• Home
  • Search
  • A Linear Algebra Formulation for Optimising Replication in Data Parallel Programs
  • Cite Icon4
  • https://doi.org/10.1007/3-540-44905-1_7Copy DOI Icon

A Linear Algebra Formulation for Optimising Replication in Data Parallel Programs

  • Jan 1, 2000
  • Olav Beckmann +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, we present an efficient technique for optimising data replication under the data parallel programming model. We propose a precise mathematical representation for data replication which allows handling replication as an explicit, separate stage in the parallel data placement problem. This representation takes the form of an invertible mapping. We argue that this property is key to making data replication amenable to good mathematical optimisation algorithms. We further outline an algorithm for optimising data replication, based on this representation, which performs interprocedural data placement optimisation over a sequence of loop nests. We have implemented the algorithm and show performance figures.KeywordsLoop NestData ReplicationData PlacementSimple ReductionCopy FunctionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Similar Papers
  • Research Article

Mapping strategies in data parallel programming models; the projection methods

  • Jan 01, 2001
  • Scalable Computing Practice and Experience
  • Nahid Emad
  • Research Article
  • Citations13

Optimal Data Placement and Replication Approach for SIoT with Edge

  • Jan 01, 2022
  • Computer Systems Science and Engineering
  • B Prabhu Shankar +1
  • Research Article
  • Citations10

Dynamic data replication and placement strategy in geographically distributed data centers

  • Feb 01, 2022
  • Concurrency and Computation: Practice and Experience
  • Laila Bouhouch +2
  • Conference Article
  • Citations8

Compiling data parallel programs to message passing programs for massively parallel MIMD systems

  • Sep 20, 1993
  • T Brandes
  • Conference Article
  • Citations6

Unifying Data and Replica Placement for Data-intensive Services in Geographically Distributed Clouds

  • Jan 01, 2019
  • Ankita Atrey +4
  • Conference Article
  • Citations6

On static timing analysis of GPU kernels

  • Jan 01, 2014
  • DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
  • Vesa Hirvisalo
  • Book Chapter
  • Citations3

Data Parallel Programming and Basic Linear Algebra Subroutines

  • Jan 01, 1988
  • S Lennart Johnsson
  • Book Chapter

Chapter 5 - Collective Communication Support

  • Jan 01, 2003
  • Interconnection Networks
  • José Duato +2
  • Book Chapter
  • Citations14

A calculational approach to flattening nested data parallelism in functional languages

  • Jan 01, 1996
  • Gabriele Keller +1
  • Supplementary Content
  • Citations3

SIMD code generation in data-parallel programming

  • Jan 01, 2009
  • Publications of the UdS (Saarland University)
  • Nicolas Fritz
  • Research Article
  • Citations54

Performance analysis of data intensive cloud systems based on data management and replication: a survey

  • Mar 14, 2015
  • Distributed and Parallel Databases
  • Saif Ur Rehman Malik +16
  • Book Chapter

Adding associative meshes to the PACCO I.P. environment

  • Jan 01, 1997
  • Alberto Biancardi +1
  • Conference Article
  • Citations8

QoS-Aware Proactive Data Replication for Big Data Analytics in Edge Clouds

  • Aug 05, 2019
  • Qiufen Xia +5
  • Research Article

Sequence Similarity Parallelization over Heterogeneous Computer Clusters Using Data Parallel Programming Model

  • Mar 26, 2017
  • Scalable Computing: Practice and Experience
  • Majid Hajibaba +2
  • Conference Article

Design, Implementation and Evaluation of Built-in Functions on Parallel Programming Model in SMYLE OpenCL

  • Sep 01, 2013
  • Noriko Etani +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.