Join us on June 25, 2025, for a webinar hosted by HPE's Johann Lombardi, where we'll explore Distributed Asynchronous Object Storage (DAOS) on Aurora. 

Distributed Asynchronous Object Storage (DAOS) is a high-performance, open-source storage stack that is transforming data management for HPC and AI workloads. Built on a fully distributed key-value architecture, DAOS overcomes the data and metadata bottlenecks inherent in traditional POSIX-based systems. By leveraging commodity hardware, it delivers exceptional performance and cost efficiency while supporting file, block, and object access modes. DAOS also offers a rich set of interfaces, including TensorFlow, PyTorch, HDF5, and MPI-IO. This talk will introduce the DAOS project and its growing open-source community, explore the architectural foundations of DAOS, and highlight its deployment on the Aurora exascale supercomputer.

Johann Lombardi is a Senior Distinguished Engineer at Hewlett Packard Enterprise (HPE) and the Technical Steering Committee (TSC) Chair of the DAOS Foundation, an open-source project under the Linux Foundation. Before joining HPE, he spent 12 years at Intel as a Senior Principal Engineer and Lead Architect for the DAOS project. Earlier in his career, Johann gained 8 years of experience contributing to the advancement of the Lustre parallel file system.

Kaushik Velusamy,  is an Assistant Computer Scientist in the data science group with the Argonne Leadership Computing Facility at Argonne National Laboratory. His research focuses on optimizing data access performance for machine learning and exploring novel computer architectures. His current projects include scientific data management, DAOS, deep learning I/O (DLIO), HDF5,  collective communications, distributed memory systems, parallel I/O, and large-scale distributed deep learning. He received his Ph.D. in Computer Science from the University of Maryland in 2021.