Filters








30,832 Hits in 3.1 sec

On the performance of parallel join processing in shared nothing database systems [chapter]

Robert Marek, Erhard Rahm
1993 Lecture Notes in Computer Science  
We focus on two major issues: (a) determining the number of processors to be allocated for the execution of join queries, and (b) determining which processors are to be chosen for join processing.  ...  We study the performance of parallel join processing under more realistic conditions, in particular for multi-user mode.  ...  In fact, for multi-user mode the optimal degree of join parallelism depends on the arrival rate and thus on the current system utilization.  ... 
doi:10.1007/3-540-56891-3_50 fatcat:c4yphstgpbefro3l2vnzdnbrpy

Dynamic load balancing in parallel database systems [chapter]

Erhard Rahm
1996 Lecture Notes in Computer Science  
For this purpose, we focus on parallel scan and join processing in multi-user mode.  ...  It turns out that both the degree of query parallelism as well as the processor allocation should be determined in a coordinated way and based on the current utilization of critical resource types, in  ...  We have discussed basic performance tradeoffs to consider for determining the optimal degree of join parallelism and selecting join processors in multi-user mode.  ... 
doi:10.1007/3-540-61626-8_4 fatcat:cuktfn5tsvgtljcjzo23vtlgp4

Thread fork/join techniques for multi-level parallelism exploitation in NUMA multiprocessors

Xavier Martorell, Eduard Ayguadé, Nacho Navarro, Julita Corbalán, Marc González, Jesús Labarta
1999 Proceedings of the 13th international conference on Supercomputing - ICS '99  
This paper presents some techniques for efficient thread forking and joining in parallel execution environments, taking into consideration the physical structure of NUMA machines and the support for multi-level  ...  parallelization and processor grouping.  ...  ACKNOWLEDGEMENTS We would like to thank to the partners of the NANOS project for the insightful discussions on various aspects of this paper.  ... 
doi:10.1145/305138.305206 dblp:conf/ics/MartorellANCGL99 fatcat:nupikhoqdjg2vavng7dkwb7bf4

Data parallel acceleration of decision support queries using Cell/BE and GPUs

Pedro Trancoso, Despo Othonos, Artemakis Artemiou
2009 Proceedings of the 6th ACM conference on Computing frontiers - CF '09  
To achieve this goal we propose data-parallel versions of the original database scan and join algorithms.  ...  The results show that parallelism can be well exploited by the GPUs. The speedup values observed were up to 21× compared to a single processor system.  ...  An analysis of the results comparing the two hash-join implementations on the multi-core system shows that the original hash-join performs more than 2× better than the dataparallel one.  ... 
doi:10.1145/1531743.1531763 dblp:conf/cf/TrancosoOA09 fatcat:aem46tslwvg6hjmvwslap7xwbm

Processing multi-join query in parallel systems

Kian-Lee Tan, Hongjun Lu
1992 Proceedings of the 1992 ACM/SIGAPP Symposium on Applied computing technological challenges of the 1990's - SAC '92  
In parallel systems, a number of joins from one or more queries ean be exeeuted either seriatly or in parallel.  ...  While seriat execution assigns all processors to execute each join one after another, the parallel execution distributes the joins to clusters formed by certain number of processors and exeeutes them concurrently  ...  Deen, in his experiments for 2-joins and 3-joins, cxmcluded that it is better to form a single cluster of parallel processom and to carry out the multi-join in series of single joins one after another,  ... 
doi:10.1145/143559.143653 dblp:conf/sac/TanL92 fatcat:wu5ldbg2njcmxbgvdlomjq2kde

Optimization of Multi-Way Join Queries for Parallel Execution

Hongjun Lu, Ming-Chien Shan, Kian-Lee Tan
1991 Very Large Data Bases Conference  
Most of the existing relational database query optimizers generate multi-way join plans only from those linear ones to reduce the optimization overhead.  ...  The optimization process not only determines the order and method in which each join should be performed, but also determines the number of joins should be executed in parallel, and the number of processors  ...  In a linear QEP (Figure3.la). joins in a multi-way join query are performed one by one.  ... 
dblp:conf/vldb/LuST91 fatcat:f634afx2rfch7ecutqyvcz5vzm

Algorithmic Aspects of Parallel Data Processing

Paraschos Koutris, Semih Salihoglu, Dan Suciu
2018 Foundations and Trends in Databases  
However, the Parallel Hash join performs poorly on skewed data, when a large number of records have the same value of the join attribute and, thus, are hashed to the same processor.  ...  The preferred algorithm in practice is the Parallel Hash join, because on most datasets this algorithm is very e ective and scales up linearly with the number of processors.  ... 
doi:10.1561/1900000055 fatcat:u5icy7htubbt7oboux4sa46mci

Scheduling Parallel Real-Time Tasks on Multi-core Processors

K Lakshmanan, S Kato, R Rajkumar
2010 2010 31st IEEE Real-Time Systems Symposium  
Parallel programming models such as OpenMP present promising solutions for more effectively using multiple processor cores.  ...  Massively multi-core processors are rapidly gaining market share with major chip vendors offering an everincreasing number of cores per processor.  ...  Parallel programming models such as OpenMP [3] are promising candidates for taking advantage of future massive multi-core processors 1 .  ... 
doi:10.1109/rtss.2010.42 dblp:conf/rtss/LakshmananKR10 fatcat:i7fghb3jezdfdjtpimgal4g7ry

Resource Planning for SPARQL Query Execution on Data Sharing Platforms

Stefan Hagedorn, Katja Hose, Kai-Uwe Sattler, Jürgen Umbrich
2014 International Semantic Web Conference  
Resource planning and especially deciding how many processors should be chosen to exploit parallel processing is complex in such a setup as increasing the number of processors does not always improve runtime  ...  In this paper, we present a cost model based on widely used statistics (VoiD) and show how to compute the optimum number of processors that should be used to evaluate a particular SPARQL query over a particular  ...  Earlier approaches on query resource allocation dealt only with the problem of allocating processors for multi-join queries [3] , other works take also multi-dimensional resources (CPU, memory, etc.)  ... 
dblp:conf/semweb/HagedornHSU14 fatcat:jiljjw7h6rehdlfaunjftya5ui

OPTIMIZATION OF LOCAL PARALLEL INDEX (LPI) IN PARALLEL/DISTRIBUTED DATABASE SYSTEMS

Mohamed Chakraoui
2016 International Journal of GEOMATE  
parallel/distributed database systems and collaboration between processors when executing multi-queries.  ...  Since the advent of multicore computers (multi processors) parallelism becomes an indispensable part of optimization.  ...  When we launch a query in parallel one-index join processing, we search on the indexed table by the attribute of index and the record loading is pointed by RowID.  ... 
doi:10.21660/2016.27.1322 fatcat:dsifoha6cnfhddxkkwqujufz5u

Accelerating database operators using a network processor

Brian Gold, Anastassia Ailamaki, Larry Huston, Babak Falsafi
2005 Proceedings of the 1st international workshop on Data management on new hardware - DAMON '05  
This paper shows an existing hardware architecture-the network processor-already fits the model for multi-threaded, multi-core execution.  ...  Increases in processor clock rate and instruction-level parallelism have left memory accesses as the dominant bottleneck in DBMS execution.  ...  We demonstrate that existing network processors, with their multi-core, multi-threaded architecture, can expose more parallel accesses to memory than a conventional, single-threaded processor.  ... 
doi:10.1145/1114252.1114260 fatcat:dm7ub4pxhrhkrpdcrsb6jzo6ea

Relational algorithms for multi-bulk-synchronous processors

Gregory Diamos, Haicheng Wu, Jin Wang, Ashwin Lele, Sudhakar Yalamanchili
2013 Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming - PPoPP '13  
At the same time, processor architectures are increasingly gravitating towards Multi-Bulk-Synchronous processor (Multi-BSP) architectures employing throughput-optimized memory systems, lightweight multithreading  ...  This paper explores the mapping of primitive relational algebra operations onto such architectures to improve the throughput of data warehousing applications built on relational databases.  ...  Binary-Search CTA-JOIN is based on a parallel binary search, similar to the partition stage of the complete join algorithm.  ... 
doi:10.1145/2442516.2442555 dblp:conf/ppopp/DiamosWWLY13 fatcat:d4tpsemud5djth45qkoxmavtg4

Dataflow query execution in a parallel main-memory environment

Annita N. Wilschut, Peter M. G. Apers
1993 Distributed and parallel databases  
In this paper, the performance and characteristics of the execution of various join-trees on a parallel DBMS are studied.  ...  The format of the optimal join-tree appears to depend on the size of the operands of the join: A multi-join between small operands performs best with a bushy schedule; larger operands are better off with  ...  Multi-join queries In this section, the trade-offs of using differently structured query trees for the execution of multi-join queries are discussed.  ... 
doi:10.1007/bf01277522 fatcat:bwbpt4oxfvd73bbtczbzt2lixu

Performance Evaluation Of Matrix Multiplication Using OpenMP For Single Dual and Multi-Core Machines

Yogesh Singh Rathore
2014 IOSR Journal of Engineering  
In this paper we study and evaluate the execution time of matrix multiplication on a single, dual and multi-core processor with same set of processors having OpenMP(Open Multi-Processing) libraries for  ...  The evaluation is based on execution of the algorithm uses single thread for computation whereas the one with OpenMP uses multi-threads.  ...  A single core machine executes one instruction at a time but with the use of OpenMP [1] a multi-core [2] [3] machine's processors of Multi-Core Architectures [14] can be used for parallel processing  ... 
doi:10.9790/3021-04135659 fatcat:kusfz22izrcqjgjsczxpjce4w4

Relational algorithms for multi-bulk-synchronous processors

Gregory Diamos, Haicheng Wu, Jin Wang, Ashwin Lele, Sudhakar Yalamanchili
2013 SIGPLAN notices  
At the same time, processor architectures are increasingly gravitating towards Multi-Bulk-Synchronous processor (Multi-BSP) architectures employing throughput-optimized memory systems, lightweight multithreading  ...  This paper explores the mapping of primitive relational algebra operations onto such architectures to improve the throughput of data warehousing applications built on relational databases.  ...  Binary-Search CTA-JOIN is based on a parallel binary search, similar to the partition stage of the complete join algorithm.  ... 
doi:10.1145/2517327.2442555 fatcat:bej64rw6lnbhzjswv6dxumyoqm
« Previous Showing results 1 — 15 out of 30,832 results