A comprehensive toolchain for workload characterization across JVM languages

Sarimbekov, Aibek; Sewe, Andreas; Kell, Stephen; Zheng, Yudi; Binder, Walter; Bulej, Lubomír; Ansaloni, Danilo

doi:10.1145/2462029.2462033

Cited by 6 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The research presented in this paper can be seen as a continuation of our previous work [20][21][22] and complementary to that of Li et al [16], who recently published an exploratory study characterizing workloads for five JVM languages using both CLBG project and real-world application benchmarks.…”

Section: Related Workmentioning

confidence: 62%

“…Using our workload characterization suite [20], we collected and analyzed hundreds of gigabytes of data resulting from weeks of running experiments with the aim to contribute to the understanding of the characteristics of workloads produced by dynamic languages executing on the JVM. Due to the lack of a proper benchmarking suite for the dynamic languages, we opted, like Li et al [16] before us, to use the benchmarks from the CLBG project augmented with several real-world applications as the workloads for our study.…”

Section: Discussionmentioning

confidence: 99%

“…The metrics were collected using our workload characterization suite [20], which relies on bytecode instrumentation, and provides a near-complete bytecode coverage. We were thus able to collect metrics that cover both the application (and the dynamic language runtime) and the Java Class Library (including any proprietary JVM vendor-specific classes) on a standard JVM.…”

Section: Metricsmentioning

confidence: 99%

“…This notion is dynamic in the sense that it may hold only for a particular program execution or for a specific program input [20,21].…”

Section: Field Object and Class Immutabilitymentioning

confidence: 99%

“…In contrast, the execution characteristics of various dynamically-typed JVM languages have so far not been studied very extensively. We have previously presented a comprehensive toolchain [20] for workload characterization across JVM languages 2 , which was successfully applied in studying the differences between Scala and Java workloads [21,22]. Recently, our toolchain was applied in a study of execution characteristics of JVM languages by Li et al [16], which included Clojure, JRuby, and Jython, as representatives of popular dynamic JVM languages.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Characteristics of dynamic JVM languages

Sarimbekov

Podzimek

Bulej

et al. 2013

Proceedings of the 7th ACM Workshop on Virtual Machines and Intermediate Languages

Self Cite

View full text Add to dashboard Cite

The Java Virtual Machine (JVM) has become an execution platform targeted by many programming languages. However, unlike with Java, a statically-typed language, the performance of the JVM and its Just-In-Time (JIT) compiler with dynamically-typed languages lags behind purpose-built language-specific JIT compilers. In this paper, we aim to contribute to the understanding of the workloads imposed on the JVM by dynamic languages. We use various metrics to characterize the dynamic behavior of a variety of programs written in three dynamic languages (Clojure, Python, and Ruby) executing on the JVM. We identify the differences with respect to Java, and briefly discuss their implications.

show abstract

Section: Related Workmentioning

confidence: 62%

Section: Discussionmentioning

confidence: 99%

Section: Metricsmentioning

confidence: 99%

“…This notion is dynamic in the sense that it may hold only for a particular program execution or for a specific program input [20,21].…”

Section: Field Object and Class Immutabilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Characteristics of dynamic JVM languages

Sarimbekov

Podzimek

Bulej

et al. 2013

Proceedings of the 7th ACM Workshop on Virtual Machines and Intermediate Languages

Self Cite

View full text Add to dashboard Cite

show abstract

Workload characterization of JVM languages

Sarimbekov

Mössenböck

Bulej

et al. 2015

Softw. Pract. Exper.

Self Cite

View full text Add to dashboard Cite

SUMMARYOriginally developed with a single language in mind, the JVM is now targeted by numerous programming languages-its automatic memory management, just-in-time compilation, and adaptive optimizationsmaking it an attractive execution platform. However, the garbage collector, the just-in-time compiler, and other optimizations and heuristics were designed primarily with the performance of Java programs in mind. Consequently, many of the languages targeting the JVM, and especially the dynamically typed languages, are suffering from performance problems that cannot be simply solved at the JVM side. In this article, we aim to contribute to the understanding of the character of the workloads imposed on the JVM by both dynamically typed and statically typed JVM languages. To this end, we introduce a new set of dynamic metrics for workload characterization, along with an easy-to-use toolchain to collect the metrics. We apply the toolchain to applications written in six JVM languages (Java, Scala, Clojure, Jython, JRuby, and JavaScript) and discuss the findings. Given the recently identified importance of inlining for the performance of Scala programs, we also analyze the inlining behavior of the HotSpot JVM when executing bytecode originating from different JVM languages. As a result, we identify several traits in the non-Java workloads that represent potential opportunities for optimization.

show abstract

Introduction to dynamic program analysis with DiSL

Marek

Zheng

Ansaloni

et al. 2013

Proceedings of the 4th ACM/SPEC International Conference on Performance Engineering

Self Cite

View full text Add to dashboard Cite

Dynamic program analysis (DPA) tools assist in many software engineering and development tasks, including profiling, program comprehension, and performance model construction and calibration. On the Java platform, many DPA tools are implemented either using aspect-oriented programming (AOP), or rely on bytecode instrumentation to modify the base program code. The pointcut/advice model found in AOP enables rapid tool development, but does not allow expressing certain instrumentations due to limitations of mainstream AOP languages-developers thus use bytecode manipulation to gain more expressiveness and performance. However, while the existing bytecode manipulation libraries handle some low-level details, they still make tool development tedious and error-prone. Targeting this issue, we provide the first complete presentation of DiSL, an open-source instrumentation framework that reconciles the conciseness of the AOP pointcut/advice model and the expressiveness and performance achievable with bytecode manipulation libraries. Specifically, we extend our previous work to provide an overview of the DiSL architecture, advanced features, and the programming model. We also include case studies illustrating successful deployment of DiSL-based DPA tools.

show abstract

A comprehensive toolchain for workload characterization across JVM languages

Cited by 6 publications

References 30 publications

Characteristics of dynamic JVM languages

Characteristics of dynamic JVM languages

Workload characterization of JVM languages

Introduction to dynamic program analysis with DiSL

Contact Info

Product

Resources

About