Speedup bounds and processor allocation for parallel programs on multiprocessors
Constantine D. Polychronopoulos, Utpal K. Banerjee · Proceedings of the International Conference on Parallel Processing · 1986
The main aim of this paper is to study allocation of processors to parallel programs executing on a multiprocessor system, and the resulting speedups. We first consider a general program represented as a sequence of steps consisting of parallel operations, then one represented as a task graph whose nodes are do across loops and whose edges represent precedence constraints, and finally a single do across loop. General bounds on program speedup are discussed and measurements of code parallelism for the LINPACK numerical package are presented. 11 refs., 4 figs.