B. Creusillet and F. Irigoin. Interprocedural analyses of Fortran programs. Parallel Computing, 24(3-4):629-648, May 1998. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Themis: Component Dependence Metadata In Adaptive.. - Kelly, Beckmann.. (2001) (Correct)
....optimization. Compilers. From the perspective of conventional compiler techniques, cross component optimization concerns optimising across sequences of loop nests, which may or may not be encapsulated in subroutines. Data access summary information, as used for interprocedural analysis [13] forms metadata describing each component. Unfortunately, with irregular data (even irregular multiblock) the actual dependence between two operations is data dependent. The data alignment problem for regular data has been extensively studied [14,15] One natural approach is to exploit these ....
B. Creusillet and F. Irigoin. Interprocedural analyses of Fortran programs. Parallel Computing, 24(3-4):629-648, May 1998.
Automatic Parallelization: An Incremental, Optimistic, Practical .. - Schwartz (1999) (Correct)
....does support an e#cient intersection. Convex Polyhedra[AI91] Represent any a#ne constraints, but intersection operation (integer programming) is expensive. Presburger Formulae[Pug94] Represent some non a#ne constraints. Intersection (Omega Test) can usually be done e#ciently. Lists of Polyhedra[CI97] Represent unions of convex polyhedra without introducing approximations. Intersection operation is even less e#cient than for individual polyhedra. Guarded Array Regions[GLL97] Represent high level constraints on accesses explicitly to ensure as little approximation as possible. E#cient ....
B. Creusillet and F. Irigoin. Interprocedural Analyses of Fortran Programs. Journal on Parallel Computing, 24(3-4):629--648, June 1997.
Themis: Component Dependence Metadata In Adaptive.. - Kelly, Beckmann.. (2001) (Correct)
....optimisation. 2 Compilers. From the perspective of conventional compiler techniques, cross component optimisation concerns optimising across sequences of loop nests, which may or may not be encapsulated in subroutines. Data access summary information, as used for interprocedural analysis [14] forms metadata describing each component. Unfortunately, with irregular data (even irregular multiblock) the actual dependence between two operations is data dependent. The data alignment problem for regular data has been extensively studied [10,12] One natural approach is to exploit these ....
B. Creusillet and F. Irigoin. Interprocedural analyses of Fortran programs. Parallel Computing, 24(3--4):629--648, May 1998.
Memory Classification Analysis for Recursive C Structures - Schwartz (1999) (Correct)
....led to the generalization of existing frameworks to work with many different ones. For example, the PIPS analysis framework has adopted a generic framework supporting intervals, lists of convex polyhedra and Presburger formulae side by side with the original single convex polyhedron representation[CI97b] with the attendant rise in implementation complexity. Department of Computer Science, Courant Institute of Mathematical Sciences, New York University, 251 Mercer St. New York, NY 10012 1185, nschwart cs.nyu.edu. 1 1.1 LMADs in Fortran However, the recent introduction of the Access Region ....
Batrice Creusillet and Franois Irigoin. Interprocedural Analyses of Fortran Programs. Journal on Parallel Computing, 24(3-4):629--648, June 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC