Visual programming support for graph-oriented parallel/distributed processing

In order to solve the visual problems of large-scale scientific computing, the project imports the middle ware for communication, and extends the classic client-server structure into client-commware-server structure. The paper proposes a visual system model for large-scale scientific computing based on clientcommware-server structure, PC-cluster and largescale display technology. The visual system model has the virtues of generality and excellently interactive capacity, and has successfully been applied to PRIS (Parallel Reservoir Integrated Simulator), a visual system of large-scale oil simulation. Applied results prove that it has a widely applicable prospective.

show abstract

“…At the same time, its visual technology is always researched by people for large-scale computing [3,4].…”

Section: Application Of Visual System Modelmentioning

confidence: 99%

Research on Parallel Visualization in Large-Scale Scientific Computing

Gao

Zhao

2006

16th International Conference on Artificial Reality and Telexistence--Workshops (ICAT'06)

View full text Add to dashboard Cite

show abstract

“…-Scheduling policy: to distribute computations among computing nodes in a computing platform efficiently, i.e., to detect the presence of SMPs or multi-core CPUs in computer nodes of a cluster platform. One efficient scheduling method that may be considered is parallel loop self-scheduling for cluster and grid environments [33], or general task scheduling for distributed systems [3,7,9,16]. -Parallelization: to semi-automatically transform existing MPI, OpenMP, or hybrid MPI/OpenMP applications into multithreaded applications, in order to explore higher degree of parallelism and explore many-core SMP multiprocessor cluster systems.…”

Section: Future Researchesmentioning

confidence: 99%

Performance-based parallel application toolkit for high-performance clusters

Weng

2008

J Supercomput

View full text Add to dashboard Cite

Advances in computer technology, encompassed with fast emerging of multicore processor technology, have made the many-core personal computers available and more affordable. The availability of network of workstations and cluster of many-core SMPs have made them an attractive solution for high performance computing by providing computational power equal or superior to supercomputers or mainframes at an affordable cost using commodity components. In order to search alternative ways to extract unused and idle computing power from these computing resources targeting to improve overall performance, as well as to fully utilize the underlying new hardware platforms, these are major topics in this field of research. In this research paper, the design rationale and implementation of an effective toolkit for performance measurement and analysis of parallel applications in cluster environments is introduced; not only generating parallel applications' timing graph representation, but also to provide application execution's performance data charts. The goal in developing this toolkit is to permit application developers have a better understanding of the application's behavior among selected computing nodes purposed for that particular execution. Additionally, multiple execution results of a given application under development can be combined and overlapped, permitting application developers to perform "what-if" analysis, i.e., to deeper understand the utilization of allocated computational resources. Experimentations using this toolkit have shown its effectiveness on the development and performance tuning of parallel applications, extending the use in teaching of message passing, and shared memory model parallel programming courses.

show abstract

“…We have developed av isual programming tool, VisualGOP [7], for designing the GOP program graphically.V isualGOP has ah ighly visual and interactive user interface, and provides aframework in whichthe design and coding of GOP programs, and the associated information can be viewed and modified. It also facilitates the compilation, mapping, and execution of the programs.…”

mentioning

confidence: 99%

Graph Scaling: A Technique for Automating Program Construction and Deployment in ClusterGOP

Chan

Cao

Sun

2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Program developmenta nd resource managementa re critical issues in large-scaled parallel applications and they raise diffi culties for the programmers. Automation tools can benefit the programmer by reducing the time and work required for programming, deploying, and managing parallel applications. In our previous work, we have developed avisual tool, VisualGOP,tohelp visual construction and automatic mapping of parallel programs to execute on the ClusterGOP platform, which provides ag raph-oriented model and the environmentf or running the parallel applications on clusters. In VisualGOP,t he programmer needs to manually build the task interaction graph. This maylead to scalability problem for large applications. In this paper, we propose ag raph scaling approacht hat helps the programmer to develop and deployal arge-scale parallel application minimizing the e ff ort of graph construction, task binding and program deployment. The graph scaling algorithms expand or reduce at ask graph to matcht he specified scale of the program and the hardware architecture, e.g., the problem size, the number of processors and interconnection topology,s oa st op roduce an automatic mapping. An example is used to illustrate the proposed approacha nd how programmer benefits in the automation tools. 1I ntroductionProgramming with parallel applications is ad i ffi cult task involving programming details, processors information and network configurations. Am ethodt o simplify parallel program developmenti st oa bstract and representt he parallel programming structure by logical graphs.Task graph is ag raphical representation of ap arallel program. It describes the logical structure of the program in whicht he nodes representt he computational tasks and the edges denote the communication links and precedence relationships among the nodes. Varieties of task graph have been proposed. Directed acyclic graph (DAG) [ 1,2] and task interaction graph (TIG) [3,4]

show abstract

Visual programming support for graph-oriented parallel/distributed processing

Cited by 5 publications

References 22 publications

Research on Parallel Visualization in Large-Scale Scientific Computing

Research on Parallel Visualization in Large-Scale Scientific Computing

Performance-based parallel application toolkit for high-performance clusters

Graph Scaling: A Technique for Automating Program Construction and Deployment in ClusterGOP

Contact Info

Product

Resources

About