This paper gives an overview about the Score-P performance measurement infrastructure which is being jointly developed by leading HPC performance tools groups. It motivates the advantages of the joint undertaking from both the developer and the user perspectives, and presents the design and components of the newly developed Score-P performance measurement infrastructure. Furthermore, it contains first evaluation results in comparison with existing performance tools and presents an outlook to the long-term cooperative development of the new system.

To study the impact of inter-vehicle communications on (vehicular) transport efficiency, e.g., for traffic management purposes, there is a need for efficient and accurate largescale simulations that jointly consider both, the vehicular traffic and the communication system. To overcome the scalability limitations of current discrete event-based network simulators like NS-2, we propose a hybrid simulation approach that can significantly reduce the number of scheduled events by making use of statistical models. Basically, we treat some data traffic, which is not the primary concern of the simulation study, as 'noise' (e.g., beaconing of nodes). While accurately modeling this background traffic we only need to simulate via discrete event-based simulation the actual application we are interested in (e.g., a data dissemination protocol). We outline how the characterization of the background traffic is gained, statistically validated and used. The achievable speed-up is demonstrated in a first application study where a speed funnel is built using inter-vehicle communications. In this scenario, the conservatively estimated speed-up factor is about 500 compared to a pure discrete event-based simulation.

The rapidly growing number of cores on modern supercomputers imposes scalability demands not only on applications but also on the software tools needed for their development. At the same time, increasing application and system complexity makes the optimization of parallel codes more difficult, creating a need for scalable performance-analysis technology with advanced functionality. However, delivering such an expensive technology can hardly be accomplished by single tool developers and requires higher degrees of collaboration within the HPC community. The unified performance-measurement system Score-P is a joint effort of several academic performance-tool builders, funded under the BMBF program HPC-Software für skalierbare Parallelrechner in the SILC project (Skalierbare Infrastruktur zur automatischen Leistungsanalyse paralleler Codes). It is being developed with the objective of creating a common basis for several complementary optimization tools in the service of enhanced scalability, improved interoperability, and reduced maintenance cost.

No abstract

Abstract.Version 3.0 of the OpenMP specification introduced the task construct for the explicit expression of dynamic task parallelism. Although automated load-balancing capabilities make it an attractive parallelization approach for programmers, the difficulty of integrating this new dimension of parallelism into traditional models of performance data has so far prevented the emergence of appropriate performance tools. Based on our earlier work, where we have introduced instrumentation for task-based programs, we present initial concepts for analyzing the data delivered by this instrumentation. We define three typical performance problems related to tasking and show how they can be visually explored using event traces. Special emphasis is placed on the event model used to capture the execution of task instances and on how the time consumed by the program is mapped onto tasks in the most meaningful way. We illustrate our approach with practical examples.