Remora : implementing adaptive parallelism on a heterogeneous cluster of networked workstations
- Authors: Rehmet, Geoffrey Michael
- Date: 1995
- Subjects: LINDA (Computer system) , Local area networks (Computer networks) , Computer networks , Remora (Computer system)
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4673 , http://hdl.handle.net/10962/d1006696 , LINDA (Computer system) , Local area networks (Computer networks) , Computer networks , Remora (Computer system)
- Description: Computers connected to a local area network are often only fully utilized for short periods of time. In fact, most workstations are not used at all for a significant portion of the day. The combined "idle time" of the workstations on a network constitutes a significant computing resource, which is generally wasted. If harnessed properly, such a resource could constitute a cheap alternative to expensive high-performance computers. Adaptive parallelism refers to the parallel execution of a computation on a dynamically changing set of processors. This thesis investigates the viability of this approach as a vehicle to harness the "idle cycles" available on a heterogeneous cluster of networked computers. A system, called Remora, which implements adaptive parallelism via the Linda programming paradigm, is presented. Experiments, performed using Remora, show that adaptive parallelism provides an efficient vehicle for using idle processor cycles, without having an adverse effect on the tasks which constitute the normal workload of the computers being used.
- Full Text:
- Date Issued: 1995
- Authors: Rehmet, Geoffrey Michael
- Date: 1995
- Subjects: LINDA (Computer system) , Local area networks (Computer networks) , Computer networks , Remora (Computer system)
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4673 , http://hdl.handle.net/10962/d1006696 , LINDA (Computer system) , Local area networks (Computer networks) , Computer networks , Remora (Computer system)
- Description: Computers connected to a local area network are often only fully utilized for short periods of time. In fact, most workstations are not used at all for a significant portion of the day. The combined "idle time" of the workstations on a network constitutes a significant computing resource, which is generally wasted. If harnessed properly, such a resource could constitute a cheap alternative to expensive high-performance computers. Adaptive parallelism refers to the parallel execution of a computation on a dynamically changing set of processors. This thesis investigates the viability of this approach as a vehicle to harness the "idle cycles" available on a heterogeneous cluster of networked computers. A system, called Remora, which implements adaptive parallelism via the Linda programming paradigm, is presented. Experiments, performed using Remora, show that adaptive parallelism provides an efficient vehicle for using idle processor cycles, without having an adverse effect on the tasks which constitute the normal workload of the computers being used.
- Full Text:
- Date Issued: 1995
Analyzing communication flow and process placement in Linda programs on transputers
- De-Heer-Menlah, Frederick Kofi
- Authors: De-Heer-Menlah, Frederick Kofi
- Date: 1992 , 2012-11-28
- Subjects: LINDA (Computer system) , Transputers , Parallel programming (Computer science)
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4675 , http://hdl.handle.net/10962/d1006698 , LINDA (Computer system) , Transputers , Parallel programming (Computer science)
- Description: With the evolution of parallel and distributed systems, users from diverse disciplines have looked to these systems as a solution to their ever increasing needs for computer processing resources. Because parallel processing systems currently require a high level of expertise to program, many researchers are investing effort into developing programming approaches which hide some of the difficulties of parallel programming from users. Linda, is one such parallel paradigm, which is intuitive to use, and which provides a high level decoupling between distributable components of parallel programs. In Linda, efficiency becomes a concern of the implementation rather than of the programmer. There is a substantial overhead in implementing Linda, an inherently shared memory model on a distributed system. This thesis describes the compile-time analysis of tuple space interactions which reduce the run-time matching costs, and permits the distributon of the tuple space data. A language independent module which partitions the tuple space data and suggests appropriate storage schemes for the partitions so as to optimise Linda operations is presented. The thesis also discusses hiding the network topology from the user by automatically allocating Linda processes and tuple space partitons to nodes in the network of transputers. This is done by introducing a fast placement algorithm developed for Linda. , KMBT_223
- Full Text:
- Date Issued: 1992
- Authors: De-Heer-Menlah, Frederick Kofi
- Date: 1992 , 2012-11-28
- Subjects: LINDA (Computer system) , Transputers , Parallel programming (Computer science)
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4675 , http://hdl.handle.net/10962/d1006698 , LINDA (Computer system) , Transputers , Parallel programming (Computer science)
- Description: With the evolution of parallel and distributed systems, users from diverse disciplines have looked to these systems as a solution to their ever increasing needs for computer processing resources. Because parallel processing systems currently require a high level of expertise to program, many researchers are investing effort into developing programming approaches which hide some of the difficulties of parallel programming from users. Linda, is one such parallel paradigm, which is intuitive to use, and which provides a high level decoupling between distributable components of parallel programs. In Linda, efficiency becomes a concern of the implementation rather than of the programmer. There is a substantial overhead in implementing Linda, an inherently shared memory model on a distributed system. This thesis describes the compile-time analysis of tuple space interactions which reduce the run-time matching costs, and permits the distributon of the tuple space data. A language independent module which partitions the tuple space data and suggests appropriate storage schemes for the partitions so as to optimise Linda operations is presented. The thesis also discusses hiding the network topology from the user by automatically allocating Linda processes and tuple space partitons to nodes in the network of transputers. This is done by introducing a fast placement algorithm developed for Linda. , KMBT_223
- Full Text:
- Date Issued: 1992
- «
- ‹
- 1
- ›
- »