Or-parallel Prolog on a distributed memory architecture
نویسندگان
چکیده
منابع مشابه
Or-Parallel Prolog on a Distributed Memory Architecture
Whilst there has been much work over the last ten years on the parallel implementation of logic programming, the vast majority of it has been focused on shared memory multiprocessor systems. In this paper, however, we focus on the exploitation of the other major type of parallel architecture-distributed memory systems. We present the design and study the performance of the Dorpp or-parallel Pro...
متن کاملOr-Parallel Prolog on Shared Memory Multiprocessors
D PROLOG implementation efforts have recently begun to shift from singleprocessor systems to the new commercially available shared-memory multiprocessors. Among the problems encountered are efficient implementation of operations on variables and the scheduling of the processors. Most of the solutions proposed so far suffer from expensive, nonconstant-time implementation of operations on variabl...
متن کاملAn OR Parallel Prolog Model for Distributed Memory Systems
This paper shows a multisequential model to exploit OR parallelism on distributed memory systems. It presents an implementation of the incremental copy mechanism oriented to distributed systems and a novel distributed scheduler is also proposed. WAM modifications to support the proposed model are very simple. The system has been implemented on a 16 processor multicomputer based on transputers. ...
متن کاملAn OR Parallel Prolog Model for Distributed Memory Systemsw
This paper shows a multisequential model to exploit OR parallelism on distributed memory systems. It presents an implementation of the incremental copy mechanism oriented to distributed systems and a novel distributed scheduler is also proposed. WAM modifications to support the proposed model are very simple. The system has been implemented on a 16 processor multicomputer based on transputers. ...
متن کاملImplementing Prolog on Distributed Systems: N-parallel Prolog
A method for distributing Prolog across multiple processors is described. Design criterion and rationale are delineated along with the assumptions behind the methodology. The underlying assumptions are based on the need to provide each processor with maximum sequential work. The parallelization mechanism was implemented using a meta-interpreter that includes new predicates for dependency detect...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of Logic Programming
سال: 2000
ISSN: 0743-1066
DOI: 10.1016/s0743-1066(99)00064-3