Ad hoc file systems for high-performance computing
Storage backends of parallel compute clusters are still based mostly on magnetic disks,
while newer and faster storage technologies such as flash-based SSDs or non-volatile …
while newer and faster storage technologies such as flash-based SSDs or non-volatile …
DAOS as HPC Storage: a View From Numerical Weather Prediction
N Manubens, T Quintino, SD Smart… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
Object storage solutions potentially address long-standing performance issues with POSIX
file systems for certain I/O workloads, and new storage technologies offer promising …
file systems for certain I/O workloads, and new storage technologies offer promising …
DAOS as HPC Storage: Exploring Interfaces
A Jackson, N Manubens - 2023 IEEE International Conference …, 2023 - ieeexplore.ieee.org
Reading and writing data to and from data storage has long been a bottleneck for high
performance computing (HPC). The hardware used for data storage exhibits performance …
performance computing (HPC). The hardware used for data storage exhibits performance …
Performance Comparison of DAOS and Lustre for Object Data Storage Approaches
N Manubens, SD Smart, T Quintino… - 2022 IEEE/ACM …, 2022 - ieeexplore.ieee.org
High-performance object stores are an emerging technology which offers an alternative
solution in the field of HPC storage, with potential to address long-standing scalability issues …
solution in the field of HPC storage, with potential to address long-standing scalability issues …
I/O Behind the Scenes: Bandwidth Requirements of HPC Applications with Asynchronous I/O
I/O bandwidth is a critical resource in an HPC cluster. As with all shared resources, its
availability is impacted significantly by the users and the applications they execute. Without …
availability is impacted significantly by the users and the applications they execute. Without …
Usage scenarios for byte-addressable persistent memory in high-performance and data intensive computing
M Weiland, B Homölle - Journal of Computer Science and Technology, 2021 - Springer
Byte-addressable persistent memory (B-APM) presents a new opportunity to bridge the
performance gap between main memory and storage. In this paper, we present the usage …
performance gap between main memory and storage. In this paper, we present the usage …
Potential of I/O aware workflows in climate and weather
JM Kunkel, LR Pedro - Supercomputing Frontiers and …, 2020 - centaur.reading.ac.uk
The efficient, convenient, and robust execution of data-driven workflows and enhanced data
management are essential for productivity in scientific computing. In HPC, the concerns of …
management are essential for productivity in scientific computing. In HPC, the concerns of …
Towards Smarter Schedulers: Molding Jobs into the Right Shape via Monitoring and Modeling
High-performance computing is not only a race towards the fastest supercomputers but also
the science of using such massive machines productively to acquire valuable results …
the science of using such massive machines productively to acquire valuable results …
Towards Smarter Schedulers: Molding Jobs into the Right Shape via Monitoring and Modeling
SAS ParaTools… - … Computing: ISC High …, 2023 - books.google.com
High-performance computing is not only a race towards the fastest supercomputers but also
the science of using such massive machines productively to acquire valuable results …
the science of using such massive machines productively to acquire valuable results …
EPCC's Exascale Journey: A Retrospective of the Past 10 Years and a Vision of the Future
M Weiland, M Parsons - Computing in Science & Engineering, 2021 - ieeexplore.ieee.org
The preparations for Exascale computing started over a decade ago and EPCC, the
supercomputing center at The University of Edinburgh, was at the heart of these efforts from …
supercomputing center at The University of Edinburgh, was at the heart of these efforts from …