A decomposition storage model

Copeland, George P.; Khoshafian, Setrag

doi:10.1145/318898.318923

Cited by 272 publications

(138 citation statements)

References 23 publications

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…Storage models for managing complex objects can be classified into three types [COP85,KHO88] including direct storage model (DSM), normalized storage model (NSM), and fully decomposed storage model (FDSM). DSM stores an entire object as a whole allowing fast retrieval of the object via object identifier, but does not support queries based on some key values and is not suitable for representing shared objects.…”

Section: Physical Database Access Methods For Multimedia Datamentioning

confidence: 99%

Architecture for distributed multimedia database systems

Berra

Chen

Ghafoor

et al. 1990

Computer Communications

View full text Add to dashboard Cite

Abstract-In the past few years considerable demand for user oriented multimedia information systems has developed. These systems must provide a rich set of functionality so that new, complex, and interesting applications can be addressed. This places considerable importance on the management of diverse data types including text, images, audio and video. These requirements generate the need for a new generation of distributed heterogeneous multimedia database systems. In this paper we identify a set of functional requirements for a multimedia server considering database management, object synchronization and integration, and multimedia query processing. A generalization of the requirements to a distributed system is presented, and some of our current research and developing activities are discussed.

show abstract

Section: Physical Database Access Methods For Multimedia Datamentioning

confidence: 99%

Architecture for distributed multimedia database systems

Berra

Chen

Ghafoor

et al. 1990

Computer Communications

View full text Add to dashboard Cite

show abstract

“…In this paper, we study (partial) decomposition of database tables to reduce bandwidth waste through suboptimal co-location of relation attributes. Full decomposition, i.e., storage using the DSM [12] yields significant bandwidth savings for analytical applications on disk-resident databases. Unfortunately, full decomposition has a negative impact on intra-tuple cache locality and therefore transaction processing performance [1].…”

Section: B Cache Efficient Storagementioning

confidence: 99%

“…Using this model, data is processed column-at-a-time which is CPU efficient but only cache efficient on data that is stored according to the Decomposed Storage Model (DSM) [12]. The DSM is known for its good OLAP performance but suffers from bad OLTP performance due to poor cache efficiency when (partially) reconstructing tuples.…”

Section: Introductionmentioning

confidence: 99%

CPU and cache efficient management of memory-resident databases

Pirk

Funke²,

Grund

et al. 2013

2013 IEEE 29th International Conference on Data Engineering (ICDE)

View full text Add to dashboard Cite

Abstract-Memory-Resident Database Management Systems (MRDBMS) have to be optimized for two resources: CPU cycles and memory bandwidth. To optimize for bandwidth in mixed OLTP/OLAP scenarios, the hybrid or Partially Decomposed Storage Model (PDSM) has been proposed. However, in current implementations, bandwidth savings achieved by partial decomposition come at increased CPU costs. To achieve the aspired bandwidth savings without sacrificing CPU efficiency, we combine partially decomposed storage with Just-in-Time (JiT) compilation of queries, thus eliminating CPU inefficient function calls. Since existing cost based optimization components are not designed for JiT-compiled query execution, we also develop a novel approach to cost modeling and subsequent storage layout optimization. Our evaluation shows that the JiT-based processor maintains the bandwidth savings of previously presented hybrid query processors but outperforms them by two orders of magnitude due to increased CPU efficiency.

show abstract

“…MonetDB 1 is a main-memory database system targeted at query-intensive applications [Bon02] that uses a vertically fragmented storage scheme called the Decomposition Storage Model (DSM) [CK85]. In DSM, each tuple gets a unique system-generated oid that is typically densely ascending (0,1,2,...), and for each column a DSM table is created that holds [oid,value] pairs.…”

Section: Ram Vs Disk Optimizationmentioning

confidence: 99%

Cache-Conscious Radix-Decluster Projections

Manegold

Boncz

Nes

et al. 2004

Proceedings 2004 VLDB Conference

View full text Add to dashboard Cite

C e n t r u m v o o r W i s k u n d e e n I n f o r m a t i c a INformation SystemsCache-Conscious Radix-Decluster Projections S. Manegold, P.A. Boncz, N.J. Nes, M.L. Kersten Cache-Conscious Radix-Decluster Projections ABSTRACT As CPUs become more powerful with Moore's law and memory latencies stay constant, the impact of the memory access performance bottleneck continues to grow on relational operators like join, which can exhibit random access on a memory region larger than the hardware caches. While cache-conscious variants for various relational algorithms have been described, previous work has mostly ignored (the cost of) projection columns. However, real-life joins almost always come with projections, such that proper projection column manipulation should be an integral part of any generic join algorithm. In this paper, we analyze cache-conscious hash-join algorithms including projections on two storage schemes: N-ary Storage Model (NSM) and Decomposition Storage Model (DSM). It turns out, that the strategy of first executing the join and only afterwards dealing with the projection columns (i.e., post-projection) on DSM, in combination with a new finely tunable algorithm called Radix-Decluster, outperforms all previously reported projection strategies. To make this result generally applicable, we also outline how DSM Radix-Decluster can be integrated in a NSM-based RDBMS using projection indices. REPORT INS-E0406 JUNE 2004 INS

show abstract

A decomposition storage model

Abstract: This report examines the relative advantages of a storage model based on decomposition (of community view relations into binary relations containing a surrogate and one attribute) over conventional n-ary storage models

Cited by 272 publications

References 23 publications

Architecture for distributed multimedia database systems

Architecture for distributed multimedia database systems

CPU and cache efficient management of memory-resident databases

Cache-Conscious Radix-Decluster Projections

Contact Info

Product

Resources

About