Analysis of Different Modelling Techniques for Phase Ordering

J  Andrews   and T  Sasikala

doi:10.17485/ijst/2014/v7i1.14

Article

Analysis of Different Modelling Techniques for Phase Ordering

VIEWS 684
PDF 332

Abstract
Full-Text HTML
Full-Text PDF
How to Cite

Indian Journal of Science and Technology

DOI: 10.17485/ijst/2014/v7i1.14

Year: 2014, Volume: 7, Issue: 1, Pages: 63-68

Original Article

Analysis of Different Modelling Techniques for Phase Ordering

J. Andrews^1* and T. Sasikala²

¹Research Scholar, Sathyabama University, Chennai, India
²Principal, SRR Engineering College, Padur, Chennai, India

*Author for the correspondence:
J. Andrews
Research Scholar, Sathyabama University, Chennai, India
E-mail: [email protected]

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

In this paper we have proposed Multi Variant Modelling Technique for selection and ordering of objective functions for compiler optimization. This model is evaluated in comparison with Linear and Interactive Modelling. Focus is mainly on Phase Order Searching. The result shows that performance achieved by multi variant modelling outperforms other modelling techniques using Mibench Benchmark applications.

Keywords: Compiler Optimization, Machine Learning, Benchmark, Modelling.