Title :
Cross-Input Learning and Discriminative Prediction in Evolvable Virtual Machines
Author :
Mao, Feng ; Shen, Xipeng
Author_Institution :
Comput. Sci. Dept., Coll. of William & Mary, Williamsburg, VA
Abstract :
Modern languages like Java and C# rely on dynamic optimizations in virtual machines for better performance. Current dynamic optimizations are reactive. Their performance is constrained by the dependence on runtime sampling and the partial knowledge of the execution. This work tackles the problems by developing a set of techniques that make a virtual machine evolve across production runs. The virtual machine incrementally learns the relation between program inputs and optimization strategies so that it proactively predicts the optimizations suitable for a new run. The prediction is discriminative, guarded by confidence measurement through dynamic self-evaluation. We employ an enriched extensible specification language to resolve the complexities in program inputs. These techniques, implemented in Jikes RVM, produce significant performance improvement on a set of Java applications.
Keywords :
learning (artificial intelligence); optimising compilers; specification languages; virtual machines; C# language; Java application; cross-input learning; discriminative prediction; dynamic optimization; incremental learning; specification language; virtual machine; Computer science; Feature extraction; Java; Machine learning; Predictive models; Production; Programming profession; Runtime; Sampling methods; Virtual machining; Adaptive Optimization; Cross-Input Learning; Discriminative Prediction; Evolvable Computing; Input-Centric Optimization; Java Virtual Machine;
Conference_Titel :
Code Generation and Optimization, 2009. CGO 2009. International Symposium on
Conference_Location :
Seattle, WA
Print_ISBN :
978-0-7695-3576-0
DOI :
10.1109/CGO.2009.10