Runtime Support of Speculative Optimization for Offline Escape Analysis

Escape analysis can improve the speed and memory efficiency of garbage collected languages by allocating objects to the call stack, but an offline analysis will potentially interfere with dynamic class loading and an online analysis must sacrifice precision for speed. We describe a technique that permits the safe use of aggressive, speculative offline escape analysis in programs potentially loading classes that violate the analysis results. Keywords Escape Analysis, Dynamic Class Loading, Speculative Optimization, Automatic Refactoring

• Type: Conference
• Year: 2007
• Where: SERP
• Authors: Kevin Cleereman, Michelle Cheatham, Krishnaprasad Thirunarayan
• Keywords: Dynamic Class Loading, Escape Analysis, Offline Escape Analysis, SERP 2007, Software Engineering