TY - GEN
T1 - An efficient processor allocation strategy that maintains a high degree of contiguity among processors in 2D mesh connected multicomputers
AU - Bani-Mohammad, S.
AU - Ould-Khaoua, M.
AU - Ababneh, I.
AU - Mackenzie, Lewis M.
PY - 2007
Y1 - 2007
N2 - Two strategies are Used for the allocation of jobs to processors connected by mesh topologies: contiguous allocation and non-contiguous allocation. In noncontiguous allocation, a job request can be split into smaller parts that are allocated to non-adjacent free submeshes 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 sub-meshes. This paper presents a new Noncontiguous allocation algorithm, referred to as GreedyAvailable-Busy-List (GABL for short), which can decrease the communication overhead among processors allocated to a given job. The simulation 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 ShortestService-Demand-First (SSD) scheduling strategy is much better than the First-Come-First-Served (FCFS) scheduling strategy.
AB - Two strategies are Used for the allocation of jobs to processors connected by mesh topologies: contiguous allocation and non-contiguous allocation. In noncontiguous allocation, a job request can be split into smaller parts that are allocated to non-adjacent free submeshes 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 sub-meshes. This paper presents a new Noncontiguous allocation algorithm, referred to as GreedyAvailable-Busy-List (GABL for short), which can decrease the communication overhead among processors allocated to a given job. The simulation 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 ShortestService-Demand-First (SSD) scheduling strategy is much better than the First-Come-First-Served (FCFS) scheduling strategy.
UR - http://www.scopus.com/inward/record.url?scp=36249009021&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=36249009021&partnerID=8YFLogxK
U2 - 10.1109/AICCSA.2007.370743
DO - 10.1109/AICCSA.2007.370743
M3 - Conference contribution
AN - SCOPUS:36249009021
SN - 1424410312
SN - 9781424410316
T3 - 2007 IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2007
SP - 934
EP - 941
BT - 2007 IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2007
T2 - 2007 IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2007
Y2 - 13 May 2007 through 16 May 2007
ER -