CUMULVS: extending a generic steering and visualization middleware for application fault-tolerance
Philip M. Papadopoulos, J.A. Kohl, B.D. Semeraro · 2002
CUMULVS is a middleware library that provides application programmers with a simple API for describing viewable and steerable fields in large-scale distributed simulations. These descriptions provide the data type, a logical name of the field/parameter, and the mapping of global indices to local indices (processor and physical storage) for distributed data fields. The CUMULVS infrastructure uses these descriptions to allow an arbitrary number of front-end "viewer" programs to dynamically attach to a running simulation, select one or more fields for visualization, and up-date steerable variables. (Viewer programs can be built using commercial visualization software such as AVS or custom software based on GUI interface builders like Tcl/Tk.) Although these data field descriptions require a small effort on the part of the application programmer, the payoff is a high degree of flexibility for the infrastructure and end-user. This flexibility has allowed us to extend the infrastructure to include "application-directed" checkpointing, where the application determines the essential state that must be saved for a restart. This has the advantage that checkpoints can be smaller and made portable across heterogeneous architectures using the semantic description information that can be included in the checkpoint file.