Re: Cache access at compile time

Dan Truong <dtruong@irisa.fr>
7 Dec 1999 00:36:04 -0500

          From comp.compilers
Related articles
Cache access at compile time abhi@bdc6.cs.iastate.edu (1999-11-16)
Re: Cache access at compile time Daniel.Vogelheim@post.rwth-aachen.de (Daniel Vogelheim) (1999-11-21)
Re: Cache access at compile time Sid-Ahmed-Ali.TOUATI@inria.fr (Sid Ahmed Ali TOUATI) (1999-11-28)
Re: Cache access at compile time dtruong@irisa.fr (Dan Truong) (1999-12-07)
| List of all articles for this month |
From: Dan Truong <dtruong@irisa.fr>
Newsgroups: comp.compilers
Date: 7 Dec 1999 00:36:04 -0500
Organization: IRISA, FRANCE
References: 99-11-075 99-11-126 99-11-160
Keywords: architecture, storage, optimize

For arrays you may look at Olivier Temam's work (IRISA and PRISM in
France) or look at Sieh's work (sp?) or Martonansi's students
(Princeton I think). This question should be asked in Comp.arch
rather than comp.compilers IMHO, as this is more an architectural
problem found at compiler level.


Estimating miss cost in loops boils down to solving Diophantine
equations for arrays. These estimations are used to perform array
padding and loop transformations.


Dan-
--
Dan N. Truong, IRISA, Campus de Beaulieu, 35042 Rennes Cedex, FRANCE
tel:(+33)2 99 84 73 36 fax:(+33)2 99 84 25 28 cellular:06 14 78 06 95
mailto:dtruong@irisa.fr homepage:http://www.irisa.fr/caps/PEOPLE/Dan
beeper:http://www.irisa.fr/caps/PEOPLE/Dan/msg.html

Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.