Current approaches to parallelizing compilation perform a purely structural
analysis of the sequential code. Conversely, a semantic analysis performin
g concept assignment for code sections, can support the recognition of the
algorithms that the code implements. This can considerably help the paralle
lization process, by allowing the introduction of heuristics and an extensi
ve pruning of the search space, and thus enabling the application of more a
ggressive code transformations. It can play an important role in overcoming
the current limitations to Automatic Parallelization. In this paper we dis
cuss the applicability of concept comprehension to the parallelization proc
ess, and we present a novel technique for automatic algorithmic recognition
we have designed and implemented. We are currently developing a reverse en
gineering tool supporting the translation of sequential Fortran code into H
PF, which is based on the recognition technique we have developed. Its work
ing criteria are illustrated and discussed. (C) 1999 Elsevier Science B.V.
All rights reserved.