Towards multi-threaded local tabling using a common table space

Areias, Miguel; Rocha, Ricardo

doi:10.1017/s1471068412000117

Cited by 9 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the all aggregator mode, we can still keep a pointer to the beginning of the trie representing all answers, but then we need to guarantee order and synchronization when inserting new answers. This can be done using a strategy similar to the full sharing strategy described in our previous work …”

Section: Conclusion and Further Workmentioning

confidence: 99%

“…To support concurrency within the shared subgoal trie structures, the design uses the lock-free hash tries data structure proposed in our previous work, 27 which showed to effectively reduce the execution time and scale better than the original lock-based designs. 17,18 For each thread evaluating a call C i , the answers are then stored in an answer trie structure private to the thread.…”

Section: Multithreaded Tablingmentioning

confidence: 99%

“…The subgoal trie structures are shared among all threads, and the leaf data structures representing each tabled subgoal call C i , instead of pointing to a single subgoal frame, point to a chain of private subgoal frames, one per thread that is evaluating the call C i . To support concurrency within the shared subgoal trie structures, the design uses the lock‐free hash tries data structure proposed in our previous work, which showed to effectively reduce the execution time and scale better than the original lock‐based designs . For each thread evaluating a call C i , the answers are then stored in an answer trie structure private to the thread.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐dimensional lock‐free arrays for multithreaded mode‐directed tabling in Prolog

Areias

Rocha

2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary This work proposes a new design for the supporting data structures used to implement multithreaded tabling in Prolog systems. Tabling is an implementation technique that improves the expressiveness of traditional Prolog systems in dealing with recursion and redundant computations. Mode‐directed tabling is an extension to the tabling technique that supports the definition of alternative criteria for specifying how answers are aggregated, thus being very suitable for problems where the goal is to dynamically calculate optimal or selective answers. In this work, we leverage the intrinsic potential that mode‐directed tabling has to express dynamic programming problems by creating a new design that improves the representation of multi‐dimensional arrays in the context of multithreaded tabling. To do so, we introduce a new mode for indexing arguments in mode‐directed tabled evaluations, named dim, where each dim argument features a uni‐dimensional lock‐free array. Experimental results using well‐known dynamic programming problems on a 32‐core machine show that the new design introduces less overheads and clearly improves the execution time for sequential and multithreaded tabled evaluations.

show abstract

Section: Conclusion and Further Workmentioning

confidence: 99%

Section: Multithreaded Tablingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐dimensional lock‐free arrays for multithreaded mode‐directed tabling in Prolog

Areias

Rocha

2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…One such feature is the ISO Prolog multithreading standardization proposal [36], which currently is implemented in several Prolog systems, including Ciao, SWI Prolog, XSB Prolog and YAP Prolog, providing a highly portable solution given the number of operating systems supported by these systems. Arguably, one of the features that promises to have a significant impact is the combination of multithreading with tabling [37,38], as Prolog users will be able to exploit the combination of a higher procedural control with higher declarative semantics. Future work plans include the extension of YAPTBE to support the execution and output analysis of standard and tabled multithreaded Prolog runs.…”

Section: Further Workmentioning

confidence: 99%

On the Implementation of a Cloud-Based Computing Test Bench Environment for Prolog Systems

2017

Self Cite

View full text Add to dashboard Cite

Software testing and benchmarking are key components of the software development process. Nowadays, a good practice in large software projects is the continuous integration (CI) software development technique. The key idea of CI is to let developers integrate their work as they produce it, instead of performing the integration at the end of each software module. In this paper, we extend a previous work on a benchmark suite for the YAP Prolog system, and we propose a fully automated test bench environment for Prolog systems, named Yet Another Prolog Test Bench Environment (YAPTBE), aimed to assist developers in the development and CI of Prolog systems. YAPTBE is based on a cloud computing architecture and relies on the Jenkins framework as well as a new Jenkins plugin to manage the underlying infrastructure. We present the key design and implementation aspects of YAPTBE and show its most important features, such as its graphical user interface (GUI) and the automated process that builds and runs Prolog systems and benchmarks.

show abstract

“…XSB was the first Prolog system to combine tabling with multithreading (Marques and Swift 2008). In more recent work (Areias and Rocha 2012b), we have proposed an alternative view to XSB's approach, where each thread views its tables as private but, at the engine level, we use a common table space, i.e., from the thread point of view, the tables are private but, from the implementation point of view, tables are shared among all threads.…”

Section: Introductionmentioning

confidence: 99%

A Lock-Free Hash Trie Design for Concurrent Tabled Logic Programs

Areias

Rocha

2015

Int J Parallel Prog

Self Cite

View full text Add to dashboard Cite

A critical component in the implementation of a concurrent tabling system is the design of the table space. One of the most successful proposals for representing tables is based on a two-level trie data structure, where one trie level stores the tabled subgoal calls and the other stores the computed answers. In this work, we present a simple and efficient lock-free design where both levels of the tries can be shared among threads in a concurrent environment. To implement lock-freedom we took advantage of the CAS atomic instruction that nowadays can be widely found on many common architectures. CAS reduces the granularity of the synchronization when threads access concurrent areas, but still suffers from low-level problems such as false sharing or cache memory side-effects. In order to be as effective as possible in the concurrent search and insert operations over the table space data structures, we based our design on a hash trie data structure in such a way that it minimizes potential low-level synchronization problems by dispersing as much as possible the concurrent areas. Experimental results in the Yap Prolog system show that our new lock-free hash trie design can effectively reduce the execution time and scale better than previous designs.

show abstract

Towards multi-threaded local tabling using a common table space

Cited by 9 publications

References 11 publications

Multi‐dimensional lock‐free arrays for multithreaded mode‐directed tabling in Prolog

Multi‐dimensional lock‐free arrays for multithreaded mode‐directed tabling in Prolog

On the Implementation of a Cloud-Based Computing Test Bench Environment for Prolog Systems

A Lock-Free Hash Trie Design for Concurrent Tabled Logic Programs

Contact Info

Product

Resources

About