This department conducts research into parallel programming models and into tools to assist development of parallel applications in high-performance computing. Currently the focus is on transparent global address spaces with background data transfers, task-parallelism based on distributed data-dependencies, collective off-loading of I/O operations, and parallel debugging. As a service to HLRS users, the group also maintains part of the software stack related to programming models, debugging, and performance analysis tools.
Dr. José Gracia
Head, Scalable Programming Models and Tools
Research Scientist
The 3xa project will develop scalable methods for the simulation of three-body interactions in particle systems, applying vectorized kernels, dynamic load balancing approaches and adaptive resolution schemata.
Focusing on critical applications for the prediction of geohazards, the Centre of Excellence for Exascale in Solid Earth aims to become a hub for HPC software within the solid earth community.
EE-HPC is testing an approach for improving energy efficiency in HPC systems by automatically regulating system parameters and settings based on current job requirements.
The Performance Optimisation and Productivity Centre of Excellence in HPC provides performance optimisation and productivity services for academic and industrial codes in all domains to help in their transition to larger scales and to monitor their progress.
targetDART is developing a task-based approach for highly scalable simulation software that mitigates load-imbalance on heterogenous systems through dynamic, adaptive and reactive distribution of computational load across compute resources.
In the first ever project to connect computers in wind parks with an HPC center, WindHPC aims to reduce energy consumption by improving efficiency in simulation codes, HPC workflows, and data management.
