A reindexing based approach towards mapping of DAG with affine schedules onto parallel embedded systems

DOI10.1016/j.jpdc.2008.08.004zbMath1327.68048OpenAlexW2004091032MaRDI QIDQ897394

Tanguy Risset, Patrice Quinton, Clémentin Tayou Djamegni, Sanjay V. Rajopadhye, Maurice Tchuente

Publication date: 18 December 2015

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

Full work available at URL: https://doi.org/10.1016/j.jpdc.2008.08.004

zbMATH Keywords

systolic arraysdependence graphallocation functionparallel embedded systemsre-indexingspace-optimalityspace-time complexitytiming functiontiming surface

Mathematics Subject Classification ID

Graph theory (including graph drawing) in computer science (68R10) Performance evaluation, queueing, and scheduling in the context of computer systems (68M20) Mathematical problems of computer architecture (68M07) Distributed systems (68M14)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Spacetime-minimal systolic arrays for Gaussian elimination and the algebraic path problem
• Triangular matrix inversion of systolic arrays
• Dynamic programming on two-dimensional systolic arrays
• Derivation of systolic algorithms for the algebraic path problem by recurrence transformations
• PICO-NPA: High-level synthesis of nonprogrammable hardware accelerators
• Mapping rectangular mesh algorithms onto asymptotically space-optimal arrays
• Complexity of matrix product on modular linear systolic arrays for algorithms with affine schedules
• Partitioning of processor arrays: a piecewise regular approach
• On the Analysis and Synthesis of VLSI Algorithms
• The mapping of linear recurrence equations on regular arrays
• The parallel execution of DO loops
• Time optimal linear schedules for algorithms with uniform dependencies
• The Organization of Computations for Uniform Recurrence Equations