Dynamic adaptive pre-tenuring

Harris, Timothy L.

doi:10.1145/362426.362476

Cited by 14 publications

(22 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-An additional concern is programs that have popular allocation sites with poor lifetime homogeneity, or that profiling mispredicts so that we generate inappropriate immortal or long advice for them. One possible direction is to apply pretenuring adaptively [Harris 2000;Jump et al 2004]. These designs would need extensions to deal with an immortal space.…”

Section: Using Pretenuring In Practicementioning

confidence: 99%

“…However, it is conceptually problematic to apply online anything like our definition of immortal objects, since this depends on knowing when the program will end. As we discuss in more detail next, neither of the online pretenuring schemes [Harris 2000;Jump et al 2004] obtain much improvement.…”

Section: Online Pretenuring?mentioning

confidence: 99%

“…Most importantly, the more general mechanism we use to gather statistics and generate advice enables our system to combine advice from different executions and perform build-time pretenuring, which is not possible in their framework. Harris [2000] and Jump et al [2004] present dynamic pretenuring schemes. Harris samples using Agesen and Garthwaite's [2000] approach, which inserts weak pointers and after a collection, computes object lifetime statistics.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Profile-based pretenuring

Blackburn

Hertz

McKinley

et al. 2007

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

Pretenuring can reduce copying costs in garbage collectors by allocating long-lived objects into regions that the garbage collector will rarely, if ever, collect. We extend previous work on pretenuring as follows: (1) We produce pretenuring advice that is neutral with respect to the garbage collector algorithm and configuration. We thus can and do combine advice from different applications. We find for our benchmarks that predictions using object lifetimes at each allocation site in Java programs are accurate, which simplifies the pretenuring implementation.(2) We gather and apply advice to both applications and Jikes RVM , a compiler and runtime system for Java written in Java. Our results demonstrate that building combined advice into Jikes RVM from different application executions improves performance, regardless of the application Jikes RVM is compiling and executing. This build-time advice thus gives user applications some benefits of pretenuring, without any application profiling. No previous work uses profile feedback to pretenure in the runtime system. (3) We find that application-only advice also consistently improves performance, but that the combination of build-time and application-specific advice is almost always noticeably better.(4) Our same advice improves the performance of generational, Older First, and Beltway collectors, illustrating that it is collector neutral. (5) We include an immortal allocation space in addition 2 • S. M. Blackburn et al.to a nursery and older generation, and show that pretenuring to immortal space has substantial benefit.

show abstract

Section: Using Pretenuring In Practicementioning

confidence: 99%

Section: Online Pretenuring?mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Profile-based pretenuring

Blackburn

Hertz

McKinley

et al. 2007

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

show abstract

“…For each paper, we explicitly state their clustering criteria for dynamic allocations. Most existing schemes use site-based [6,5,14,9,7], typebased, [16,11]. or context-based clustering [12,3,15].…”

Section: Related Workmentioning

confidence: 99%

“…Harris [9] implements the first dynamic pretenuring scheme for Java programs in Sun's Research VM. Harris reports statistics on information that could be used at runtime to classify an allocation site as to be pretenured: object class, allocation site and dynamic call context up to a depth of five.…”

Section: Related Workmentioning

confidence: 99%

Towards intelligent analysis techniques for object pretenuring

Singer

Brown

Luján

et al. 2007

Proceedings of the 5th International Symposium on Principles and Practice of Programming in Java - PPPJ '07

View full text Add to dashboard Cite

Object pretenuring involves the identification of long-lived objects at or before their instantiation. It is a key optimization for generational garbage collection systems, which are standard in most high performance Java virtual machines. This paper presents a new study of factors that are used to indicate object lifespans. We adopt the information theory measurement of normalized mutual information to compare these various different factors in a common framework. A study of garbage collection traces from four standard Java benchmark programs shows that there is high dependence on some of these factors such as allocation site and object type. We also identify and measure new factors based on object-oriented metrics.

show abstract