Indian Journal of Science and Technology
DOI: 10.17485/ijst/2014/v7i1.14
Year: 2014, Volume: 7, Issue: 1, Pages: 63-68
Original Article
J. Andrews1* 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]
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.
Subscribe now for latest articles and news.