Load Balancing on PC Clusters with the Super-Programming Model
نویسندگان
چکیده
Recent work in high-performance computing has shifted attention to PC clusters. For PC-clusters, member nodes are independent computers connected by generalpurpose networks. The latency of data communications is long and load balancing among the nodes becomes a critical issue. We introduce a new model for program development on PC clusters, namely the SuperProgramming Model (SPM) to address this issue. In SPM, PC clusters are modeled as a single virtual machine with PCs as the processing units. The workload is modeled as a collection of Super-Instructions (SIs). Each SI can achieve a limited workload. Application programs are coded using SIs. SIs are dynamically assigned to available PCs at run time. For limited workload, no SI overloads any PC. Therefore, dynamic load balancing becomes an easier task. We apply SPM to mining association rules. Our experiments show that under normal conditions the workload is balanced very well. A performance model is also developed to describe the scalable behavior of SPM.
منابع مشابه
A Super-Programming Technique for Large Sparse Matrix Multiplication on PC Clusters
The multiplication of large spare matrices is a basic operation in many scientific and engineering applications. There exist some high-performance library routines for this operation. They are often optimized based on the target architecture. For a parallel environment, it is essential to partition the entire operation into well balanced tasks and assign them to individual processing elements. ...
متن کاملParallelizing Sparse Grid Volume Visualization with Implicit Preview and Load Balancing
New algorithms that work entirely on sparse grids can create data sets that cannot be handled on uniform grids any more due to their size. On the other hand, most visualization techniques are only capable of handling uniform grids. As the interpolation on sparse grids is a complicated and time consuming process, direct volume visualization is unthinkable for bigger data sets until the underlyin...
متن کاملUTS: An Unbalanced Tree Search Benchmark
This paper presents an unbalanced tree search (UTS) benchmark designed to evaluate the performance and ease of programming for parallel applications requiring dynamic load balancing. We describe algorithms for building a variety of unbalanced search trees to simulate different forms of load imbalance. We created versions of UTS in two parallel languages, OpenMP and Unified Parallel C (UPC), usi...
متن کاملA Parallel Loop Self-Scheduling on Extremely Heterogeneous PC Clusters
Cluster computers are a viable and less expensive alternative to symmetric multiprocessor systems. However, a serious difficulty in concurrent programming of a cluster computer system is how to deal with scheduling and load balancing of such a system which may consist of heterogeneous computers. Self-scheduling schemes suitable for parallel loops with independent iterations on heterogeneous com...
متن کاملA novel bi-level stochastic programming model for supply chain network design with assembly line balancing under demand uncertainty
This paper investigates the integration of strategic and tactical decisions in the supply chain network design (SCND) considering assembly line balancing (ALB) under demand uncertainty. Due to the decentralized decisions, a novel bi-level stochastic programming (BLSP) model has been developed in which SCND problem has been considered in the upper-level model, while the lower-level model contain...
متن کامل