Skip to Main content Skip to Navigation
Conference papers

Iterative compilation in a non-linear optimisation space

Abstract : This paper investigates the applicability of iterative search techniques in program optimisation. Iterative compilation is usually considered too expensive for general purpose computing but is applicable to embedded applications where the cost is easily amortised over the number of embedded systems produced. This paper presents a case study, where an iterative search algorithm is used to investigate a nonlinear transformation space and find the fastest execution time within a fixed number of evaluations. By using execution time as feedback, it searches a large but restricted transformation space and shows performance improvement over existing approaches. We showthat in the case of large transformation spaces, we can achieve within 0.3% of the best possible time by visiting less then 0.25% of the space using a simple algorithm and find the minimum after visiting less than 1% of the space.
Document type :
Conference papers
Complete list of metadata

Cited literature [6 references]  Display  Hide  Download

https://hal.inria.fr/inria-00475919
Contributor : Erven Rohou <>
Submitted on : Friday, April 23, 2010 - 12:17:48 PM
Last modification on : Tuesday, June 15, 2021 - 4:14:59 PM
Long-term archiving on: : Tuesday, September 28, 2010 - 12:32:29 PM

File

iterative.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00475919, version 1

Citation

François Bodin, Toru Kisuki, Peter Knijnenburg, Mike O' Boyle, Erven Rohou. Iterative compilation in a non-linear optimisation space. Workshop on Profile and Feedback-Directed Compilation, Oct 1998, Paris, France. ⟨inria-00475919⟩

Share

Metrics

Record views

919

Files downloads

621