Parallelism in a Main-Memory System: The Performance of PRISMA/DB

Research output: Contribution to conferencePaperAcademicpeer-review

16 Downloads (Pure)

Abstract

his paper evaluates the performance of the parallel, main-memory DBMS, PRISMA/DB. First, an abstract architecture for parallel query execution is presented. A performance model for the execution of simple relational operations on this architecture is developed. The parameters in the model are set using experiments on PRISMA/DB and the performance of PRISMA/DB is analized in the context of the model. Several conclusions can be drawn from the model combined with the results of the performance experiments. Firstly, the performance of PRISMA/DB appears to be competitive with respect toother systems. Secondly, the developed model can explain the results from the performance experiments to a large extent. Also, it is concluded that observed linear speedup for small numbers of processors cannot always be extrapolated to larger numbers of processors. Finally, it is concluded that the optimal number of processors for the parallelexecution of an operation is smaller for a main- memory system than for a disk -based system. The results of this study can be used to design data fragmentation strategies for large parallel machines.
Original languageUndefined
Pages521-532
Number of pages12
Publication statusPublished - Aug 1992

Keywords

  • DB-PDB: PARALLEL DATABASES
  • IR-66478
  • EWI-7372

Cite this

@conference{14b2a8bd11664425b576b5bae377fff8,
title = "Parallelism in a Main-Memory System: The Performance of PRISMA/DB",
abstract = "his paper evaluates the performance of the parallel, main-memory DBMS, PRISMA/DB. First, an abstract architecture for parallel query execution is presented. A performance model for the execution of simple relational operations on this architecture is developed. The parameters in the model are set using experiments on PRISMA/DB and the performance of PRISMA/DB is analized in the context of the model. Several conclusions can be drawn from the model combined with the results of the performance experiments. Firstly, the performance of PRISMA/DB appears to be competitive with respect toother systems. Secondly, the developed model can explain the results from the performance experiments to a large extent. Also, it is concluded that observed linear speedup for small numbers of processors cannot always be extrapolated to larger numbers of processors. Finally, it is concluded that the optimal number of processors for the parallelexecution of an operation is smaller for a main- memory system than for a disk -based system. The results of this study can be used to design data fragmentation strategies for large parallel machines.",
keywords = "DB-PDB: PARALLEL DATABASES, IR-66478, EWI-7372",
author = "A.N. Wilschut and Jan Flokstra and Apers, {Peter M.G.}",
note = "Imported from EWI/DB PMS [db-utwente:inpr:0000003143]",
year = "1992",
month = "8",
language = "Undefined",
pages = "521--532",

}

Parallelism in a Main-Memory System: The Performance of PRISMA/DB. / Wilschut, A.N.; Flokstra, Jan; Apers, Peter M.G.

1992. 521-532.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - Parallelism in a Main-Memory System: The Performance of PRISMA/DB

AU - Wilschut, A.N.

AU - Flokstra, Jan

AU - Apers, Peter M.G.

N1 - Imported from EWI/DB PMS [db-utwente:inpr:0000003143]

PY - 1992/8

Y1 - 1992/8

N2 - his paper evaluates the performance of the parallel, main-memory DBMS, PRISMA/DB. First, an abstract architecture for parallel query execution is presented. A performance model for the execution of simple relational operations on this architecture is developed. The parameters in the model are set using experiments on PRISMA/DB and the performance of PRISMA/DB is analized in the context of the model. Several conclusions can be drawn from the model combined with the results of the performance experiments. Firstly, the performance of PRISMA/DB appears to be competitive with respect toother systems. Secondly, the developed model can explain the results from the performance experiments to a large extent. Also, it is concluded that observed linear speedup for small numbers of processors cannot always be extrapolated to larger numbers of processors. Finally, it is concluded that the optimal number of processors for the parallelexecution of an operation is smaller for a main- memory system than for a disk -based system. The results of this study can be used to design data fragmentation strategies for large parallel machines.

AB - his paper evaluates the performance of the parallel, main-memory DBMS, PRISMA/DB. First, an abstract architecture for parallel query execution is presented. A performance model for the execution of simple relational operations on this architecture is developed. The parameters in the model are set using experiments on PRISMA/DB and the performance of PRISMA/DB is analized in the context of the model. Several conclusions can be drawn from the model combined with the results of the performance experiments. Firstly, the performance of PRISMA/DB appears to be competitive with respect toother systems. Secondly, the developed model can explain the results from the performance experiments to a large extent. Also, it is concluded that observed linear speedup for small numbers of processors cannot always be extrapolated to larger numbers of processors. Finally, it is concluded that the optimal number of processors for the parallelexecution of an operation is smaller for a main- memory system than for a disk -based system. The results of this study can be used to design data fragmentation strategies for large parallel machines.

KW - DB-PDB: PARALLEL DATABASES

KW - IR-66478

KW - EWI-7372

M3 - Paper

SP - 521

EP - 532

ER -