Reinhard Lüling

Load balancing in large networks: a comparative study

The authors compare six well known and two new load balancing strategies on torus and ring topologies of different sizes and workload characteristics. Through simulations on a large transputer network, they show that all strategies behave differently under the workload of process and data migration. The two new algorithms based on the gradient model method are shown to be robust to both kinds of workloads. Thus, these new algorithms are good candidates for distributed operating systems running on large networks, where the workload characteristics can not be determined in advance.<<ETX>>

A dynamic distributed load balancing algorithm with provable good performance

The overall efficiency of parallel algorithms is most decisively effected by the strategy applied for the mapping of workload. Strategies for balancing dynamically generated workload on a processor network which are also useful for practical applications have intensively been investigated by simulations and by direct applications. This paper presents the complete theoretical analysis of a dynamically distributed load balancing strategy. The algorithm is adaptive by nature and is therefore useful for a broad range of applications. A similar algorithmic principle has already been implemented for a number of applications in the areas of combinatorial optimization, parallel programming languages and graphical animation. The algorithm performed convincingly for all these applications. In our analysis we will prove that the expected number of packets on each processor varies only by a constant factor compared with that on any other processor, independent of the generation and consumption of workload on each processor. We give exact bounds for these vahtes and prove an exact upper bound, independent of the number of proce% sors. Thus, the algorithm achieves a well-balanced workload distribution on any network for any underlying application. We also prove that the variation of the expected number of packets on a processor is very small and only dependent on the parameters of the algorithm. Furthermore, we present some analysis of the costs of our algorithm. We will also show that all tradeoffs between balancing quality, variation and costs can be determined by the parameters of the algorithm. “ This work wss partly supported by the German Department of Science and Technology (BMFT), PARAWAN project 41=sS39-ITR 9007 BO and the DFG Forschergruppe ‘EfTiziente Nutzung msssiv paralleled Systeme” Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage, the ACM copyright notice and the title of the publication and its date appear, and notice is given that copying is by permission of the Association for Computing Machinery. To copy otherwise, or to republish, requires a fee and/or specific permission. ACM-SPAA’93-6/93 /Velen,Germany. @ 1993 ACM 0.89791.599-2/93/0006/01 64...

Problem Independent Distributed Simulated Annealing and its Applications

1.50

Load balancing for distributed branch & bound algorithms

Simulated annealing has proven to be a good technique for solving hard combinatorial optimization problems. Some attempts at speeding up annealing algorithms have been based on shared memory multiprocessor systems. Also parallelizations for certain problems on distributed memory multiprocessor systems are known.

Static and dynamic mapping of media assets on a network of distributed multimedia information servers

The authors present a new load balancing strategy and its application to distributed branch & bound algorithms and demonstrate its efficiency by solving some NP-complete problems on a network of up to 256 transputers. The parallelization of their branch & bound algorithm is fully distributed. Every processor performs the same algorithm but each on a different part of the solution tree. In this case it is necessary to distribute subproblems among the processors to achieve a well balanced workload. Their load balancing method overcomes the problem of search overhead and idle times by an appropriate load model and avoids trashing effects by a feedback control method. Using this strategy they were able to achieve a speedup of up to 237.32 on a 256 processor network for very short parallel computation times, compared to an efficient sequential algorithm.<<ETX>>

Sorting large data sets on a massively parallel system

This paper presents principles and algorithms for the management of a network of media servers. Such a server network allows the online delivery of broadband multimedia data, e.g. audio and video streams, to a large number of widely distributed clients. Thus, the implementation of large scale distributed broadband media information services is possible if such networks can be handled efficiently. In the paper two new combinatorial optimization problems are defined that have to be solved for an efficient management of the distributed media servers connected by a high-bandwidth communication network. The algorithms consider the case of a static mapping of media assets onto the server network as well as the dynamic migration of media assets on such a network. The first scenario is used in the case that all media assets are loaded for the first time onto the server network. The second scenario is applied dynamically during run-time of an information service taking the varying user access pattern and changing media content of the server network into account. In this paper the algorithms are presented and their efficiency is demonstrated using some benchmark instances. The algorithms are part of a larger distributed system that allows the management of a network of distributed media servers. The principles of this system are presented as well as some applications that have been developed and are supported by this distributed server management system (DSMS).This paper presents principles and algorithms for the management of a network of media servers. Such a server network allows the online delivery of broadband multimedia data, e.g. audio and video streams, to a large number of widely distributed clients. Thus, the implementation of large scale distributed broadband media information services is possible if such networks can be handled efficiently. In the paper two new combinatorial optimization problems are defined that have to be solved for an efficient management of the distributed media servers connected by a high-bandwidth communication network. The algorithms consider the case of a static mapping of media assets onto the server network as well as the dynamic migration of media assets on such a network. The first scenario is used in the case that all media assets are loaded for the first time onto the server network. The second scenario is applied dynamically during run-time of an information service taking the varying user access pattern and changing media content of the server network into account. In this paper the algorithms are presented and their efficiency is demonstrated using some benchmark instances. The algorithms are part of a larger distributed system that allows the management of a network of distributed media servers. The principles of this system are presented as well as some applications that have been developed and are supported by this distributed server management system (DSMS).

COMBINING HELPFUL SETS AND PARALLEL SIMULATED ANNEALING FOR THE GRAPH-PARTITIONING PROBLEM∗

This paper presents a performance study for many of todays popular parallel sorting algorithms. It is the first to present a comparative study on a large scale MIMD system. The machine, a Parsytec GCel, contains 1024 processors connected as a two-dimensional grid. To justify the experimental results, we develop a theoretical model to predict the performance in terms of communication and computation times. We get a very close relation between the experiments and the theoretical model as long as the edge congestion caused by the algorithms is predicted precisely. We compare: Bitonicsort, Shearsort, Gridsort, Samplesort, and Radixsort. Experiments were performed using random instances according to a well known benchmark problem. Results show that for the machine we used, Bitonicsort performs best for smaller numbers of keys per processor (<2048) and Samplesort outperforms all other methods for larger instances.<<ETX>>

An analytical comparison of nearest neighbor algorithms for load balancing in parallel computers

In this paper we present a new algorithm for the k-partitioning problem which achieves an improved solution uality compared to known heuristics. We apply the principle of so called “helpful sets”, which has shown to be very efficient for graph bisection, to the direct k-partitioning problem. The principle is extended in several ways. We introduce a new abstraction technique which shrinks the graph during runtime in a dynamic way leading to shorter computation times and improved solutions qualities. The use of stochastic methods provides further improvements in terms of solution quality. Additionally we present a parallel implementation of the new heuristic. The parallel algorithm delivers the same solution quality as the sequential one while providing reasonable parallel efficiency on MIMD-systems of moderate size. All results are verified by experiments for various graphs and processor numbers.

Two Strategies for Solving the Vertex Cover Problem on a Transputer Network

With nearest neighbor load balancing algorithms, a processor makes balancing decisions based on its local information and manages work load migrations within its neighborhood. This paper compares a couple of fairly well-known nearest neighbor algorithms, the dimension exchange and the diffusion methods and their variants in terms of their performances in both one-port and all-port communication architectures. It turns out that the dimension exchange method outperforms the diffusion method in the one-port communication model, and that the strength of the diffusion method is in asynchronous implementations in the all-port communication model. The underlying communication networks considered assume the most popular topologies, the mesh and the torus and their special cases: the hypercube and the k-ary n-cube.<<ETX>>

An Integrated Approach to Semantic Evaluation and Content-Based Retrieval of Multimedia Documents

In this article, we present an implementation of a distributed branch and bound algorithm solving the Vertex Cover problem on a network of up to 63 Transputers.