - Mar 1983 |
Externally published | Yes |