Christian Rössel

TL;DR: This paper gives an overview about the Score-P performance measurement infrastructure and contains first evaluation results in comparison with existing performance tools and presents an outlook to the long-term cooperative development of the new system.

TL;DR: The unified performance-measurement system Score-P is a joint effort of several academic performance-tool builders, funded under the BMBF program HPC-Software fur skalierbare Parallelrechner in the SILC project, 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.

TL;DR: Initial concepts for analyzing the data delivered by instrumentation for task-based programs and 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.

TL;DR: A portable method to distinguish individual task instances and to track their suspension and resumption with event-based instrumentation is described and possible extensions of the OpenMP specification are discussed to provide general support for task identifiers with untied tasks.

TL;DR: This paper describes how Score-P, a scalable performance measurement infrastructure for parallel applications, is extended to support trace-based performance analyses of RMA parallelization models and designs a generic event model to record RMA operations in the OTF2 trace format.