|Code selection trade-offs email@example.com (Tim Frink) (2008-05-12)|
|Re: Code selection trade-offs firstname.lastname@example.org (=?windows-1252?Q?Bj=F6rn_Franke?=) (2008-05-15)|
|Re: Code selection trade-offs email@example.com (IndianTechie) (2008-05-23)|
|Re: Code selection trade-offs firstname.lastname@example.org (Walter Banks) (2008-05-24)|
|Date:||Thu, 15 May 2008 19:29:50 +0100|
|Posted-Date:||15 May 2008 20:13:28 EDT|
> Do you know of any works where profiling information/ static program
> analysis is used as a heuristic to control code selection, i.e. the
> (profiling) execution counts of particular code structures are
> influencing the choice of instructions used to translate the source
> code into assembler?
This may be a little off-topic, but in this paper a technique is used
that uses profiling based basic block execution counts to guide the
generation of new instructions for extensible processor cores that
allow you to define your own application-specific instruction set
Richard Bennett, Alastair Murray, Bjvrn Franke, and Nigel Topham.
Combining Source-to-Source Transformations and Processor Instruction Set
Extension for the Automated Design-Space Exploration of Embedded Systems.
Proceedings of ACM SIGPLAN/SIGBED 2007 Conference on Languages
Compilers, and Tools for Embedded Systems (LCTES 07), June 2007, San
Return to the
Search the comp.compilers archives again.