Abstract | ||
---|---|---|
Software tools to aid the generation of parallel implementation from scalar code rely on very accurate dependence analysis. Conventional techniques produce dependence graphs which are unduly conservative and mean that the quality of the subsequent parallel code is severely compromised. In this paper we provide a brief description of extensions to conventional dependence analysis that involve symbolic algebra and the exploitation of user supplied knowledge. These features have been embedded with the Computer Aided Parallelisation Tools (CAPTools) software and form the basis for a set of tools that enable high quality parallel code to be generated from its scalar source semi-automatically. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1007/3-540-58430-7_63 | CONPAR |
Keywords | Field | DocType |
dependence analysis,user interaction,symbolic extensions | Graph,Computer-aided,Computer science,Scalar (physics),Symbolic computation,Dependence analysis,Theoretical computer science,Software,Inference engine | Conference |
ISBN | Citations | PageRank |
3-540-58430-7 | 0 | 0.34 |
References | Authors | |
5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
S. P. Johnson | 1 | 139 | 17.43 |
Cos S. Ierotheou | 2 | 9 | 3.70 |
M. Cross | 3 | 0 | 0.34 |
P. F. Leggett | 4 | 88 | 11.64 |