Agent, genetic algorithm with task duplication based scheduling technique for heterogenous systems

Simple item page
dc.contributor.authorSidhu, Navdeep
dc.contributor.examiningcommitteeGraham, Peter (Computer Science)en_US
dc.contributor.examiningcommitteeCai, Jun (Electrical and Computer Engineering)en_US
dc.contributor.supervisorThulasiraman, Parimala (Computer Science)en_US
dc.date.accessioned2018-09-08T13:32:06Z
dc.date.available2018-09-08T13:32:06Z
dc.date.issued2018-08-16en_US
dc.date.submitted2018-08-29T15:20:09Zen
dc.degree.disciplineComputer Scienceen_US
dc.degree.levelMaster of Science (M.Sc.)en_US
dc.description.abstractHigh-Performance Computing (HPC) is used to solve complex problems in parallel for in- creased performance. Over the past few years, parallelization has become more challenging with the many core general purpose systems and accelerators. One of the challenges is in better utilization of the resources available on these architectures through better task scheduling strategies. In this thesis I consider a distributed, heterogeneous network with general processing CPU based systems of varying speed and architectures. I propose an efficient mapping and scheduling of tasks to processors using agents to explore the network and Genetic Algorithm with Task Duplication Scheduling(GATDS) to schedule the tasks. The SIPS (Serial algorithms In Parallel System) framework is used to exploit parallelism using abstract syntax trees generated directly from the source code. This framework helps in automating the process of converting serial code for use in parallel systems, thus reducing the overhead of writing parallel code. GATDS is compared with various scheduling strategies for task independent and task dependent problems. The performance of GATDS is comparable to the use of existing genetic algorithms for task independent problems. For inter-dependant tasks, the proposed technique matches or performs better than the traditional Chunk scheduler and genetic algorithm 75 % of the time. GATDS also provides better resource utilization.en_US
dc.description.noteOctober 2018en_US
dc.identifier.citationSidhu, Navdeep Singh, Parimala Thulasiraman, and Ruppa Thulasiraman. "Agent, Genetic Algorithm with Task Duplication Based Scheduling Technique For Heterogenous Systems." Proceedings of the Annual Conference of the Administrative Sciences Association of Canada, Management Science Division, May 26-29, 2018, 43-81.en_US
dc.identifier.urihttp://hdl.handle.net/1993/33261
dc.language.isoengen_US
dc.rightsopen accessen_US
dc.subjectGA - Genetic Algorithmen_US
dc.subjectTDS - Task Duplication Strategy/Schedulingen_US
dc.subjectSIPS - Serial Algorithms in Parallel Systemen_US
dc.subjectGA-TDS - Genetic Algorithm with Task Duplication Schedulingen_US
dc.subjectDAG - Directed Acyclic Graphen_US
dc.subjectHPC - High Performance Computingen_US
dc.titleAgent, genetic algorithm with task duplication based scheduling technique for heterogenous systemsen_US
dc.typemaster thesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sidhu_Navdeep.pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
Description:
Main Thesis
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.2 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica