Stardust: An Environment for Parallel Programming on Networks of Heterogeneous Workstations

Cabillic, Gilbert; Puaut, Isabelle

doi:10.1006/jpdc.1996.1271

Cited by 20 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SDSMs can be run on top of``found'' resources, such as idle workstations on desks or clusters of multiprocessors [10,20,26]. SDSMs can be run on top of heterogeneous systems [5,27]. SDSMs support a variety of standard parallel interfaces, from the ANL macros used in the original SPLASH benchmark suite to OpenMP [8].…”

Section: Introductionmentioning

confidence: 99%

The Impact of Symmetry on Software Distributed Shared Memory

Keleher¹

2000

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

The Impact of Symmetry on Software Distributed Shared Memory

Keleher¹

2000

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…This is a limitation for LBDCS and many other similar architecture glued systems. With availability of very high performance WS architectures and communication speeds, architecture independent task migration is expected to be feasible for more and more applications [13]. Currently LBDCS is experimented on a small NOW for small applications.…”

Section: Resultsmentioning

confidence: 99%

“…The Stardust project presented by G. Cabicclic and I. Puaut [13] suggests a system which under a set of restrictions can allow migration of buffers or shared virtual memory regions. The system is primarily SPMD (single program multiple data) based.…”

Section: Migration Based Load Balancingmentioning

confidence: 99%

A load balanced distributed computing system

Bozyiğit

AlGhamdi

Ghouseuddin

et al. 1999

Concurrency: Pract. Exper.

View full text Add to dashboard Cite

“…Process migration among heterogeneous hosts is complex and appears to restrict significantly the permitted application behaviour. 23,24 Star is implemented on top of a Unix operating system (SunOs). It works on a set of workstations (hosts) connected by a local area network (Ethernet).…”

Section: Environmentmentioning

confidence: 99%

The STAR fault manager for distributed operating environments. design, implementation and performance

Sens¹,

Folliot²

1998

Softw: Pract. Exper.

View full text Add to dashboard Cite

This paper presents the design, implementation and performance evaluation of a software fault manager for distributed applications. Dubbed Star, it uses the natural redundancy existing in networks of workstations to offer a high level of fault tolerance. Fault management is transparent to the supported parallel applications. To improve the response time of fault-tolerant applications, Star implements non-blocking and incremental checkpointing to perform an efficient backup of process state. Moreover, Star is application independent, highly configurable. Star actually runs on top of SunOs and is easily portable to UNIX™-like operating systems. The current implementation is based on independent checkpointing and message logging. Measurements show the efficiency and the limits of this implementation.The challenge is to show that a software approach to fault tolerance can efficiently be implemented in a standard networked environment.

show abstract

Stardust: An Environment for Parallel Programming on Networks of Heterogeneous Workstations

Cited by 20 publications

References 25 publications

The Impact of Symmetry on Software Distributed Shared Memory

The Impact of Symmetry on Software Distributed Shared Memory

A load balanced distributed computing system

The STAR fault manager for distributed operating environments. design, implementation and performance

Contact Info

Product

Resources

About