Open AccessProceedings Article10.1109/IPDPS.2007.370421

Parallel Java: A Unified API for Shared Memory and Cluster Parallel Programming in 100% Java

- 26 Mar 2007

- pp 1-8

TL;DR: This paper describes parallel Java's features and architecture; compares and contrasts parallel Java to other Java-based parallel middleware libraries; and reports performance measurements of parallel Java programs.

Abstract: Parallel Java is a parallel programming API whose goals are (1) to support both shared memory (thread-based) parallel programming and cluster (message-based) parallel programming in a single unified API, allowing one to write parallel programs combining both paradigms; (2) to provide the same capabilities as OpenMP and MPI in an object oriented, 100% Java API; and (3) to be easily deployed and run in a heterogeneous computing environment of single-core CPUs, multi-core CPUs, and clusters thereof. This paper describes parallel Java's features and architecture; compares and contrasts parallel Java to other Java-based parallel middleware libraries; and reports performance measurements of parallel Java programs.

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

Most frequently asked questions

1. What are the contributions in "Parallel java: a unified api for shared memory and cluster parallel programming in 100% java" ?

This paper describes Parallel Java ’ s features and architecture ; compares and contrasts Parallel Java to other Javabased parallel middleware libraries ; and reports performance measurements of Parallel Java programs.

2. What are the future works in "Parallel java: a unified api for shared memory and cluster parallel programming in 100% java" ?

Future plans for PJ include improving the performance of PJ ’ s low-level message passing classes ; improving the performance of PJ ’ s high-level message passing ( communicator ) operations ; implementing additional message passing operations such as all-reduce, all-to-all, and barrier ; and adding parallel file I/O capabilities like those of MPI-2. 0. While the work so far has focused on implementing PJ ’ s functionality, future work will also focus on performance measurements and comparisons.

Figure 4. AES key search SMP program speedup

Figure 6. PJ vs. mpiJava message passing performance

Figure 5. AES key search cluster program speedup

Citations

Patent

Parallel runtime execution on multiple processors

Aaftab A. Munshi, +1 more

- 09 Apr 2008

TL;DR: In this article, a method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described.

...read moreread less

171

Patent

Data parallel computing on multiple processors

Aaftab A. Munshi, +1 more

- 03 May 2007

TL;DR: In this article, a method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or multiple threads of the application are described.

...read moreread less

112

•Journal Article•10.1021/CT300035U

The Structure, Thermodynamics and Solubility of Organic Crystals from Simulation with a Polarizable Force Field

Michael J. Schnieders, +6 more

- 08 May 2012

- Journal of Chemical Theory and Computati...

TL;DR: The results suggest that coupling the polarizable AMOEBA force field with an orthogonal space based free energy algorithm, as implemented in the program Force Field X, is a consistent procedure for predicting the structure, thermodynamic stability and solubility of organic crystals.

...read moreread less

Patent

Application interface on multiple processors

Aaftab A. Munshi, +1 more

- 03 May 2007

TL;DR: In this paper, a programming language for a parallel computing architecture is described, which includes an API to allow an application to make calls using the API to allocate execution of the threads between the host processor and the GPU.

...read moreread less

Patent

Application programming interfaces for data parallel computing on multiple processors

Aaftab A. Munshi, +1 more

- 04 Nov 2008

TL;DR: In this paper, a method and an apparatus for a parallel computing program calling APIs (application programming interfaces) in a host processor to perform a data processing task in parallel among compute units are described.

...read moreread less

...

Expand

References

•Journal Article•10.1155/2001/450503

Development of mixed mode MPI / OpenMP applications

Lorna Smith, +1 more

- 01 Aug 2001

- Scientific Programming

TL;DR: The results demonstrate that this style of programming will not always be the most effective mechanism on SMP systems and cannot be regarded as the ideal programming model for all codes, however, significant benefit may be obtained from a mixed mode implementation.

...read moreread less

230

•Book Chapter•10.1007/BFB0097964

MPIJAVA: An Object-Oriented JAVA Interface to MPI

Mark Baker, +4 more

- 12 Apr 1999

TL;DR: This paper describes and discusses the syntax, functionality and performance of mpiJava, an object-oriented Java interface to MPI, and discusses some performance measurements made of communications bandwidth and latency to compare mpi Java on these systems.

...read moreread less

158

Proceedings Article•10.1109/RFIC.1999.805265

Development of three dimensional ceramic-based MCM inductors for hybrid RF/microwave applications

A. Sutono, +3 more

- 14 Jun 1999

TL;DR: In this article, planar and multilayer (3-D) inductor structures fabricated on a multi-layer ceramic-based Multi-Chip-Module (MCM-C) technology are presented for hybrid RF and microwave system implementation.

...read moreread less

•Book Chapter•10.1007/3-540-45591-4_75

MPJ: A Proposed Java Message Passing API and Environment for High Performance Computing

Mark Baker, +1 more

- 01 May 2000

TL;DR: This paper sketches out a proposed reference implementation for message passing in Java (MPJ), an MPI-like API from the Message-Passing Working Group of the Java Grande Forum, which relies heavily on RMI and Jini for finding computational resources, creating slave processes, and handling failures.

...read moreread less

Proceedings Article•10.1109/CCGRID.2005.1558647

Object-oriented SPMD

Laurent Baduel, +2 more

- 09 May 2005

TL;DR: This article presents an evolution of classical SPMD programming for clusters and grids based on an active object pattern, extended as a typed group of active objects, to which S PMD's specificities are added.

...read moreread less

Parallel Java: A Unified API for Shared Memory and Cluster Parallel Programming in 100% Java

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions in "Parallel java: a unified api for shared memory and cluster parallel programming in 100% java" ?

2. What are the future works in "Parallel java: a unified api for shared memory and cluster parallel programming in 100% java" ?

Figures

Citations

Parallel runtime execution on multiple processors

Data parallel computing on multiple processors

The Structure, Thermodynamics and Solubility of Organic Crystals from Simulation with a Polarizable Force Field

Application interface on multiple processors

Application programming interfaces for data parallel computing on multiple processors

References

Development of mixed mode MPI / OpenMP applications

MPIJAVA: An Object-Oriented JAVA Interface to MPI

Development of three dimensional ceramic-based MCM inductors for hybrid RF/microwave applications

MPJ: A Proposed Java Message Passing API and Environment for High Performance Computing

Object-oriented SPMD

Related Papers (5)

Nested parallelism for multi-core HPC systems using Java

F-MPJ: scalable Java message-passing communications on parallel systems

A Parallel Java Grande Benchmark Suite

MPIJAVA: An Object-Oriented JAVA Interface to MPI

MPJ/Ibis: a flexible and efficient message passing platform for java