Automatic Selection of Application-Specific Reconfigurable Processor Extensions

Christophe Wolinski 1 Krzysztof Kuchcinski 2
1 CAIRN - Energy Efficient Computing ArchItectures with Embedded Reconfigurable Resources
Inria Rennes – Bretagne Atlantique , IRISA-D3 - ARCHITECTURE
2 Department of Computer Science [Lund]
Abstract : This paper presents a new method for automatic selection of application-specific processor extensions and shows how applications are scheduled on these new reconfigurable architectures. The extensions are implemented as specialized sequential or parallel instructions. They correspond to identified most frequently occurring computational patterns or other interesting patterns and are finally selected during mapping and scheduling. Our methods can handle both time-constrained and resource-constrained scheduling. Experimental results show that the presented method provides high coverage of application graphs with small number of patterns and ensures high application execution speed-up both for sequential and parallel application execution with processor extensions implementing selected patterns.
Keywords : Reconfigurable architectures resource assignment scheduling system-level synthesis constraint programming
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download
https://hal.inria.fr/inria-00451655
Contributor : François Charot <>
Submitted on : Friday, January 29, 2010 - 3:51:11 PM
Last modification on : Friday, November 16, 2018 - 1:39:39 AM
Long-term archiving on: Friday, June 18, 2010 - 5:30:34 PM

File

wolinski-date08.pdf
Publisher files allowed on an open archive

Identifiers

Collections

CNRS | INRIA | IRISA | UNIV-RENNES1 | IRISA-D3 | INSTITUT-TELECOM | UR1-UFR-ISTIC | UNIV-RENNES

Citation

Christophe Wolinski, Krzysztof Kuchcinski. Automatic Selection of Application-Specific Reconfigurable Processor Extensions. Design, Automation & Test in Europe Conference (DATE '08), Mar 2008, Munich, Germany. pp.1214-1219, ⟨10.1145/1403375.1403670⟩. ⟨inria-00451655⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

378

Files downloads

267

 

 

Contact

archive-ouverte@inria.fr