Filters








4,868 Hits in 3.7 sec

REX: Recursive, Delta-Based Data-Centric Computation [article]

Svilen R. Mihaylov, Zachary G. Ives, Sudipto Guha
2012 arXiv   pre-print
Conversely, "cloud" platforms like MapReduce execute chains of batch tasks across clusters in a fault tolerant way, but have too much overhead to support ad hoc queries.  ...  is efficiently updated in an extensible way.  ...  An alternative type of recursion in REX is fixpoint recursion with implicit termination, which was heavily studied for Datalog.  ... 
arXiv:1208.0089v1 fatcat:kc55jzf3e5fqlme5xxwkrqplu4

REX

Svilen R. Mihaylov, Zachary G. Ives, Sudipto Guha
2012 Proceedings of the VLDB Endowment  
Conversely, "cloud" platforms like MapReduce execute chains of batch tasks across clusters in a fault tolerant way, but have too much overhead to support ad hoc queries.  ...  is efficiently updated in an extensible way.  ...  An alternative type of recursion in REX is fixpoint recursion with implicit termination, which was heavily studied for Datalog.  ... 
doi:10.14778/2350229.2350246 fatcat:pfzv4hkikjgjzcwwt5hv6gg4vi

Enabling Incremental Query Re-Optimization [article]

Mengmeng Liu, Zachary G. Ives, Boon Thau Loo
2014 arXiv   pre-print
Our techniques build upon the recently proposed approach of formulating query plan enumeration as a set of recursive datalog queries; we develop a variety of novel optimization approaches to ensure effective  ...  An open question has been whether it is possible to build a cost-based re-optimization architecture for adaptive query processing in a streaming or repeated query execution environment, e.g., by incrementally  ...  • A formulation of query re-optimization as an incremental view maintenance problem, for which we develop novel algorithms. • An implementation over a query engine developed for recursive stream processing  ... 
arXiv:1409.6288v1 fatcat:mtjxm43idnaxjbmhpp4m2jbssq

Enabling Incremental Query Re-Optimization

Mengmeng Liu, Zachary G. Ives, Boon Thau Loo
2016 Proceedings of the 2016 International Conference on Management of Data - SIGMOD '16  
As declarative query processing techniques expand to the Web, data streams, network routers, and cloud platforms, there is an increasing need to re-plan execution in the presence of unanticipated performance  ...  We start by leveraging the recently proposed approach of formulating query plan enumeration as a set of recursive datalog queries; we develop a variety of novel optimization approaches to ensure effective  ...  . • An implementation over a query engine developed for recursive stream processing [20] , with a comprehensive evaluation of performance against alternative approaches, over a diverse workload. • "Porting  ... 
doi:10.1145/2882903.2915212 pmid:28659658 pmcid:PMC5484402 dblp:conf/sigmod/LiuIL16 fatcat:ze4eygzlfbccjpnnvjiadhrmnu

Efficient optimization and processing for distributed monitoring and control applications

Mengmeng Liu
2012 Proceedings of the on SIGMOD/PODS 2012 PhD Symposium - PhD '12  
adaptive query processing systems.  ...  In particular, we make the following contributions: 1) supporting the maintenance of recursive queries over distributed data streams, 2) enabling full-fledged cost-based incremental query re-optimization  ...  Indeed, how to support a fixpoint operator in the core data stream execution engine, and how to process recursive queries over streams has not been well-studied before.  ... 
doi:10.1145/2213598.2213615 dblp:conf/sigmod/Liu12 fatcat:6hzc4ilrcbap5b75oc6uej74he

Accelerating maximum likelihood estimation for Hawkes point processes

Ce Guo, Wayne Luk
2013 2013 23rd International Conference on Field programmable Logic and Applications  
We then design and optimise a pipelined engine based on our proposed strategy.  ...  In the experiments, an FPGA-based implementation of the proposed engine is shown to be up to 72 times faster than a single-core CPU, and 10 times faster than an 8-core CPU.  ...  In this study, we accelerate the parameter estimation process by designing a pipelined hardware architecture for log-likelihood evaluation.  ... 
doi:10.1109/fpl.2013.6645502 dblp:conf/fpl/GuoL13 fatcat:ffixiig7rrgn3lz6aczgfaydpq

Scalable Data Processing for Community Sensing Applications

Sérgio Duarte, David Navalho, Heitor Ferreira, Nuno Preguiça
2012 Journal on spesial topics in mobile networks and applications  
In such scenario, scalability of data processing becomes a major issue.  ...  We propose and evaluate three strategies for data processing in this architecture.  ...  Case-study and Experimental Evaluation Performance metrics of the three distribution strategies were evaluated using a case-study application that concerns realtime road traffic monitoring.  ... 
doi:10.1007/s11036-012-0424-9 fatcat:3fyspmvvbzfq5dpbdmymco22gq

Scalable Data Processing for Community Sensing Applications [chapter]

Heitor Ferreira, Sérgio Duarte, Nuno Preguiça, David Navalho
2012 Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering  
In such scenario, scalability of data processing becomes a major issue.  ...  We propose and evaluate three strategies for data processing in this architecture.  ...  Case-study and Experimental Evaluation Performance metrics of the three distribution strategies were evaluated using a case-study application that concerns realtime road traffic monitoring.  ... 
doi:10.1007/978-3-642-30973-1_7 fatcat:227p6et4fbhizjxxg2djbig43a

Asynchronous and fault-tolerant recursive datalog evaluation in shared-nothing engines

Jingjing Wang, Magdalena Balazinska, Daniel Halperin
2015 Proceedings of the VLDB Endowment  
Queries are translated into query plans that can execute in shared-nothing engines, are incremental, and support a variety of iterative models (synchronous, asynchronous, different processing priorities  ...  We implement the approach in the Myria big-data management system and use our implementation to empirically study the performance characteristics of different combinations of iterative models, failure  ...  These experiments illustrate that MyriaX achieves state of the art performance on standard queries, including iterative queries and is thus a good platform for the study of the performance differences  ... 
doi:10.14778/2824032.2824052 fatcat:bcr2wjexdzfctemlcbksue3ofu

Managing the operator ordering problem in parallel databases

Harald Kosch
2000 Future generations computer systems  
Finally, we summarize selected performance results to give a flavor of the practical relevance.  ...  This paper focuses on parallel query optimization. We consider the operator problem and introduce a new class of execution strategies called Linear-Oriented Bushy Trees (LBTs).  ...  Second, right-deep segmentation of a BT is hard to do [20] . Experimental studies with the Volcano product showed that parallel pipeline chains in BTs might degrade performance [29] .  ... 
doi:10.1016/s0167-739x(99)00080-1 fatcat:3xjlzfrrirb27jakg2oa756wcm

Efficient Evaluation of XQuery over Streaming Data

Xiaogang Li, Gagan Agrawal
2005 Very Large Data Bases Conference  
With the growing popularity of XML and emergence of streaming data model, processing queries over streaming XML has become an important topic.  ...  This paper presents a new framework and a set of techniques for processing XQuery over streaming data.  ...  Approximate processing of queries using a single pass on streaming data has been extensively studied by many researchers, and we do not consider this possibility here.  ... 
dblp:conf/vldb/LiA05 fatcat:h4u3pyzjk5gblltb54p2dbe5mq

Neural Person Search Machines [article]

Hao Liu, Jiashi Feng, Zequn Jie, Karlekar Jayashree, Bo Zhao, Meibin Qi, Jianguo Jiang, Shuicheng Yan
2017 arXiv   pre-print
Instead of comparing the query against all candidate regions generated in a query-blind manner, we propose to recursively shrink the search area from the whole image till achieving precise localization  ...  In this process, NPSM employs an internal primitive memory component to memorize the query representation which modulates the attention and augments its robustness to other distracting regions.  ...  Generally, all of the previous person search methods are based on such a simple two-stage search strategy: first to detect all candidate persons within an image and then to perform exhaustive comparison  ... 
arXiv:1707.06777v1 fatcat:e7c4dwa3drelzjl2zpyh3jsc24

Big Data Analytics with Datalog Queries on Spark

Alexander Shkapsky, Mohan Yang, Matteo Interlandi, Hsuan Chiu, Tyson Condie, Carlo Zaniolo
2016 Proceedings of the 2016 International Conference on Management of Data - SIGMOD '16  
We perform an experimental comparison with other state-ofthe-art large-scale Datalog systems and verify the efficacy of our techniques and effectiveness of Spark in supporting Datalog-based analytics.  ...  Our BigDatalog system addresses the problem by providing concise declarative specification of complex queries amenable to efficient evaluation.  ...  We very much appreciate the time and effort they put forth to make this a better paper. We thank Jingjing Wang and Jiwon Seo for their assistance with the experimental comparison.  ... 
doi:10.1145/2882903.2915229 pmid:28626296 pmcid:PMC5470845 dblp:conf/sigmod/ShkapskyYICCZ16 fatcat:fw2fje66wfaipfvhax5bi4mim4

The Vadalog system

Luigi Bellomarini, Emanuel Sallinger, Georg Gottlob
2018 Proceedings of the VLDB Endowment  
As the main contribution of this paper, we illustrate the first implementation of Warded Datalog+/-, a high-performance Datalog+/-system utilizing an aggressive termination control strategy.  ...  We also provide a comprehensive experimental evaluation. PVLDB Reference Format: Luigi Bellomarini, Emanuel Sallinger, and Georg Gottlob.  ...  The Vadalog system as presented here is IP of the University of Oxford.  ... 
doi:10.14778/3213880.3213888 fatcat:cbkkhqm2mfhihht76fo6bq5mne

A survey of parallel execution strategies for transitive closure and logic programs

Filippo Cacace, Stefano Ceri, Maurice Houtsma
1993 Distributed and parallel databases  
to query processing.  ...  This technology is being tested in several experimental database architectures and a few commercial systems for conventional select-project-join queries.  ...  Stefano Ceri is partially supported by Esprit Project P6333, IDEA and the research of Maurice Houtsma has been made possible by a fellowship of the Royal Netherlands Academy of Arts and Sciences.  ... 
doi:10.1007/bf01264013 fatcat:pe4vicsr3vctzoj437towrkdv4
« Previous Showing results 1 — 15 out of 4,868 results