High Performance Computing Initiative

In a scientific community that increasingly relies upon High Performance Computing (HPC) for large scale sim-ulations and analysis, the reliability of hardware and ap-plications devoted to HPC is extremely important. While hardware reliability is not likely to dramatically increase in the coming years, software must be able to provide the reli-ability required by demanding applications. One way to in-crease the reliability of HPC systems is to use checkpointing to save the state of an application. If the application fails for some reason (hardware or software errors), the applica-tion can be restarted from the most recent checkpoint. This paper presents Dynamic Virtual Clustering as a platform to enable completely transparent parallel checkpointing. 1 Dynamic Virtual Clusterin