Publications
Detailed Information
Optimized RTL Code Generation from Coarse-Grain Dataflow Specification for Fast HW/SW Cosynthesis
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Hyunuk | - |
dc.contributor.author | Yang, Hoeseok | - |
dc.contributor.author | Ha, Soonhoi | - |
dc.date.accessioned | 2009-08-23T23:42:48Z | - |
dc.date.available | 2009-08-23T23:42:48Z | - |
dc.date.issued | 2008-07 | - |
dc.identifier.citation | J Sign Process Syst, 52(1), 13-34, July | en |
dc.identifier.issn | 1939-8018 (print) | - |
dc.identifier.issn | 1939-8115 (online) | - |
dc.identifier.uri | https://hdl.handle.net/10371/7508 | - |
dc.description.abstract | This paper presents a new methodology of automatic RTL code generation from coarse-grain dataflow specification for fast HW/SW cosynthesis. A node in a coarse-grain dataflow specification represents a functional block such as FIR and DCT and an arc may deliver multiple data samples per block invocation, which complicates the problem and distinguishes it from behavioral synthesis problem. Given optimized HW library blocks for dataflow nodes, we aim to generate the RTL codes for the entire hardware system including glue logics such as buffer and MUX, and the central controller. In the proposed design methodology, a dataflow graph can be mapped to various hardware structures by changing the resource allocation and schedule information. It simplifies the management of the area/performance tradeoff in hardware design and widens the design space of hardware implementation of a dataflow graph. We also support Fractional Rate Dataflow (FRDF) specification for more efficient hardware implementation. To overcome the additional hardware area overhead in the synthesized architecture, we propose two techniques reducing buffer overhead. Through experiments with some real examples, the usefulness of the proposed technique is demonstrated. | en |
dc.description.sponsorship | This work was supported by Brain Korea 21 project,
SystemIC 2010 project funded by Korean MOCIE, and KOSEF research program (R17-2007-086- 01001-0). This work was also partly sponsored by ETRI SoC Industry Promotion Center, Human Resource Development Project for IT SoC Architect. The ICT and ISRC at Seoul National University and IDEC provided research facilities for this study. | en |
dc.language.iso | en | en |
dc.publisher | Springer Verlag | en |
dc.subject | HW/SW codesign | en |
dc.subject | system level design | en |
dc.subject | dataflow graph (DFG) | en |
dc.subject | RTL | en |
dc.subject | VHDL | en |
dc.title | Optimized RTL Code Generation from Coarse-Grain Dataflow Specification for Fast HW/SW Cosynthesis | en |
dc.type | Article | en |
dc.contributor.AlternativeAuthor | 정현욱 | - |
dc.contributor.AlternativeAuthor | 양회석 | - |
dc.contributor.AlternativeAuthor | 하순회 | - |
dc.identifier.doi | 10.1007/s11265-007-0070-9 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.