A novel partitioning and tracing approach for distributed systems based on vector clocks

Tracking, partitioning and tracing in modern dynamic high performance computing systems are three of the most innovative and important development aspects for performance optimization purposes and state-of-the-art advanced quality. This paper discusses these three aspects with respect to distributed systems and proposes new mechanisms for an advanced utilization of software in this domain. We present a specific tracking mechanism via vector clocks for model and code partitioning purposes and the determination of causality relations. Further, a tracing approach for an effective analysis and thereby utilization of code and the corresponding architecture is introduced. The combination of both approaches leads to a high degree of parallelism and a fine-grained structure of execution units, that further traced, supports a precise analysis of synchronous and asynchronous system´s behavior as well as an optimal load balancing. The mechanisms are introduced with respect to a model based control engineering tool and event diagrams.