Abstract
Contiguous allocation of parallel jobs usually suffers from the degrading effects of fragmentation, because it requires that the alio-cated processors be contiguous and have the same topology as the network topology connecting these processors. This paper suggests two non-contiguous processor allocation strategies, referred to as Paging and Greedy-Available respectively, for the 3D mesh network and compares their performance using software simulation against the well-known contiguous First Fit strategy. The comparative evaluation is conducted for two job scheduling strategies, notably first-come-first-served (FCFS) and out-of-order (OO). The results reveal that our proposed non-contiguous strategies exhibit superior performance properties despite the added contention that results from non-contiguity. The results also reveal that the scheduling and allocation strategies both have substantial effect on the performance of contiguous and non-contiguous allocation in that the OO scheduling strategy leads to much better performance than its FCFS counterpart in the 3D mesh.
| Original language | English |
|---|---|
| Pages (from-to) | 309-317 |
| Number of pages | 9 |
| Journal | International Journal of Computers and Applications |
| Volume | 29 |
| Issue number | 3 |
| Publication status | Published - 2007 |
Fingerprint
Keywords
- Dispersal ratio
- External message interference
- Fragmentation
- Multicomputer
- Scheduling effectiveness
- Turnaround time
ASJC Scopus subject areas
- Hardware and Architecture
Cite this
Processor allocation and job scheduling on 3D mesh interconnection networks. / Mohammad, S. B.; Khaoua, M. O.; Mackenzie, L. M.; Ababneh, I.
In: International Journal of Computers and Applications, Vol. 29, No. 3, 2007, p. 309-317.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Processor allocation and job scheduling on 3D mesh interconnection networks
AU - Mohammad, S. B.
AU - Khaoua, M. O.
AU - Mackenzie, L. M.
AU - Ababneh, I.
PY - 2007
Y1 - 2007
N2 - Contiguous allocation of parallel jobs usually suffers from the degrading effects of fragmentation, because it requires that the alio-cated processors be contiguous and have the same topology as the network topology connecting these processors. This paper suggests two non-contiguous processor allocation strategies, referred to as Paging and Greedy-Available respectively, for the 3D mesh network and compares their performance using software simulation against the well-known contiguous First Fit strategy. The comparative evaluation is conducted for two job scheduling strategies, notably first-come-first-served (FCFS) and out-of-order (OO). The results reveal that our proposed non-contiguous strategies exhibit superior performance properties despite the added contention that results from non-contiguity. The results also reveal that the scheduling and allocation strategies both have substantial effect on the performance of contiguous and non-contiguous allocation in that the OO scheduling strategy leads to much better performance than its FCFS counterpart in the 3D mesh.
AB - Contiguous allocation of parallel jobs usually suffers from the degrading effects of fragmentation, because it requires that the alio-cated processors be contiguous and have the same topology as the network topology connecting these processors. This paper suggests two non-contiguous processor allocation strategies, referred to as Paging and Greedy-Available respectively, for the 3D mesh network and compares their performance using software simulation against the well-known contiguous First Fit strategy. The comparative evaluation is conducted for two job scheduling strategies, notably first-come-first-served (FCFS) and out-of-order (OO). The results reveal that our proposed non-contiguous strategies exhibit superior performance properties despite the added contention that results from non-contiguity. The results also reveal that the scheduling and allocation strategies both have substantial effect on the performance of contiguous and non-contiguous allocation in that the OO scheduling strategy leads to much better performance than its FCFS counterpart in the 3D mesh.
KW - Dispersal ratio
KW - External message interference
KW - Fragmentation
KW - Multicomputer
KW - Scheduling effectiveness
KW - Turnaround time
UR - http://www.scopus.com/inward/record.url?scp=35048894871&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=35048894871&partnerID=8YFLogxK
M3 - Article
VL - 29
SP - 309
EP - 317
JO - International Journal of Computers and Applications
JF - International Journal of Computers and Applications
SN - 1206-212X
IS - 3
ER -