P. Kacsuk and M.J. Wise. Implementations of Distributed Prolog. John Wiley, Chichester, 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....by copying the contents of CURRENT or SOLUTION BEs to the new BEs and untrailing multiple variables bound since the creation of the choice point. Alternatively, other techniques similar to the ones used to exploit OR parallelism could be used instead of copying (e.g. hash windows, bindingarrays [6]) 4 Comparison MAM vs. WAM We have implemented sequential emulators for both WAM and MAM abstract machines. A set of benchmark programs have been run on a DEC 3800 system whose CPU is an Alpha 21064 microprocessor. All benchmarks were taken from [12] excepting bits pal, which is taken from ....

P. Kacsuk and M. Wise (editors). Implementations of Distributed Prolog. John Wiley & Sons. 1992

....a shared memory system that supports both and parallelism between determinate goals and or parallelism. Several distributed memory PLPs have been proposed. Some support pure IAP [21] or pure ORP [2] Both ANDP and ORP are supported in Conery s And Or model [5] and in the dataflow based models [10]. In the latter models, computation nodes receive messages with goals to solve, and send answers to these goals. Unfortunately, sending goals and receiving solutions is expensive and may become a bottleneck to the system. Another alternative is to copy segments of the execution stacks between ....

P. Kacsuk and M. J. Wise, editors. Implementations of Distributed Prolog. Wiley, Series in Parallel Computing, 1992.

....parallel execution is not slower than sequential execution. Most OR parallel logic programming systems were implemented on shared memory symmetric multiprocessors [2, 18] Some prototypes were also implemented on distributed memory systems but they do not include the usual Prolog side effects [3, 4, 15]. The objective of PloSys is to build a Prolog like OR parallel logic programming system for distributed memory parallel architectures. Prolog like means that PloSys will implement Prolog cut and side effects. This will ease the parallelisation of applications since applications will be ....

Peter Kacsuk and Michael Wise, editors. Implementations of Distributed Prolog. John Wiley and Sons,

....after the breadth condition, CURRENT BEs are copied, whereas if it is executed after the backtrack condition then the SOLUTION BEs are copied. Alternatively, other techniques similar to the ones used to exploit ORparallelism could be used instead of copying (e.g. hash windows, binding arrays [5]) UU LM UU LM UU LM MU Local Interconn. Network CM CM CM CM Shared Memory Shared Interconnection Network Figure 3: A parallel architecture for Multipath 4 Parallel Implementation A parallel architecture that efficiently exploits the features of the Multipath execution model is ....

P. Kacsuk and M. Wise (editors). Implementations of Distributed Prolog. John Wiley & Sons. 1992

....(seconds) for sequential WAM and MAM emulators. MAX PATHS refers to the value the MAM emulator behaves better. 14 operations needed to unify two Prolog terms for each binding environment in the computation state. We call this kind of parallelism path parallelism. The sources of parallelism [4] most related to path parallelism are unification parallelism and data parallelism. In unification parallelism, parallel unifications are related to different arguments of a goal for a single binding environment. In this case, there may be data dependences among the unifications. In path ....

P. Kacsuk and M. Wise (editors). Implementations of Distributed Prolog. John Wiley & Sons. 1992

.... execution model that does not preserve the semantics of the original logic language (i.e. Prolog) but can be used as a basis to define new languages, such as Parlog, KL1 and Concurrent Prolog that are usually classified as Concurrent Logic Programming Languages or Committed Choice Languages [Kacsuk 92, Takeuchi 92] Since we are interested in parallel implementations of the Prolog interpreter without changes to the original semantics of the language, we limit our attention to independent ANDparallelism. In principle, the basic conditions for exploring independent AND parallelism in Prolog do ....

P. Kacsuk, M.J. Wise, Implementations of Distributed Prolog , Wiley, 1992.

....main restriction is that logical variables will be bound only once during an and parallel execution phase. Most parallel logic programming systems have been developed for bus based shared memory architectures, even though a few systems have been implemented for distributed memory architectures [14]. Specialised hardware has also been built for parallel logic programming, as exemplified by PIM machines developed at ICOT to support the KL1 language [13] However, the modern computer architectures being developed today pose new challenges, such as the high latency of memory accesses and the ....

Kacsuk, P., and Wise, M. J., Eds. Implementations of Distributed Prolog. Wiley, Series in Parallel Computing, 1992.

....parallelism present in today s multicomputers; both shared memorymulticomputers and distributed memory ones. Besides AND , OR , and stream AND parallel execution of Prolog programs, there emerged a so called process based program execution with explicit process creation and explicit communication [3]. Some representatives of process based Prolog languages are Delta Prolog [4, 5] CS Prolog [6, 7, 8] and PMS Prolog [9] The roots of these languages reaches back into the middle eighties. Even recent blackboard oriented languages (e.g. Shared Prolog [10] and Multi Prolog [11] and coordination ....

P'eter Kacsuk and Michael J. Wise, editors. Implementations of Distributed Prolog. Wiley Series in Parallel Computing. John Wiley & Sons, Chichester, 1992.

....the delay declarations which turn the sequential program into a parallel one without affecting its correctness. The AND OR parallelism of logic programming has been long known and used both within the concurrent logic languages and within parallel implementations of Prolog. In Kacsuk and Wise [KW92] various parallel implementations of Prolog are surveyed and the obtained speeds up are thoroughly documented. The logic programming paradigm has been recognized as an attractive and simple framework for solving computing problems in several areas in which the traditional approach based on ....

P. Kacsuk and M. J. Wise. Implementations of Distributed Prolog. John Wiley & Sons, Chichester, England, 1992.

....to create effectively a seamless integrated language. 2 Related Work With respect to the distributed logic programming aspects, a detailed motivation and an overview of related work can be found in [Eliens, 1992] Conceptual as well as technical issues of related work can also be found in [Kacsuk and Wise, 1992]. For ActiveC the main objective was to give it a communication model identical to DLP. Many other research efforts extend the C or C programming language into a parallel or distributed language. We ve compared ActiveC design decisions with about 15 other parallel and distributed C C ....

P. Kacsuk and M. Wise (eds.), Implementations of distributed Prolog, Wiley, 1992

.... leads to consider three kinds of parallelism ( OR , independent AND and dependent AND ) The main advantages are wellknown : no complexity is added to the programming language, existing programs can easily be re used and the implementation technology shares a large part with existing systems [16], 6] 12] Data parallel execution of logic programs has been investigated by two main propositions. Parallelism is achieved through recursion loop unfolding in the model Reform [22] 23] and by parallel exploration of disjunctive branches in [27] Recently, attempts have been made to introduce ....

P. Kacsuk and M. Wise, editors. Implementation of distributed prolog, Parallel computing. John Wiley & sons, 1992.

....explained in the paper. Keywords: parallel computing, load balancing, scheduling, performance monitoring, transputers, workstation clusters, graphical tools 1 Introduction Recently, there have been many research efforts to exploit the inherently available parallelism of Prolog programs [1] 3] 4][8][12] 13] 16] LOGFLOW is an allsolution parallel logic programming system able to exploit OR parallelism and pipeline AND parallelism of Prolog programs. 2 The LOGFLOW project is intended to implement Prolog in massively parallel distributed memory multicomputers. Its abstract execution model ....

P. Kacsuk and M.J. Wise,eds., Implementations of Distributed Prolog, (John Wiley, 1992.)

No context found.

P. Kacsuk and M.J. Wise. Implementations of Distributed Prolog. John Wiley, Chichester, 1992.

No context found.

Peter Kacsuk and Michael J. Wise, editors. Implementations of Distributed Prolog. Series in Parallel Computing. Wiley, Chichester, 1992.

No context found.

P'eter Kacsuk and Michael J. Wise, editors. Implementations of Distributed Prolog. Wiley Series in Parallel Computing. John Wiley & Sons, Chicester, 1992.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC