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

Abstract : We address the problem of optimally mapping uniform DAGs to systolic arrays, given an ane timing function. We introduce an automatic allocation method based on a preprocessing by reindexing that transforms the initial DAG into a new one that enables the well known projection method to minimize the number of processors along a number of directions. We demonstrate its superiority to other methods, and establish the space-optimality of the proposed method. We also show an upper bound on the number of processors that corresponds to the best space complexity that both the projection method and the so-called grouping method can give for the initial DAG. We also describe how the new allocation method can be implemented in tools.
Document type :
Journal articles
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00410708
Contributor : Tanguy Risset <>
Submitted on : Monday, August 24, 2009 - 10:52:46 AM
Last modification on : Thursday, November 21, 2019 - 1:53:06 AM
Long-term archiving on: Tuesday, June 15, 2010 - 10:43:11 PM

File

Allo2D.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00410708, version 1

Citation

Clementin Tayou Djamegni, Patrice Quinton, Sanjay Rajopadhye, Tanguy Risset, Maurice Tchuente. A reindexing based approach towards mapping of DAG with affine schedules onto parallel embedded systems. Journal of Parallel and Distributed Computing, Elsevier, 2009, 69 (1), pp.1-11. ⟨hal-00410708⟩

Share

Metrics

Record views

1090

Files downloads

289