Name
Abstract | ||
|---|---|---|
Hardware-software codesign is a powerful technique that can be used to build complex systems. In this paper, we propose a compiler driven hardware-software codesign strategy that works at application level, aiming at facilitating algorithm architecture co-explorations. The proposed approach employs an intermediate code representation, called loop hierarchy tree (LHT), to perform codesign exploration, and applies a branch-and-bound search to find a hardware-software partitioning that minimizes execution latency under the given area constraints. We also developed fast cost estimation models for LHT and can be extended to handle codesign for more complex hybrid architectures. Experimental results show that our approach is successful in finding good solutions for the applications on the target codesign platform. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/SASP.2009.5226327 | SASP |
Keywords | Field | DocType |
loop intensive applications,trees (mathematics),tree searching,compiler driven hardware software codesign strategy,cost estimation models,software architecture,loop hierarchy tree,hardware-software codesign,algorithm architecture coexplorations,branch and bound search,program compilers,application software,estimation,hardware,cost estimation,complex system,branch and bound,embedded computing,pediatrics,space exploration,computer architecture,field programmable gate arrays,testing | Complex system,Computer science,Real-time computing,Software,Application software,Cost estimation models,Computer architecture,Parallel computing,Field-programmable gate array,Compiler,Software architecture,For loop,Embedded system | Conference |
ISBN | Citations | PageRank |
978-1-4244-4938-5 | 4 | 0.45 |
References | Authors | |
19 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuanrui Zhang | 1 | 180 | 15.48 |
| Mahmut T. Kandemir | 2 | 7371 | 568.54 |