Customer Profile
About Vanderbilt ACCRE
The Vanderbilt Advanced Computing Center for Research and Education (ACCRE) is a campus-wide high-performance computing (HPC) resource. Its core mission is to enable faculty, researchers, and students to tackle scientific, engineering, and cross-disciplinary questions of societal importance that would otherwise be difficult or impossible.
ACCRE supports researchers from diverse disciplines—including genetics, physics, astronomy, and social sciences—enabling them to run large simulations, data analyses, and machine-learning models across a massive environment consisting of 750 compute nodes and 80 GPU nodes.
The Problem
Fragmented Silos & High Costs: ACCRE relied on separate storage systems for performance (GPFS, VDURA) and archive (LStore).
This created data silos that made it difficult to move data efficiently, constrained agility, and relied on expensive legacy appliances that locked them into specific vendors.
The Solution
Unified Global Namespace: Hammerspace unified Tier 0 (server-local NVMe), Tier 1 (Commodity), and Tier 2 (LStore Archive) into a single environment.
This allowed ACCRE to activate underused local NVMe storage as a high-performance tier and dynamically compose storage resources without data migration.
“Hammerspace… allows for immense flexibility, immense cost savings, and covers all cluster workload profiles. This integration not only cuts our costs dramatically but also changes how we deliver compute and storage services.”