Dynamic Scheduling for Dependence Loops on Heterogeneous Clusters

Distributed computing systems are a viable and less expensive alternative to parallel computers. However, concurrent programming methods in distributed systems have not been studied as extensively as for parallel computers. In the past, a variety of dynamic scheduling schemes suitable for loops with independent iterations on heterogeneous computer clusters have been obtained and studied. However, no study of dynamic schemes for loops with iteration dependencies has been reported so far. In this work we study the problem of scheduling loops with iteration dependencies for heterogeneous clusters. The iteration dependencies incur an extra degree of difficulty and make the development of such schemes quite a challenge. We extend three well known dynamic schemes (CSS, TSS and DTSS) by introducing synchronization points at certain intervals so that processors compute in pipelined fashion. Our scheme is called dynamic multi-phase scheduling (DMPS) and we apply it to loops with iteration dependencies. We implemented our new scheme on a network of heterogeneous computers and studied its performance. Through extensive testing on four real-life applications we show that the proposed method is efficient for parallelizing nested loops with dependencies on heterogeneous systems. Results show that DTSS gives a speedup of 3-5 out of the ideal 7, in all cases, when applied to dependence loops.