MPTRAC v2.2: GPU Performance Measurements on JUWELS Booster

Performance measurements of the Massive-Parallel Trajectory Calculations model version 2.2 collected on the JUWELS Booster supercomputer using NVIDIA Nsight Systems. The dataset is associated with a 2021 preprint publication in Geoscientific Model Development authored by researchers from Forschungszentrum Jülich. The data likely contains metrics evaluating the efficiency of Lagrangian transport simulations on Graphics Processing Units.

Use Cases

• Benchmarking GPU performance for atmospheric trajectory calculations based on the described model.
• Analyzing computational efficiency of parallelized Lagrangian transport simulations based on the platform and tools mentioned.
• Comparing performance metrics of scientific software across different HPC systems based on the described collection method.
• Validating model scalability and optimization techniques for geoscientific computing based on the described use of NVIDIA Nsight Systems.

Strengths

• Data is directly linked to a peer-reviewed preprint publication, providing academic context.
• Measurements were collected using a specific, industry-standard profiling tool (NVIDIA Nsight Systems).
• Performance evaluation was conducted on a named, high-performance computing system (JUWELS Booster).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Forschungszentrum Jülich

Collection Method

Collected with NVIDIA Nsight Systems on the JUWELS Booster supercomputer.