A Multithreaded Java Grande Benchmark Suite
@inproceedings{Smith2001AMJ,
title={A Multithreaded Java Grande Benchmark Suite},
author={Lorna Smith and J. Mark Bull},
year={2001}
}Increasing interest is being shown in the use of Java for larg e scale orGrandeapplications. This new use of Java places specific demands on the Java execution envi ronments that can be tested using the Java Grande benchmark suite [5], [6], [7]. The large processing r equirements of Grandeapplications makes parallelisation of interest. A suite of shared memory paral lel benchmarks has been developed from the serial Java Grande benchmark suite, using Java native threa ds. The contents of the…
No Paper Link Available
35 Citations
A Platform-Independent Distributed Runtime for Standard Multithreaded Java
- Computer ScienceInternational Journal of Parallel Programming
- 2006
This work evaluates the efficiency of JavaSplit on several combinations of operating systems, JVM implementations, and communication hardware.
A distributed runtime for Java: yesterday and today
- Computer Science18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.
- 2004
This paper gives a detailed overview of the existing distributed runtime systems for Java and presents a new approach, implemented in a system called JavaSplit, able to execute standard multithreaded Java while preserving portability.
JavaSplit: a runtime for execution of monolithic Java programs on heterogenous collections of commodity workstations
- Computer Science2003 Proceedings IEEE International Conference on Cluster Computing
- 2003
Since Java-Split is orthogonal to the implementation of a local JVM, it achieves portability across any existing platform and allows each node to locally optimize the performance of itsJVM, e.g., via a just-in-time compiler (JIT).
EFFICIENT SUPPORT OF FINE-GRAINED FUTURES IN JAVA
- Computer Science
- 2006
This work presents and empirically evaluate a novel implementation of futures for Java that couples estimates of future computational granularity with underlying resource avail ability to enable automatic and adaptive decisions of when to spawn futures in parallel or to execute them sequentially.
Using AspectJ to separate concerns in parallel scientific Java code
- Computer ScienceAOSD '04
- 2004
It is concluded that: (1) scientific software is rarely produced in true object-oriented style; and (2) the inherent loop structure of many scientific algorithms is incompatible with the join point philosophy of AspectJ.
Java for High Performance Computing
- Computer Science
Performance issues relevant to HPC applications will be examined, and benchmarks for evaluating different Java environments, for inter-language comparisons and for testing the performance and scalability of different Java parallel models (native threads, message passing and OpenMP) will be considered.
Benchmarking the CLI for high performance computing
- Computer ScienceIEE Proc. Softw.
- 2003
Whether the common language infrastructure has any future in the high-performance computing community is reviewed by benchmarking three implementations of the CLI and comparing those with the results on Java virtual machines.
HPC.NET - are CLI-based Virtual Machines Suitable for High Performance Computing?
- Computer ScienceACM/IEEE SC 2003 Conference (SC'03)
- 2003
Whether the Common Language Infrastructure has any future in the high-performance computing community, for example by targeting the same application space as the Java-Grande Forum is reviewed.
Jthread, a deadlock-free mutex library
- Computer SciencePPDP
- 2015
We design a mutex library for Hop -- a dialect of Scheme which supports preemptive multithreading and shared memory -- that mixes deadlock prevention and deadlock avoidance to provide an easy to use,…
Performance Implications of Next-Generation Multi-processing Platforms on e-Business Server Applications
- Computer Science2008 IEEE International Conference on e-Business Engineering
- 2008
The performance evaluation and analysis show that it is practical of avoiding performance interferences among highly parallel, CPU-intensive server applications by restricting thread migration, and effective performance isolation can be achieved along with performance gain.
References
SHOWING 1-10 OF 22 REFERENCES
A benchmark suite for high performance Java
- Computer ScienceConcurr. Pract. Exp.
- 2000
The design and implementation of a standard benchmark suite for Java execution environments are described, paying particular attention to Java-specific issues.
A methodology for benchmarking Java Grande applications
- Computer ScienceJAVA '99
- 1999
Initial results presented here show interesting differences between JVMs, demonstrating the validity of EPCC's approach, and future work will concentrate on parallel benchmarks.
Benchmarking Java against C and Fortran for scientific applications
- Computer ScienceJGI '01
- 2001
A subset of the Java Grande benchmarks has been re‐written in C and Fortran allowing direct performance comparisons between the three languages.
Benchmarking Java Grande Applications
- Computer Science, Economics
- 2000
The performance of a range of Java execution environments have been tested using the Java Grande benchmark suite and the results presented.
The Hyperion system: Compiling multithreaded Java bytecode for distributed execution
- Computer ScienceParallel Comput.
- 2001
Compiling Multithreaded Java Bytecode for Distributed Execution (Distinguished Paper)
- Computer ScienceEuro-Par
- 2000
Our work combines Java compilation to native code with a run-time library that executes Java threads in a distributed-memory environment. This allows a Java programmer to view a cluster of processors…
Developing a practical parallel multi-pass renderer in Java and C++: toward a Grande application in Java
- Computer ScienceJAVA '00
- 2000
As software is becoming more complicated, costs for developing and maintaining parallel applications are rapidly increasing, and reusable portable software is certainly needed even in the parallel processing area.
A more efficient RMI for Java
- Computer ScienceJAVA '99
- 1999
It is demonstrated that a much faster drop-in RMI and an efficient serialization can be designed and implemented completely in Java without any native code, and the re-designed RMI supports non-TCP/IP communication networks, even with heterogeneous transport protocols.
A high performance cluster JVM presenting a pure single system image
- Computer ScienceJAVA '00
- 2000
This paper discusses the various techniques used in cJVM to achieve high scalability, and demonstrates the usefulness of these techniques on a large (10Kloc) Java application, achieving 80% efficiency on a four-node cluster.