The Workshop On Performance and Scalability of Storage Systems (WOPSSS) aims to present state-of-the-art research, innovative ideas, and experience that focus on the design and implementation of HPC storage systems in both academic and industrial worlds, with a special interest on their performance analysis.

This year, for our 5th edition, we propose to give a specific twist to address the system and operating system aspects of the storage stack. The addressed workloads remain HPC, Big Data, Cloud, and Artificial Intelligence. All these data intensive domains have to overcome the I/O bottleneck by analyzing the performance, detecting parameters restricting the performance and eventually providing I/O optimizations.

WOPSSS intends to encourage the discussion of these topics between researchers and practitioners from both the academic and the industrial worlds.

The workshop is held in conjunction with EuroSys'20.

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference.

• Papers need to be submitted via Easychair (http://easychair.org/conferences/?conf=wopsss2020)

• Papers are required to be formatted according to ACM SIG proceedings (https://www.overleaf.com/read/vkypwtbmtrkv)

• The submissions are "single-blind", i.e. submissions are allowed to include the author names.

WOPSSS workshop invites two types of submissions:

• Regular papers (8 pages) discussing original contributions, experience reports, or work in progress reports (supported by initial validations);

• Contributed talks, summarized in 2 page extended abstracts, reporting positions and visions for the future, identifying new challenges and research venues, or reports for early ongoing work.

List of Topics

WOPSSS topics of interest include but are not limited to:

• AI and Deep Learning workloads interactions with storage
• Storage systems modeling and analysis tools
• Feed-back and empirical evaluation of storage systems
• Application I/O characterization
• AI workload and storage performance analysis
• Parallel I/O and storage systems: consistency, caching, replication, reliability and fault recovery overhead
• Network challenges and storage systems: Scalability, QoS, Partitionability
• Low latency storage systems usability and analysis: memory-only, Flash, NVRAM, Storage Class Memory
• File system design
• Cloud and distributed storage

Committees

Program Committee (to be completed)

•  Leonardo Bautista, BSC, Spain
•  Julien Bigot, Maison de la Simulation, France
•  Carlo Cavazzoni, CINECA, Italy
•  Konstantinos Chasapis, DDN, Germany
•  Stefano Cozzini, CNR, Italy
•  Julian Kunkel, University of Reading, UK
•  Jacques-Charles Lafoucrière, CEA, France
•  Ramon Nou, BSC, Spain
•  Manolis Marazakis, FORTH, Greece
•  Marek Michalewicz, ICM, Poland
•  Judit Planas, EPFL, Switzerland
•  Benedikt Steinbusch, FZJ, Germany
•  Stéphane Thiell, Stanfor University, USA
•  Josef Weidendorfer, Leibniz Computing Centre (LRZ), Germany

Steering committee

• Jean-Thomas Acquaviva, DDN, France 
• Jalil Boukhobza, Univ. Bretagne Occidentale, France 
• André Brinkman, Johannes Gutenberg University Mainz, Germany
• Phlippe Deniel, CEA/DIF, France
• Massimo Lamanna, CERN, Switzerland
• Pedro Javier García, University of Castilla-La Mancha, Spain 
• Allen D. Malony, University of Oregon, USA

Contact

All questions about submissions should be emailed to jtacquaviva@ddn.com