Assessment of the I/O and Storage Subsystem in Modular Supercomputing Architectures

Neuwirth, Sarah

doi:10.1109/cluster51413.2022.00077

Cited by 2 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DEEP-EST prototype [19,20] (see Figures 3a and 3b) has been developed in a close co-design loop between applications, system software, and system component architects. It consists of three computing modules and two storage modules.…”

Section: Deep-est Prototypementioning

confidence: 99%

“…The goal is to support a broad variety of different workloads with varying compute node and memory configuration requirements. The Input/Output Software for Exascale Architectures (IO-SEA) project [20,34] seeks to improve the I/O and data management in large-scale MSA systems and builds upon the results of the SAGE 1-2 [35] projects and MAESTRO. Its main focus is to provide a novel data management and storage platform for exascale computing based on hierarchical storage management (HSM) and on-demand provisioning of storage services.…”

Section: Current European Research Projects Advancing the Msamentioning

confidence: 99%

“…As exascale-class modular supercomputing systems come within reach, scientific advances that match the growth in theoretical computing power will require massive innovations in software stacks for storage and data processing, including the following core capabilities [20]:…”

Section: Exascale Data Challenges and Emerging Workloadsmentioning

confidence: 99%

“…The changing landscape of emerging hybrid HPC workloads along with the ever increasing gap between the compute and storage performance capabilities reinforces the need for an in-depth understanding of extreme-scale I/O and for rethinking existing data storage and management techniques. This is especially true for modular supercomputing systems [20].…”

Section: Pos(lattice2022)245mentioning

confidence: 99%

See 3 more Smart Citations

Modular Supercomputing and its Role in Europe’s Exascale Computing Strategy

Neuwirth¹

2023

Proceedings of the 39th International Symposium on Lattice Field Theory — PoS(LATTICE2022)

View full text Add to dashboard Cite

Reaching Exascale compute performance at an affordable budget requires increasingly heterogeneous HPC systems, which combine general purpose processing units (CPUs) with acceleration devices such as graphics processing units (GPUs) or many-core processors. The Modular Supercomputing Architecture (MSA) developed within the EU-funded DEEP project series breaks with traditional HPC system architectures by orchestrating these heterogeneous computing resources at system-level, organizing them in compute modules with different hardware and performance characteristics. Modules with disruptive technologies, such as quantum devices, can also be included in a modular supercomputer to satisfy the needs of specific user communities. The goal is to provide cost-effective computing at extreme performance scales fitting the needs of a wide range of Computational Sciences. This approach brings substantial benefits for heterogeneous applications and workflows since each part can be run on exactly matching computing resources, therefore improving the time to solution and energy use. It is therefore ideal for supercomputer centers running a heterogeneous mix of applications. This work introduces the Modular Supercomputing Architecture -which constitutes the central element in Europe's roadmap to Exascale computing -, including its history, its role in Europe's Exascale computing strategy, its hardware and software elements, and experiences from mapping applications and workflows to MSA systems.

show abstract

Section: Deep-est Prototypementioning

confidence: 99%

Section: Current European Research Projects Advancing the Msamentioning

confidence: 99%

Section: Exascale Data Challenges and Emerging Workloadsmentioning

confidence: 99%

Section: Pos(lattice2022)245mentioning

confidence: 99%

See 2 more Smart Citations