Forskning ved Københavns Universitet - Københavns Universitet

Forside

Efficient Incremental Checkpointing of Java Programs

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Efficient Incremental Checkpointing of Java Programs. / Lawall, Julia Laetitia; Muller, Gilles.

International Conference on Dependable Systems and Networks (DSN 2000). IEEE Computer Society Press, 2000. s. 61-70.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Lawall, JL & Muller, G 2000, Efficient Incremental Checkpointing of Java Programs. i International Conference on Dependable Systems and Networks (DSN 2000). IEEE Computer Society Press, s. 61-70, International Conference on Dependable Systems and Networks, New York, NY, USA, 25/06/2000. https://doi.org/http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515

APA

Lawall, J. L., & Muller, G. (2000). Efficient Incremental Checkpointing of Java Programs. I International Conference on Dependable Systems and Networks (DSN 2000) (s. 61-70). IEEE Computer Society Press. https://doi.org/http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515

Vancouver

Lawall JL, Muller G. Efficient Incremental Checkpointing of Java Programs. I International Conference on Dependable Systems and Networks (DSN 2000). IEEE Computer Society Press. 2000. s. 61-70 https://doi.org/http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515

Author

Lawall, Julia Laetitia ; Muller, Gilles. / Efficient Incremental Checkpointing of Java Programs. International Conference on Dependable Systems and Networks (DSN 2000). IEEE Computer Society Press, 2000. s. 61-70

Bibtex

@inproceedings{2c70dbc0bb5d11debda0000ea68e967b,
title = "Efficient Incremental Checkpointing of Java Programs",
abstract = "This paper investigates the optimization of language-level checkpointing of Java programs. First, we describe how to systematically associate incremental checkpoints with Java classes. While being safe, the genericness of this solution induces substantial execution overhead. Second, to solve the dilemma of genericness versus performance, we use automatic program specialization to transform the generic checkpointing methods into highly optimized ones. Specialization exploits two kinds of information: (i) structural properties about the program classes, (ii) knowledge of unmodified data structures in specific program phases. The latter information allows us to generate phase-specific checkpointing methods. We evaluate our approach on two benchmarks, a realistic application which consists of a program analysis engine, and a synthetic program which can serve as a metric. Specialization gives a speedup proportional to the complexity of the object structure and the modification pattern. Measured speedups for the program analysis engine are up to 1.5, and for the synthetic program are up to 15.",
author = "Lawall, {Julia Laetitia} and Gilles Muller",
year = "2000",
doi = "http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515",
language = "English",
isbn = "0-7695-0707-7",
pages = "61--70",
booktitle = "International Conference on Dependable Systems and Networks (DSN 2000)",
publisher = "IEEE Computer Society Press",
note = "null ; Conference date: 25-06-2000 Through 28-06-2000",

}

RIS

TY - GEN

T1 - Efficient Incremental Checkpointing of Java Programs

AU - Lawall, Julia Laetitia

AU - Muller, Gilles

PY - 2000

Y1 - 2000

N2 - This paper investigates the optimization of language-level checkpointing of Java programs. First, we describe how to systematically associate incremental checkpoints with Java classes. While being safe, the genericness of this solution induces substantial execution overhead. Second, to solve the dilemma of genericness versus performance, we use automatic program specialization to transform the generic checkpointing methods into highly optimized ones. Specialization exploits two kinds of information: (i) structural properties about the program classes, (ii) knowledge of unmodified data structures in specific program phases. The latter information allows us to generate phase-specific checkpointing methods. We evaluate our approach on two benchmarks, a realistic application which consists of a program analysis engine, and a synthetic program which can serve as a metric. Specialization gives a speedup proportional to the complexity of the object structure and the modification pattern. Measured speedups for the program analysis engine are up to 1.5, and for the synthetic program are up to 15.

AB - This paper investigates the optimization of language-level checkpointing of Java programs. First, we describe how to systematically associate incremental checkpoints with Java classes. While being safe, the genericness of this solution induces substantial execution overhead. Second, to solve the dilemma of genericness versus performance, we use automatic program specialization to transform the generic checkpointing methods into highly optimized ones. Specialization exploits two kinds of information: (i) structural properties about the program classes, (ii) knowledge of unmodified data structures in specific program phases. The latter information allows us to generate phase-specific checkpointing methods. We evaluate our approach on two benchmarks, a realistic application which consists of a program analysis engine, and a synthetic program which can serve as a metric. Specialization gives a speedup proportional to the complexity of the object structure and the modification pattern. Measured speedups for the program analysis engine are up to 1.5, and for the synthetic program are up to 15.

U2 - http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515

DO - http://doi.ieeecomputersociety.org/10.1109/ICDSN.2000.857515

M3 - Article in proceedings

SN - 0-7695-0707-7

SP - 61

EP - 70

BT - International Conference on Dependable Systems and Networks (DSN 2000)

PB - IEEE Computer Society Press

Y2 - 25 June 2000 through 28 June 2000

ER -

ID: 15196504