A fast and scalable scheduling algorithm for distributed memory systems

A Task Duplication Based Scalable Scheduling Algorithm for Distributed Memory Systems

“…The first case is if the condition stated in Section 2 is satisfied and the required number of processors are available. In this case, optimal schedule is guaranteed and the proof is shown in [8,9]. Next, the cases where either the condition is not necessarily satisfied, or the required number of processors is not available is considered.…”

DFRN: a new approach for duplication based scheduling for distributed memory multiprocessor systems

“…Like SDBS [13] algorithm, the FSS [18] algorithm first calculates the start time and the completion time of each node by traversing the input DAG. The algorithm then generates clusters by performing depth first search starting from the exit node.…”

“…(10) endif (11) else // if Vi is a join node (12) identify CIP and Pc (13) if CIP is LN (14) DFRN (Pc ,Vi) // apply DFRN to Pc (15) else // if CIP is not LN (16) copy the schedule up to CIP onto Pu (17) DFRN (Pu ,Vi) // apply DFRN to Pu (18) endif (19) …”

“…Since HNF is chosen as the node selection method, the effect of task duplication can be easily seen by comparing HNF with DFRN. From SPD algorithms, a more recent one, FSS [18] is chosen for comparison. CPFD is chosen from SFD algorithms since it has been shown that CPFD outperforms DSH and BTDH [9].…”

“…They typically provide good schedules for an input DAG where computation cost is strictly larger than communication cost. CPM [12], SDBS [13], and FSS [18] belong to this category.…”