|Interprocedural analysis in Parallelizing compiler firstname.lastname@example.org (1993-11-05)|
|Re: Interprocedural analysis in Parallelizing compiler email@example.com (1993-11-09)|
|From:||firstname.lastname@example.org (Preston Briggs)|
|Keywords:||Fortran, parallel, optimize, bibliography|
|Organization:||Rice University, Houston|
|Date:||Tue, 9 Nov 1993 02:17:38 GMT|
email@example.com (Kamal Prasad) writes:
> I am looking for a paper/method which does the foll:- In Fortran,
>one can specify in a call the dimensions of an array on which the routine
>will act. If we assume that the subroutine will act on the entire array,
>then this leads to a loss of potential parallelism. This loss is to be
>eleminated by evaluating the strip of array passed.
>The routine will evaluate the portion of array bounded by the values of
>the parameters. Any statement in the calling routine that modifies/uses
>portions of array A not being passed to abc can be executed in parallel
>with call statement.
This sort of analysis is called "array section analysis."
A paper is
author="Vasanth Balasundaram and Ken Kennedy",
title="A Technique for Summarizing Data Access and Its Use in
Parallelism Enhancing Transformations",
where "pldi89" is the proceedings of the 1989 condference on
Programming Language Design and Implementation.
Return to the
Search the comp.compilers archives again.