Skip to main content

Decrypting The Java Gene Pool: Predicting Objects' Lifetimes with Micro-patterns

Marion, Sebastien and Jones, Richard and Ryder, Chris (2007) Decrypting The Java Gene Pool: Predicting Objects' Lifetimes with Micro-patterns. In: ISMM '07 Proceedings of the 6th international symposium on Memory management. ISMM International Symposium on Memory Management . ACM, New York, USA, pp. 67-78. ISBN 978-1-59593-893-0. (doi:10.1145/1296907.1296918)

PDF - Author's Accepted Manuscript
Download (235kB) Preview
[img]
Preview
Official URL
https://dx.doi.org/10.1145/1296907.1296918

Abstract

Pretenuring long-lived and immortal objects into infrequently or never collected regions reduces garbage collection costs significantly. However, extant approaches either require computationally expensive, application-specific, off-line profiling, or consider only allocation sites common to all programs, i.e. invoked by the virtual machine rather than application programs. In contrast, we show how a simple program analysis, combined with an object lifetime knowledge bank, can be exploited to match both runtime system and application program structure with object lifetimes. The complexity of the analysis is linear in the size of the program, so need not be run ahead of time. We obtain performance gains between 6-77% in GC time against a generational copying collector for several SPEC jvm98 programs.

Item Type: Book section
DOI/Identification number: 10.1145/1296907.1296918
Uncontrolled keywords: Garbage collection, Pretenuring, Micro-Patterns, Data Mining, Decision Trees, Java
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Faculties > Sciences > School of Computing > Systems Architecture Group
Depositing User: Richard Jones
Date Deposited: 24 Nov 2008 18:04 UTC
Last Modified: 03 Oct 2019 13:15 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/14541 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year