Qing Zheng Gives Presentation at MSST Conference
Qing’s presentation was titled, Accelerated Disks and Flashes: LANL’s Early Experience in Speeding Up Analytics Workloads Using Smart Devices.
Zeng’s work is part of a joint collaboration between LANL and Seagate that explores developing efficient computing near storage, especially in settings where erasure encoding is needed for data protection. This overarching goal is to improve the sustainability of compute and storage architectures.
This work is on proof-of-concept high-performance compute architecture that provides optimized computing capabilities across and within storage devices. The architecture allows for computing functions to be pushed down into an erasure-encoded hard drive tier. The architecture will allow for faster, more efficient, less energy-intensive and less thermally demanding data retrieval.
Contributors include Jason Lee, Brian Atkinson, Jarrett Crews, David Bonnie, Dominic Manno and Gary Grider of Los Alamos National Laboratory, Philip Kufeldt, Ivan Rodriguez, Evan Burgess, David Allen, and John Bent of Seagate and Bradley Settlemyer of NVIDIA.
In addition to MSST, Qing and his team also presented their work at this year’s Storage Technology Showcase conference: https://storagetechshow.com/.
Qing Zheng is a Research Scientist at New Mexico Consortium and a Guest Scientist in Los Alamos National Laboratory’s HPC Design Group. Qing performs I/O and storage research that guides the Lab’s future computing platform and storage infrastructure designs. Qing received his PhD in Computer Science from Carnegie Mellon University in 2021. Qing is known for his expertise in distributed filesystem metadata and large-scale data analytics. Qing’s work has been exhibited at local science museums, reported by national media, and recognized with multiple R&D 100 and Supercomputing Best Paper Awards.