Concurrent Garbage Collection Using Hardware-Assisted Profiling

Abstract

In the presence of on-chip multithreading, a Virtual Machine (VM) can readily take advantage of service threads for enhancing performance by executing tasks such as profile collection and analysis, dynamic optimization, and garbage collection concurrently with program execution. In this context, a hardware- assisted profiling mechanism is proposed. The Relational Profiling Architecture (RPA) is designed from the top down. RPA is based on a relational model similar to the relational database model. Instructions selected for profiling produce a record of information. A simple query engine examines these records for patterns, and communicates matching records to service threads. The power and flexibility of RPA is demonstrated by developing a concurrent generational garbage collector for Java. Detailed execution-driven simulations show that this collector has an average runtime overhead of 0.6%. The short pauses in the application required for synchronization with the garbage collector are at most 53µs, given a 1GHz clock frequency.