Application-Driven Exascale: The JUPITER Benchmark Suite

TL;DR

The paper introduces the JUPITER Benchmark Suite, a collection of 16 real-world applications designed for exascale supercomputers, emphasizing usability, reproducibility, and relevance to scientific research.

Contribution

It presents a new benchmark suite tailored for exascale systems, incorporating diverse real applications and supporting procurement and development of the JUPITER supercomputer.

Findings

Scalability studies of selected applications

Identification of key requirements for exascale benchmarks

Open source release of the JUPITER Benchmark Suite

Abstract

Benchmarks are essential in the design of modern HPC installations, as they define key aspects of system components. Beyond synthetic workloads, it is crucial to include real applications that represent user requirements into benchmark suites, to guarantee high usability and widespread adoption of a new system. Given the significant investments in leadership-class supercomputers of the exascale era, this is even more important and necessitates alignment with a vision of Open Science and reproducibility. In this work, we present the JUPITER Benchmark Suite, which incorporates 16 applications from various domains. It was designed for and used in the procurement of JUPITER, the first European exascale supercomputer. We identify requirements and challenges and outline the project and software infrastructure setup. We provide descriptions and scalability studies of selected applications and a set of key takeaways. The JUPITER Benchmark Suite is released as open source software with this work at https://github.com/FZJ-JSC/jubench.