A Fast and Efficient Processor Allocation Strategy which Combines a Contiguous and Non-contiguous Processor Allocation Algorithms

Two strategies are used for the allocation of jobs to processors connected by mesh topologies: contiguous allocation and non-contiguous allocation. In non-contiguous allocation, a job request can be split into smaller parts that are allocated possibly non-adjacent free sub-meshes rather than always waiting until a single submesh of the requested size and shape is available. Lifting the contiguity condition is expected to reduce processor fragmentation and increase system utilization. However, the distances traversed by messages can be long, and as a result the communication overhead, especially contention, is increased. The extra communication overhead depends on how the allocation request is partitioned and assigned to free submeshes. This paper presents a new Non-contiguous allocation algorithm, referred to as Greedy-AvailableBusy-List (GABL for short), which can decrease the communication overhead among processors allocated to a given parallel job. The GABL algorithm relies on a new approach that decomposes the allocation requests based on the sub-meshes available for allocation. This decreases the number of sub-meshes allocated to a job, hence decreases the distance traversed by messages, and which in turn decreases the communication overhead. In addition to allocation strategies, two job scheduling strategies, referred to as First-Come-First-Served (FCFS) and Shortest-Service-Demand-First (SSD) are studied, and they are used to compare the performance of allocation strategies. To evaluate the performance improvement achieved by our strategy and compare it against well-known existing non-contiguous and contiguous strategies, we conduct extensive simulation runs under the assumption of wormhole routing and two communication patterns, notably one-to-all and all-to-all. The results show that the new strategy can reduce the communication overhead and substantially improve performance in terms of parameters such as job turnaround time and system utilization. Moreover, the results reveal that the SSD scheduling strategy is much better than the FCFS scheduling strategy, therefore, the scheduling and allocation strategies both have substantial effect on the performance of contiguous and noncontiguous allocation strategies in 2D mesh.