Proceedings Article10.1145/337449.337474
HBench:Java: an application-specific benchmarking framework for Java virtual machines
Xiaolan Zhang,Margo Seltzer +1 more
- 03 Jun 2000
- pp 62-70
24
TL;DR: The performance results demonstrate HBench:Java’ s superiority over traditional benchmarking approaches in predicting real application performance and its ability to pinpoint performance problems.
read more
Abstract: Java applications represent a broad class of programs, ranging from programs running on embedded products to highperformance server applications. Standard Java benchmarks ignore this fact and assume a fixed workload. When an actual application’s beha vior differs from that included in a standard benchmark, the benchmark results are useless, if not misleading. In this paper, we present HBench:Java, an application-specific benchmarking framework, based on the concept that a s ystem's performance must be measured in the context of the application of interest. HBench:Java employs a methodology that uses vectors to characterize the application and the underlying JVM and carefully combines the two vectors to form a single metric that reflects a specific application’ s performance on a particular JVM such that the per formance of multiple JVMs can be realistically compared. Our performance results demonstrate HBench:Java’ s superiority over traditional benchmarking approaches in predicting real application performance and its ability to pinpoint performance problems.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Using Genetic Search for Reverse Engineering of Parametric Behavior Models for Performance Prediction
TL;DR: This paper presents a novel comprehensive approach for reverse engineering and performance prediction of components using genetic programming for reconstructing a behavior model from monitoring data, runtime bytecode counts, and static bytecode analysis.
Patent
Measuring software system performance using benchmarks
Andreas Blumenthal,Mirko Luedde,Thomas Manzke,Bjoern Mielenhausen,Christiaan E. Swanepoel +4 more
- 03 Sep 2004
TL;DR: In this paper, the authors use a dynamic synthetic benchmark to evaluate the performance of a program application running on a virtual machine using a load profile that includes information about instructions that make up the application, their call frequencies, and their workloads.
80
Performance Prediction for Black-Box Components Using Reengineered Parametric Behaviour Models
Michael Kuperberg,Klaus Krogmann,Ralf Reussner +2 more
- 14 Oct 2008
TL;DR: A novel integrated approach is presented that overcomes limitations by reconstructing behaviour models with platform-independent resource demands of bytecode components with parameterised over input parameter values and is validated by predicting the performance of a file sharing application.
Patent
Application execution profiling in conjunction with a virtual machine
Gerard Chauvel,Dominique D'Inverno,Serge Lasserre,Gilbert Cabillic,Jean-Philippe Lesot,Michel Banatre,Frederic Parain,Jean-Paul Routeau +7 more
- 29 Jan 2002
TL;DR: In this article, a profiling system independently creates application profiles (10) that indicate the number of executions of each operation in the application and virtual machine profiles (14) which indicate the time/energy consumed by each operation on a particular hardware platform.
28
References
Machine characterization based on an abstract high-level language machine
TL;DR: A metric based on pershapes is introduced that provides a quantitative way of measuring how similar two machines are in terms of their performance distributions.
92
•Proceedings Article
Comprehensive profiling support in the java TM virtual machine
Sheng Liang,Deepa Viswanathan +1 more
- 03 May 1999
TL;DR: A general-purpose, portable, and extensible approach for obtaining comprehensive profiling information from the Java virtual machine, which can uncover CPU usage hot spots, heavy memory allocation sites, unnecessary object retention, contended monitors, and thread deadlocks.
A methodology for benchmarking Java Grande applications
J. M. Bull,Lorna Smith,Martin Westhead,D. S. Henty,R. A. Davey +4 more
- 01 Jun 1999
TL;DR: Initial results presented here show interesting differences between JVMs, demonstrating the validity of EPCC's approach, and future work will concentrate on parallel benchmarks.
74
Analysis and development of Java Grande benchmarks
J. A. Mathew,Paul Coddington,Ken A. Hawick +2 more
- 01 Jun 1999
TL;DR: A range of Java benchmark programs are reviewed, including those collected by the Java Grande Forum as useful performance indicators for large-scale scientific applications, or “Java Grande applications”, and some general trends in the performance of Java on various platforms are observed.
74
Machine Characterization Based on an Abstract High-level Language Machine
Rafael H. Saavedra-Barrera,Alan Jay Smith,Eugene Miya +2 more
- 02 Nov 1990
TL;DR: A linear performance model decomposes program execution into n distinct operations, such as adds, multiplies, loads, and stores, and a machine is characterized as an n-vector of operation times, which is the time required for the machine to execute the program.
50