Adaptive distributed execution of Java applications

Increasingly large-scale clusters of PC/WS continue to become majority platform in HPC field. Such a commodity cluster environment, there may be incremental upgrade due to several reasons, such as rapid progress in processor technologies, or user needs and it may cause the performance heterogeneity between nodes from which the application programmer will suffer as load imbalances. To overcome these problems, some dynamic load balancing mechanisms are needed. In this paper, we report our ongoing work on dynamic load balancing extension to Omni/SCASH which is an implementation of OpenMP on Software Distributed Shared Memory, SLASH. Using our dynamic load balancing mechanisms, we expect that programmers can have load imbalances adjusted automatically by the runtime system without explicit definition of data and task placements in a commodity cluster environment with possibly heterogeneous performance nodes.

Parallelizing a Level 3 BLAS Library for LAN-Connected Workstations

Load balancing technique may improve the performance and scalability of the Internet greatly. Many researchers focus on intra-domain load balancing which distributes traffic over multiple paths or server farms in a single domain. However, there is little research on interdomain (such as inter-AS or inter-PoP) load balancing due to the loose relationship and complex policies among domains. It is important to study inter-domain load balancing under the trend toward a denser mesh of inter-domain connectivity within the Internet. In this paper, we propose a distributed and dynamic load balancing mechanism using a hashing-based algorithm to distribute traffic between domains which preserves per-flow packet ordering and supports unequal weighted distribution when dynamic adaptation is used. We also evaluate the performance of the mechanism.

The goal of this paper is to determine how efficiently we can implement an adequate parallel programming environment on a workstation cluster without modifying the existing operating system. We have implemented a runtime environment for parallel programs and gang-scheduling on a workstation cluster. In this paper, we report the techniques used to implement an efficient runtime environment and gangscheduling on a workstation cluster. The most important technique is “network preemption.” A unique feature of our approach is that the gang-scheduling is also written in a parallel language. Our evaluation shows that gang-scheduling on workstation clusters can be practical.

Numerous works has been done for load balancing of web servers in grid environment. Reason behinds popularity of grid environment is to allow accessing distributed resources which are located at remote locations. For effective utilization, load must be balanced among all resources. Importance of load balancing is discussed by distinguishing the system between without load balancing and with load balancing. Various performance metrics that need to be considered for designing an efficient load balancing algorithm are also described. Intensive review of literature of different load balancing approaches for web servers have been carried out and presented in this paper. On the basis of literature survey, a new dynamic load balancing mechanism is proposed for optimizing waiting time and cost.

This paper introduces a distributed co- evolutionary particle swarm optimization algorithm (DCPSO). In DCPSO, the population is decomposed into the subpopulations that are each responsible for optimizing one parameter, and co-evolve in a competitive manner. Such co-evolution mechanism with both cooperation and competition are designed to be effective and efficient in solving multi-objective (MO) problems under distributed computation. The competition mechanism also indirectly helps DCPSO to overcome the fault-tolerance constraint in distributed computation. DCPSO shows substantial speedup from non-distributed version by sharing workload among computational nodes. In addition, a dynamic load balancing mechanism is used to further speed up the total runtime by minimizing the amount of idle time in each node.

Express versus PVM: A performance comparison

In this paper, we present a parallel iterative solution for large banded systems of linear equations based on incomplete LU-factorization (ILU). A master—workers parallel computing scheme is used. The proposed algorithm incurs reduced storage and communication overhead as compared to previous methods. The reduction in communication overhead has been achieved by pipelining the inter-workers message passing and limiting the communication between master and workers to initial work distribution and final results collection.The performance of the proposed algorithm is evaluated analytically and experimentally using Parallel Virtual Machine (PVM) as a parallel programming environment on a cluster of Linux work-stations. The obtained performance results show that the proposed algorithm exhibits higher efficiency for coarse grain computations corresponding to large matrix sizes and reduced number of processors.

Traditionally, PVM and MPI programs live on message passing systems, from clusters of non-dedicated workstations to MPP machines. The performance of a parallel program in such an environment is usually determined by the single least performing task in that program. In a homogeneous, stable environment, such as an MPP machine, this can only be repaired by improving the workload balance between the individual tasks. In a cluster of workstations, differences in the performance of individual nodes and network components can be an important cause of imbalance. Moreover, these differences will be time dependent as the load generated by other users plays an important role. Worse yet, nodes may be dynamically removed from the available pool of workstations. In such a dynamically changing environment, redistributing tasks over the available nodes can help to maintain the performance of individual programs and of the pool as a whole. Condor [1] solves this task migration problem for sequential programs. However, the migration of tasks in a parallel program presents a number of additional challenges, for the migrator as well as for the scheduler. For PVM programs, there are a number of solutions, including Dynamite [2]; Hector [3] was designed to migrate MPI tasks and to checkpoint complete MPI programs. The latter capability is very desirable for long-running programs in an unreliable environment.This brings us to the Grid, where both performance and availability of resources vary dynamically and where reliability is an important issue. Once again, Livny with his Condor-G [4] provides a solution for sequential programs, including provisions for fault-tolerance. In the Polder Metacomputer Project, based on our experience with Dynamite, we are currently investigating the additional challenges in creating a task-migration and checkpointing capability for the Grid environment. This includes the handling of shared resources, such as open files; differences in administrative domains, etc. Eventually, the migration of parallel programs will allow large parallel applications to surf the Grid and ride the waves in this highly dynamic environment.KeywordsParallel ProgramMessage Passing InterfaceMessage PassingAdditional ChallengeGrid EnvironmentThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A strategy is proposed for fast and efficient parallel computations using a cluster of workstations to simulate flood flows. We implement ANUGA software to conduct flood simulations. ANUGA solves the two-dimensional shallow water equations using a finite volume method. ANUGA can be run in either sequential or parallel. We focus our work on parallel computations. Our computation scenarios are implemented on a cluster of workstations. Parallel computation results are assessed based on execution time and efficiency. The strategy that we propose gives a significant advantage when we want to get fast and efficient computations using a cluster of workstations.

Programming large object oriented systems is a difficult task. With the help of specific programming tools integrated in a uniform programming environment, this task can be facilitated. In this paper, we describe the design and implementation of a programming environment for the programming language ObjTalk [Rathke, C. 86], an object oriented extension to the programming language LISP. Special attention will be given to the integration of graphical and non-graphical visual aids.

Octave is a freely distributable MATLAB/sup TM/-like computer-aided control systems design (CACSD) programming environment. The Octave control systems toolbox (OCST) was developed as a set of script files to add functionality to the Octave environment. The OCST was designed to use an object-oriented data structure to represent linear system parameters and relevant companion data in a single data structure.

Parallel workstation clusters and MPI for sparse systems in computational science

A Functional Programming Based CACSD Environment

Workstation clusters are being recognized as the main promising computing resource of the near future. A large size workstation cluster, consisting of locally connected workstations, has the power comparable to a supercomputer, at a fraction of the cost. Further, a wide area coupling of workstation clusters is not only suitable for exchange of mail and news or establishment of distributed information systems, but can also be exploited as a large metacomputer. The wide area distribution aspects will be covered in a separate paper by the E=MC2 project [8]. This paper shows the potential power by characterizing the system and the needs of current applications, and outlines the general idea to efficiently utilize networks of workstation. The second part of the paper introduces the approach of the HiCon project to solve the operating system and programming environment problems that currently restrict proper exploitation of workstation clusters, and demonstrates the feasibility by real measurement results. It concludes with general results for the research community in this area.KeywordsLoad BalanceDynamic Load BalanceTask Response TimeParallel Finite ElementWorkstation ClusterThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.