Optimizing for reduced code space using genetic algorithms
Proceedings of the ACM SIGPLAN 1999 workshop on Languages, compilers, and tools for embedded systems
Scheduling straight-line code using reinforcement learning and rollouts
Proceedings of the 1998 conference on Advances in neural information processing systems II
Machine Learning
A Comparative Study on Feature Selection in Text Categorization
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Meta optimization: improving compiler heuristics with machine learning
PLDI '03 Proceedings of the ACM SIGPLAN 2003 conference on Programming language design and implementation
Inducing heuristics to decide whether to schedule
Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation
Using Machine Learning to Focus Iterative Optimization
Proceedings of the International Symposium on Code Generation and Optimization
Method-specific dynamic compilation using logistic regression
Proceedings of the 21st annual ACM SIGPLAN conference on Object-oriented programming systems, languages, and applications
Efficiently exploring architectural design spaces via predictive modeling
Proceedings of the 12th international conference on Architectural support for programming languages and operating systems
Automatic Feature Generation for Machine Learning Based Optimizing Compilation
Proceedings of the 7th annual IEEE/ACM International Symposium on Code Generation and Optimization
Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
Automatic creation of tile size selection models
Proceedings of the 8th annual IEEE/ACM international symposium on Code generation and optimization
A case for machine learning to optimize multicore performance
HotPar'09 Proceedings of the First USENIX conference on Hot topics in parallelism
Spatial Based Feature Generation for Machine Learning Based Optimization Compilation
ICMLA '10 Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications
Hi-index | 0.00 |
Modern compilers have many optimization passes which help to get a better binary code for a given program. These optimizations are NP-hard. People use different heuristics to get a near optimal solution. These heuristics are designed by a compiler expert after examining sample programs. This is a challenging task. Recently, people have used machine learning techniques instead of heuristics for compiler optimizations. Machine learning techniques have not only eliminated the human efforts but have also out-performed human made huristics. However, the human efforts have now been moved from creating heuristics to selecting good features. Selecting right set of features is important for machine learning techniques since no machine learning tool will work well with poorly choosen features. This paper introduces a noval approach to generate features for machine learning for compiler optimization problems with out any human involvement.