Title :
Interprocedural induction variable analysis
Author :
Tang, Peiyi ; Yew, Pen-Chung
Author_Institution :
Dept. of Comput. Sci., Arkansas Univ., Little Rock, AR, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
Induction variable analysis is an important part of the symbolic analysis in parallelizing compilers. Induction variables can be formed by FOR or DO loops within procedures or loops of recursive procedure calls. This paper presents an algorithm to find induction variables in formal parameters of procedures caused by recursive procedure calls. The compile-time knowledge of induction variables in formal parameters is essential to summarize array sections to be used for data dependency testing and parallelization
Keywords :
arrays; parallelising compilers; program control structures; program testing; subroutines; DO loops; FOR loops; array section summarization; compile-time knowledge; data dependency testing; formal parameters; interprocedural induction variable analysis; parallelization; parallelizing compilers; recursive procedure calls; symbolic analysis; Algorithm design and analysis; Computer science; Parallel architectures; Program processors; Testing;
Conference_Titel :
Parallel Architectures, Algorithms and Networks, 2002. I-SPAN '02. Proceedings. International Symposium on
Conference_Location :
Makati City, Metro Manila
Print_ISBN :
0-7695-1579-7
DOI :
10.1109/ISPAN.2002.1004289
