Static memory management within bytecode languages on multicore systems

Abstract

Object-code virtualization, commonly used to achieve software portability, relies on a virtual execution environment, typically comprising an interpreter used for initial execution of methods, and a JIT for native code generation. The availability of multiple processors on current architectures makes it attractive to perform dynamic compilation in parallel with application execution. The pipeline model is appealing for the compilation tasks that dynamic compilers need to perform, but it can bring deadlock issues when static memories are exploited by the running program. This research suggests a solution that both solves the mentioned problem and reduces the unnecessary compiler threads used to handle static memories. The proposed solution is a self-aware runtime system that both it is able to detect/avoid deadlocks and it adapts the number of compilation threads needed to handle static memories to the current workload.