Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Leveraging Computational Storage for Simulation Science Storage System Design

SNIAVideo via YouTube

Overview

Explore a 39-minute conference talk from the Storage Developer Conference (SDC) 2023 that delves into how computational storage can revolutionize simulation science storage systems. Learn about high-performance computing data centers' challenges in managing massive data generation from large-scale simulations, and discover innovative solutions for data absorption, processing, and indexing. Examine Los Alamos National Laboratory's collaborative efforts with partners like Aeon Computing, Eideticom, NVIDIA, SK hynix, and Seagate in implementing computational storage solutions. Gain insights into transparent ZFS I/O pipeline offloads, analytics acceleration using flash key-value based storage devices, and in-drive SQL-like query processing in erasure coded data lake tiers. Understand the importance of an open, standards-based approach for computational storage through object storage systems, while exploring real-world implementations, practical lessons learned, and future directions in this field. The presentation by Gary Grider from Los Alamos National Laboratory offers valuable knowledge about computational storage use-cases for HPC applications and their practical implementations.

Syllabus

SDC 2023 - Leveraging Computational Storage for Simulation Science Storage System Design

Taught by

SNIAVideo

Reviews

Start your review of Leveraging Computational Storage for Simulation Science Storage System Design

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.