Improving Gang scheduling through job performance analysis and malleability

Proceedings of the International Conference on Supercomputing

Volumn , Issue , 2001, Pages 303-311

  Corbalan, J ^a   Martorell, X ^a   Labarta, J ^a  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; JOB ANALYSIS; PROGRAM PROCESSORS; SCHEDULING;

GANG SCHEDULING;

PARALLEL PROCESSING SYSTEMS;

EID: 0034832381     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/377792.377852     Document Type: Conference Paper

References (27)

1. Performance-driven processor allocation
2. Improving processor allocation through run-time measured efficiency
3. Packing schemes for gang scheduling
4. Job scheduling in multiprogrammed parallel systems
5. Improved utilization and responsiveness with gang scheduling
6. Distributed hierarchical control for parallel processing
7. Toward convergence in job schedulers for parallel supercomputers
8. Evaluation of design choices for gang scheduling using distributed hierarchical control
9. Utilization and predictability in scheduling the IBM SP2 with backfilling
10. The effect of correlating quantum allocation and job size for gang scheduling
11. The ANL/IBM SP scheduling system
12. Scheduling in multi-programmed parallel systems
13. A dynamic processor allocation policy for multiprogrammed shared-memory multiprocessors
14. Using runtime measured workload characteristics in parallel processors scheduling
15. Scheduling techniques for concurrent systems
16. Trace-driven analysis of migration-based gang scheduling policies for parallel computers
17. Improving throughput and utilization in parallel machines through concurrent gang
18. Improving parallel job scheduling using runtime measurements
19. Process control and scheduling issues for multiprogrammed shared-memory multiprocessors
20. The MIPS R10000 superscalar microprocessor
21. Resource allocation schemes for gang scheduling
22. Improving parallel job scheduling by combining gang scheduling and backfilling techniques