Or-parallel Prolog on a distributed memory architecture

Silva, Fernando M. A.; Watson, Paul

doi:10.1016/s0743-1066(99)00064-3

Cited by 7 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research on execution of logic programs on Distributed Memory architectures (e.g., [Benjumea and Troya 1993;Kacsuk and Wise 1992]) has been more sparse and perhaps less incisive. Currently, there is renewed interest in distributed memory architectures [Silva and Watson 2000;Araujo and Ruz 1998;Castro et al 1999;Gupta and Pontelli 1999c;Hermenegildo 1994;Cabeza and Hermenegildo 1996], thanks to their increased availability at affordable prices and their scalability. Nevertheless, the focus of this survey is on describing execution models for shared memory architectures.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Parallel execution of prolog programs

Gupta

Pontelli

Ali

et al. 2001

ACM Trans. Program. Lang. Syst.

116

View full text Add to dashboard Cite

Since the early days of logic programming, researchers in the field realized the potential for exploitation of parallelism present in the execution of logic programs. Their high-level nature, the presence of non-determinism, and their referential transparency, among other characteristics, make logic programs interesting candidates for obtaining speedups through parallel execution. At the same time, the fact that the typical applications of logic programming frequently involve irregular computations, make heavy use of dynamic data structures with logical variables, and involve search and speculation, makes the techniques used in the corresponding parallelizing compilers and run-time systems potentially interesting even outside the field. The objective of this paper is to provide a comprehensive survey of the issues arising in parallel execution of logic programming languages along with the most relevant approaches explored to date in the field. Focus is mostly given to the challenges emerging from the parallel execution of Prolog programs. The paper describes the major techniques used for shared memory implementation of Or-parallelism, Andparallelism, and combinations of the two. We also explore some related issues, such as memory management, compile-time analysis, and execution visualization.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The Binding Array model has also been adapted for distributed shared memory architectures and implemented in the Dorpp system [Silva and Watson 2000].…”

Section: 51mentioning

confidence: 99%

Parallel execution of prolog programs

Gupta

Pontelli

Ali

et al. 2001

ACM Trans. Program. Lang. Syst.

116

View full text Add to dashboard Cite

show abstract

“…However, both the Opera system and the Benjumea's system have been developed on now-obsolete Transputer hardware, and, additionally, both rely on a stack-copying mechanism which will produce poor performance in programs where the task-granularity is small. A different approach has been suggested by Silva and Watson with their DORPP model (Silva and Watson 2000), which extends the binding array scheme Lusk et al (1990) to a distributed setting, relying on the European Declarative System (EDS) platform to support distributed computation (EDS provides a limited form of distributed shared memory); good results have been presented running DORPP on an EDS simulator.…”

Section: Related Workmentioning

confidence: 99%

“…One of the major reasons to adopt stack-splitting, as described earlier, is the ability to perform scheduling on the bottom-most choice-point. Other DMP implementations of or-parallelism have reversed to the use of scheduling on the top-most choice-point (e.g., (Araujo and Ruz 1998;Briat et al 1992;Silva and Watson 2000), where during a sharing operation only the oldest choice-point with unexplored alternatives is exchanged between agents. Top-most scheduling will share only one choice-point at the time, thus relieving the engine from the need of controlling access to shared choice-points.…”

Section: Schedulingmentioning

confidence: 99%

“…Most research in or-parallel execution of Prolog so far has focused on techniques aimed at shared-memory multiprocessors (SMPs). Relatively fewer efforts (Foong 1995;Araujo and Ruz 1998;Castro et al 1999;Briat et al 1992;Benjumea and Troya 1993;Silva and Watson 2000) have been devoted to implementing Prolog systems on distributed-memory platforms (DMPs). Out of these efforts only a small number have been implemented as working prototypes, and even fewer have produced acceptable speedups.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PALS: Efficient Or-Parallel execution of Prolog on Beowulf clusters

Pontelli

Villaverde

Guo

et al. 2007

Theory and Practice of Logic Programming

View full text Add to dashboard Cite

This paper describes the development of the PALS system, an implementation of Prolog capable of efficiently exploiting or-parallelism on distributed-memory platformsspecifically Beowulf clusters. PALS makes use of a novel technique, called incremental stack-splitting. The technique proposed builds on the stack-splitting approach, previously described by the authors and experimentally validated on shared-memory systems, which in turn is an evolution of the stack-copying method used in a variety of parallel logic and constraint systems-e.g., MUSE, YAP, and Penny. The PALS system is the first distributed or-parallel implementation of Prolog based on the stack-splitting method ever realized. The results presented confirm the superiority of this method as a simple yet effective technique to transition from shared-memory to distributed-memory systems. PALS extends stack-splitting by combining it with incremental copying; the paper provides a description of the implementation of PALS, including details of how distributed scheduling is handled. We also investigate methodologies to effectively support order-sensitive predicates (e.g., side-effects) in the context of the stack-splitting scheme. Experimental results obtained from running PALS on both Shared Memory and Beowulf systems are presented and analyzed.

show abstract