• Corpus ID: 6975124

More Eecient Serialization and Rmi for Java

  title={More Eecient Serialization and Rmi for Java},
  author={Michael Philippsen and Bernhard Haumacher},
In current Java implementations, Remote Method Invocation (RMI) is too slow, especially for high performance computing. RMI is designed for wide-area and high-latency networks, it is based on a slow object serialization, and it does not support high-performance communication networks. The paper demonstrates that a much faster drop-in RMI and an e cient drop-in serialization can be designed and implemented completely in Java without any native code. Moreover, the re-designed RMI supports nonTCP… 

Figures and Tables from this paper

Java Virtual Machine support for object serialization

A subset of Java's object serialization protocol in native code is implemented, using the Java Native Interface (JNI) and JVM internals, and it is shown that this approach is up to eight times faster than Java's original objectserialization protocol for array objects.

Java Communications for Large-Scale Parallel Computing

The results demonstrate that fast parallel and distributed computing in Java is indeed possible and an efficient serialization and improved RMI design and implementation save more than 50% of the runtime in comparison to the standard implementations available at the moment.

Client Rem oteObject Skeleton Stub Registry

This paper presents the design issues in layering a C++ and Java based RMI system on top of SOAP RPC along with an XML Pull Parser that is designed to parse SOAP calls and explains the various features of the resulting SoapRMI system.

JavaGrande - High Performance Computing with Java

The JavaGrande Forum is a group of users, researchers, and interested parties from industry trying to use Java for resource-intensive applications or improve the Java platform, making it possible to create large-sized applications that run quickly and efficiently in Java.

Scientific Computation

It is found that although ineecient for communication intensive problems, JavaSpaces yields good speedups for parametric experiments, relative to both sequential Java and C, which boosts performance without compromising Java portability or extensive algorithm recoding.

Casanova: a language for game development

It is concluded that Casanova is not just capable of making games, but that it also makes it easier to create games and to avoid bugs and common pitfalls.



An efficient implementation of Java's remote method invocation

This paper builds a Java system based on a native compiler, which supports both compile time and run time generation of marshallers, and finds that almost all of the run time overhead of RMI can be pushed to compile time.

Parastation Eecient Parallel Computing by Clustering Workstations Design and Evaluation

Implementations of ParaStation using various platforms, such as Digi-tal's AlphaGeneration workstations and Linux PCs, achieve end-to-end latencies as low as 2s and a sustained bandwidth of up to 15 Mbyte/s per channel, even with small packets.

ParaStation: Efficient parallel computing by clustering workstations: Design and evaluation

Java/DSM: A Platform for Heterogeneous Computing

Compared with existing approaches for heterogeneous computing, this system transparently handles both the hardware differences and the distributed nature of the system and is therefore much easier to program.

Reflective remote method invocation

Reflective RMI (RRMI) is an open RMI implementation which makes better use of the object-oriented features of Java and directly employs the reflection capabilities of the current Java language to invoke methods remotely.

Performance evaluation of popular distributed object technologies for Java

The performance of primitive object operations including remote object creation, remote method call, transferring arrays of objects and transferring large numerical data is measured and evaluated and no DOT won all benchmarks, but HORB showed very good performance for most benchmarks.

TreadMarks: Distributed Shared Memory on Standard Workstations and Operating Systems

A performance evaluation of TreadMarks running on Ultrix using DECstation-5000/240's that are connected by a 100-Mbps switch-based ATM LAN and a 10-Mbps Ethernet supports the contention that, with suitable networking technology, DSM is a viable technique for parallel computation on clusters of workstations.

Java RMI performance and object model interoperability: experiments with Java/HPC++

This paper explores the design of RMI and extracts a subset of the RMI object model that is compatible with C++ and HPC++ remote object semantics and is being used as part of the LSA distributed linear system analyzer project.

Performance of the Firefly RPC

This paper reports on the performance of the remote procedure call (RPC) implementation for the Firefly multiprocessor and analyzes the implementation to account precisely for all measured latency and estimates how much faster RPC could be if certain improvements were made.

Interfacing Java to the virtual interface architecture

Javia is described, a Java interface to the Virtual Interface Architecture (VIA), an emerging UNI standard in the industry that allows Java programs to allocate arrays in pinned memory and use them as communication buffers without copy.