Performance of iterative methods for distributed memory machines

DOI10.1016/0168-9274(93)90102-WMaRDI QIDQ685971zbMATH OpenFDO

Authors E. A. Vavalis, Dan C. Marinescu, John R. Rice

Publication date 6 October 1993

Published in Applied Numerical Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0168-9274(93)90102-W

zbMATH Keywords

distributed memory machineshypercube machinesiterative methodslarge linear systemsmassively parallel machinesperformance

Mathematics Subject Classification ID

Iterative numerical methods for linear systems (65F10) Numerical solution of discretized equations for boundary value problems involving PDEs (65N22) Parallel numerical computation (65Y05) Complexity and performance of numerical algorithms (65Y20)

Recommendations

• Efficient techniques for performing an irregular computation on distributed memory machines
• Analytical estimation of the scalability of iterative numerical algorithms on distributed memory multiprocessors
• Pipelined iterative methods for shared memory machines
• Performance evaluation of iterative parallel algorithms
• Measuring the performance of parallel computers with distributed memory
• Memory Aspects and Performance of Iterative Solvers
• The performance of parallel iterative solvers
• Evaluating speedups on distributed memory architectures
• Publication:4945817

Cites work

• Algorithm 586: ITPACK 2C: A FORTRAN Package for Solving Large Sparse Linear Systems by Adaptive Accelerated Iterative Methods
• Development of Parallel Methods for a 1024-Processor Hypercube
• scientific article; zbMATH DE number 3896231 (Why is no real title available?)
• On high level characterization of parallelism

Cited in

(12)

• A practical and portable model of programming for iterative solvers on distributed memory machines
• Pipelined iterative methods for shared memory machines
• The local memory access sequence of multiple induction variables on distributed memory machines
• PARALLEL ITERATIVE SOLUTION OF LARGE LINEAR SYSTEMS ON HYPERCUBES
• scientific article; zbMATH DE number 1217617 (Why is no real title available?)
• Memory Aspects and Performance of Iterative Solvers
• The computational complexity of the quadrant interlocking (QI) iterative methods on shared memory parallel computers
• On the cost of iterative computations
• Iterative-method performance evaluation for multiple vectors associated with a large-scale sparse matrix
• On the speedup of parallel iterative numerical methods
• The communication performance of the Cray T3D and its effect on iterative solvers
• The performance of parallel iterative solvers

Describes a project that uses

Uses Software

• ITPACK
• ELLPACK

This page was built for publication: Performance of iterative methods for distributed memory machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q685971)