Abstract | ||
---|---|---|
In this paper we develop compilation techniques for the realization of applications described in a High Level Language (HLL) onto a Runtime Reconfigurable Architecture. The compiler determines Hyper Operations (HyperOps) that are subgraphs of a data flow graph (of an application) and comprise elementary operations that have strong producer-consumer relationship. These HyperOps are hosted on computation structures that are provisioned on demand at runtime. We also report compiler optimizations that collectively reduce the overheads of data-driven computations in runtime reconfigurable architectures. On an average, HyperOps offer a 44% reduction in total execution time and a 18% reduction in management overheads as compared to using basic blocks as coarse grained operations. We show that HyperOps formed using our compiler are suitable to support data flow software pipelining. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-00641-8_21 | ARC |
Keywords | Field | DocType |
coarse grained operation,compiling techniques,compiler optimizations,runtime reconfigurable architecture,compilation technique,computation structure,coarse grained runtime reconfigurable,hyper operations,data flow graph,basic block,high level language,data flow software pipelining,compiler optimization,mechanical engineering,data flow,software pipelining | Computer architecture,Software pipelining,Computer science,Parallel computing,Binary decision diagram,Data-flow analysis,Optimizing compiler,Compiler,High-level programming language,Data flow diagram,Computation | Conference |
Volume | ISSN | Citations |
5453 | 0302-9743 | 13 |
PageRank | References | Authors |
0.91 | 17 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mythri Alle | 1 | 87 | 8.34 |
Keshavan Varadarajan | 2 | 106 | 9.96 |
Alexander Fell | 3 | 66 | 8.66 |
S. K. Nandy | 4 | 320 | 50.83 |
Ranjani Narayan | 5 | 155 | 21.06 |