Meta optimization: improving compiler heuristics with machine learning

By M. Stephenson, Saman P. Amarasinghe, M. Martin, U. O'Reilly. ACM-SIGPLAN Symposium on Programming Language Design and Implementation, 2003

316 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Hardware and Architecture, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/a64898b11dcfe41a1596344f39ca22f1ebdf2288

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Marc Toussaint
2. Christopher K. I. Williams
3. J. Demmel
4. R. Vuduc
5. Edwin V. Bonilla

In Hardware and Architecture

1. J. Demmel
2. R. Vuduc
3. K. Yelick

In Management Science and Operations Research

1. Marc Toussaint
2. Christopher K. I. Williams
3. J. Demmel
4. R. Vuduc
5. Edwin V. Bonilla

Citations in the corpus

• Automatic performance tuning of sparse matrix kernels (2003, methodology): “The Meta Optimization project proposes automatic tuning of the compiler’s internal priority (or cost) functions [286].”
• Search Based Software Engineering: A Comprehensive Analysis and Review of Trends Techniques and Applications (2009, unknown): “[443] 2003 Automatic programming, compiler optimisation Minimise code execution time (the fastest code is the fittest) Tree GP Real”
• Using machine learning to focus iterative optimization (2006, methodology): “[18] used genetic programming to tune heuristic priority functions for three compiler optimizations: within the Trimaran’s IMPACT compiler.”