Filters








6,423 Hits in 6.8 sec

Intra-disk Parallelism: An Idea Whose Time Has Come

Sriram Sankar, Sudhanva Gurumurthi, Mircea R. Stan
2008 2008 International Symposium on Computer Architecture  
We find that rotational latency is the primary bottleneck that intra-disk parallelism needs to optimize. • We present an intra-disk parallel design, which involves the use of multiple disk arm assemblies  ...  We discuss about the multi-actuator drives that were used in mainframes back in the 1970s and 80s, why they were discontinued, and show why our intra-disk parallelism idea is different. • We present a  ...  Acknowledgements This research has been supported in part by NSF CAREER Award CCF-0643925, NSF grant CNS-0551630, a MARCO IFC grant, and gifts from HP and Google.  ... 
doi:10.1109/isca.2008.11 dblp:conf/isca/SankarGS08 fatcat:bpujs27iyvanrbhtcyvm2mto6u

Parallel database systems

David J. DeWitt, Jim Gray
1990 SIGMOD record  
Parallel database machine architectures based on exotic hardware have evolved to a parallel database systems running atop a parallel dataflow software architecture based on conventional shared-nothing  ...  Table of Contents of The 1983 paper titled Database Machines: An Idea Whose Time has Passed? A Critique of the Future of Database Machines 1 Introduction 1 2.  ...  Software Two software mechanisms have been used in the construction of most parallel database systems: declustering [LNN87] for mapping tuples to disks and an intra-operator parallelizer to distribute  ... 
doi:10.1145/122058.122071 fatcat:4mjtunvs2bav5c27z2jjdeu4zy

Compiler-Directed Energy Optimization for Parallel Disk Based Systems

Seung Woo Son, Guangyu Chen, Ozcan Ozturk, Mahmut Kandemir, Alok Choudhary
2007 IEEE Transactions on Parallel and Distributed Systems  
periods of parallel disks.  ...  Disk subsystem is known to be a major contributor to overall power consumption of high-end parallel systems.  ...  This is one of the most pressing problems facing parallel systems, where disk requests coming from individual processors can interleave in time and eventually make disk idle time (and active time) prediction  ... 
doi:10.1109/tpds.2007.1056 fatcat:j6x43ablsfgwddkt43fwesfzpm

Distributed and Parallel Database Systems [chapter]

M Özsu, Patrick Valduriez
2014 Computing Handbook, Third Edition  
The system has the full functionality of a DBMS. It is neither, as indicated above, a distributed file system, nor is it a transaction processing system.  ...  Parallelism can increase throughput (using inter-query parallelism) and decrease transaction response times (using intra-query and intra-operation parallelism).  ...  Intra-operation parallelism is achieved by executing an operation on several nodes of a multiprocessor machine.  ... 
doi:10.1201/b16768-16 fatcat:ula52uqbt5arbnbbxhzoayfqsu

Distributed and parallel database systems

M. Tamer Özsu, Patrick Valduriez
1996 ACM Computing Surveys  
The system has the full functionality of a DBMS. It is neither, as indicated above, a distributed file system, nor is it a transaction processing system.  ...  Parallelism can increase throughput (using inter-query parallelism) and decrease transaction response times (using intra-query and intra-operation parallelism).  ...  Intra-operation parallelism is achieved by executing an operation on several nodes of a multiprocessor machine.  ... 
doi:10.1145/234313.234368 fatcat:twwvplp3gvf2tg5fjqcgdvrcjy

Query Load Balancing in Parallel Database Systems [chapter]

Luc Bouganim
2017 Encyclopedia of Database Systems  
We consider the execution of multi-join queries in a hierarchical parallel system, i.e., a shared-nothing system whose nodes are shared-memory multiprocessors.  ...  Cela est obtenu en permettant à chaque processeur d'un noeud d'exécuter n'importe quelle opération pouvant être traitée localement, tirant ainsi parti du parallélisme inter et intra-opération présent dans  ...  Acknowledgments The authors wish to thank Benoit Dageville for many fruitful discussions on parallel execution model and Jean-Paul Chieze for helping us with the KSR1 at Inria.  ... 
doi:10.1007/978-1-4899-7993-3_1080-2 fatcat:5zr45zzzwzgcnfgwxgc4ahpdhi

Parallel data intensive computing in scientific and commercial applications

Mario Cannataro, Domenico Talia, Pradip K Srimani
2002 Parallel Computing  
The purpose of this introductory article is to provide an overview of the main issues in parallel data intensive computing in scientific and commercial applications and to encourage the reader to go into  ...  The integration of parallel and distributed computational environments will produce major improvements in performance for both computing intensive and data intensive applications in the future.  ...  Improvement in disk access times must face mechanical constraints, so it has been less than 10% per year.  ... 
doi:10.1016/s0167-8191(02)00091-1 fatcat:qetjnt73xrbf3eil5p6suwx4ua

Parallel OLAP query processing in database clusters with data replication

Alexandre A. B. Lima, Camille Furtado, Patrick Valduriez, Marta Mattoso
2009 Distributed and parallel databases  
Current DBC solutions for OLAP query processing provide for intra-query parallelism only, at the cost of full replication of the database.  ...  We also propose a new load balancing strategy that takes advantage of an adaptive virtual partitioning to redistribute the load to the replicas.  ...  Each one has already been employed in isolation for intra-query parallelism implementation during OLAP query processing.  ... 
doi:10.1007/s10619-009-7037-8 fatcat:yo57te5zzngkpjg3c4zone27wq

Parallel Solutions in ClustRa

Svein Erik Bratsberg, Svein-Olaf Hvasshovd, Øystein Torbjørnsen
1997 IEEE Data Engineering Bulletin  
I would also like to thank Scott Shurts, whose comments greatly improved this article.  ...  Acknowledgements We'd like to acknowledge the extensive contributions of a number of past and present participants of the SQL server development team that built this parallelism release of Sybase SQL Server  ...  The basic idea is that each site has a replica of the database.  ... 
dblp:journals/debu/BratsbergHT97 fatcat:4kjcg2v2pfe3pjlyj7z2wrm57a

Parallelism-Aware Batch Scheduling

Onur Mutlu, Thomas Moscibroda
2008 SIGARCH Computer Architecture News  
Our parallelism-aware batch scheduler (PAR-BS) design is based on two key ideas. First, PAR-BS processes DRAM requests in batches to provide fairness and to avoid starvation of requests.  ...  Requests whose latencies would otherwise have been overlapped could effectively become serialized.  ...  than it would for an intensive thread, whose DRAM-related stall-time is already high even when running alone.  ... 
doi:10.1145/1394608.1382128 fatcat:yfmte3tzcvdivb4blz2itqfgt4

Multi-Resource Parallel Query Scheduling and Optimization [article]

Minos Garofalakis, Yannis Ioannidis
2014 arXiv   pre-print
Scheduling query execution plans is a particularly complex problem in shared-nothing parallel systems, where each site consists of a collection of local time-shared (e.g., CPU(s) or disk(s)) and space-shared  ...  of parallel execution.  ...  xf er time(disk) · |R 1 | + min seek time(disk) · |R 1 | blocks per cylinder(disk) , Figure 3 : 3 (a) A system site with d = 2 ts resources and s = 1 ss resource.  ... 
arXiv:1403.7729v1 fatcat:ifovbnih35ce5ayupf6tvydf2u

Introduction to parallel computing

2004 ChoiceReviews  
Today's supercomputers and parallel computers provide an unprecedented amount of computational power in one machine.  ...  In addition, an understanding of technical vocabulary is critical in order to converse about parallel computers.  ...  It is convenient at times to be able to use the idea that an instance of savings,.-account is also an instance of bank_account.  ... 
doi:10.5860/choice.42-0990 fatcat:kiymwofenbavfdixftjhnuavx4

Introduction to parallel computing

1992 ChoiceReviews  
Today's supercomputers and parallel computers provide an unprecedented amount of computational power in one machine.  ...  In addition, an understanding of technical vocabulary is critical in order to converse about parallel computers.  ...  It is convenient at times to be able to use the idea that an instance of savings,.-account is also an instance of bank_account.  ... 
doi:10.5860/choice.30-1558 fatcat:7qgaeun2ujgcjj3cc3bfbvvbi4

Parallel data processing with MapReduce

Kyong-Ha Lee, Yoon-Joon Lee, Hyunsik Choi, Yon Dohn Chung, Bongki Moon
2012 SIGMOD record  
We also discuss the open issues and challenges raised on parallel data analysis with MapReduce.  ...  A prominent parallel data processing tool MapReduce is gaining significant momentum from both industry and academia as the volume of data to analyze grows rapidly.  ...  In addition, the MapReduce framework has a latency problem that comes from its inherent batch processing nature. All of inputs for an MR job should be prepared in advance for processing.  ... 
doi:10.1145/2094114.2094118 fatcat:kuvfuwss3fcmbf2d7oqqfibmoq

Parallel production systems [chapter]

1994 Lecture Notes in Computer Science  
The slow speed of execution has prohibited the use of production systems in domains requiring high performance and real-time response.  ...  The thesis proposes a parallel version of the Rete algorithm which exploits parallelism at a very fine grain to reduce the variation.  ...  An obvious direction for further work is to implement the ideas proposed in this thesis on an actual multiprocessor.  ... 
doi:10.1007/3-540-58698-9_2 fatcat:utbp2gxxdneo7n5hczk67h6qqi
« Previous Showing results 1 — 15 out of 6,423 results