ATML Application Optimization and User Service Tools

The Algorithm, Tools and Methods Lab "Application Optimization and User Service Tools" is responsible for the optimization and scaling of applications in terms of performance, efficiency and parallel I/O. We provide users with the knowledge and proper tools sets for their project management and their work on the Jülich HPC systems. We strongly interact with the Simulation and Data Laboratories and the Cross-sectional teams "Methods and Algorithms" and "Performance Analysis" as well as the department "High-Performance Computing Systems".

Know-How and Focal Points

We are experienced in parallelisation libraries like MPI and OpenMP. We know about specialities of the local HPC systems and this makes it possible for us to guide the users in optimization strategies on the Jülich systems, e.g. for compiler and memory usage, task mapping, and I/O.

We collaborate with users in the need of on-demand support, but we also offer close long-term collaborations with user projects to optimize their applications on the Jülich HPC systems, e.g. to implement parallel I/O or a hybrid parallelisation.

We focus on assisting users to choose optimal parameters for their simulations, this leads to our interest in benchmarking:

• We monitor and benchmark standard simulation software packages.
• We perform evaluations and parameter studies of selected user applications.
• We benchmark new architectures and develop system benchmarks.

With this work we also assist the system administrators in evaluating the system behaviour.

Training

We emphasize on equipping users with knowledge for their usage of HPC systems:

• We provide courses in MPI, OpenMP, and Parallel I/O.
• We organize the bi-yearly introductory course to the Jülich supercomputer systems.
• We collaborate in the Extreme Scaling Workshops as well as in PRACE Training Events

Research and Development

Our research interest is the optimization of parallel I/O, this has led to the library SIONlib, which implements efficient parallel I/O of task-local data from massively parallel applications.

In addition, we have a strong interest in tool development with focus on application monitoring, optimization and benchmarking. We are currently working on the following projects:

• LLview Job monitoring
• JUBE - Benchmarking Environment

Due to our benchmarking activities we also develop system benchmarks:

• Linktest: Scalable MPI point-to-point benchmark

We further put emphasize on convenient access to our systems and are developing software for managing projects and user accounts:

• JARDS: Resource Allocation Software "Joint Application, Review, and Dispatch Service"
• JuDoor : Portal for managing accounts, projects and resourses at JSC

Collaborations with EU and national funded projects

• PRACE - Partnership for Advanced Computing in Europe
• DEEP-Projects - Dynamic Exascale Entry Platform
• IO-SEA - Storage I/O and Data Management for Exascale Architectures
• RED-SEA - Network Solution for Exascale Architectures
• EoCoE - Energy Oriented Centre of Excellence
• UNSEEN - HPC for Energy Systems Modelling
• METIS - Methods and Models for Energy Transformation and Integration Systems
• SiVeGCS - Coordination and securing the further availability of GCS' supercomputing resources in the framework of the national HPC infrastructure
• EUPEX - European Pilot for Exascale

Industry Collaborations

• TenneT - Design and implementation of a specialised cluster system in context of electric energy distribution.

Team members

More