A solution of the cache ping-pong problem in multiprocessor systems

DOI10.1016/0743-7315(92)90030-QzbMATH Open0796.68011OpenAlexW2064160348MaRDI QIDQ1206375FDOQ1206375

Authors: Mi Lu, Jesse Zhixi Fang 

Publication date: 1 April 1993

Published in: Journal of Parallel and Distributed Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0743-7315(92)90030-q

Recommendations

• On the problem of optimizing parallel programs for complex memory hierarchies
• Volume driven selection of loop and data transformations for cache-coherent parallel processors
• Compiler controlled prefetching for multiprocessors using low-overhead traps and prefetch engines
• Languages and Compilers for Parallel Computing
• A consistent generation of pipeline parallelism and distribution of operations and data among processors

zbMATH Keywords

cache ping-pong problemparallel processing systems

Mathematics Subject Classification ID

Distributed algorithms (68W15) Mathematical problems of computer architecture (68M07)

Cited In (3)

• Partitioning and mapping of nested loops for linear array multicomputers
• The entropy of a distributed computation random number generation from memory interleaving
• A theoretical foundation for program transformations to reduce cache thrashing due to true data sharing

This page was built for publication: A solution of the cache ping-pong problem in multiprocessor systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1206375)