Load balancing on PC clusters with the super-programming model
Dejiang Jin, Sotirios G. Ziavras · 2005
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.