Overview of Brown-GPU

Brown-GPU was optimized for communities running traditional, tightly-coupled science and engineering applications. Brown-GPU was built through a partnership with Dell and Intel in March 2018. Brown-GPU consisted of Dell compute nodes with two 12-core Intel Xeon Gold "Sky Lake" processors (24 cores per node), 96 GB of memory, and three Tesla P100 GPUs. All nodes had 100 Gbps EDR Infiniband interconnect and a 5-year warranty.

Brown-GPU Namesake

Brown-GPU was named in honor of Herbert C. Brown, Nobel Laureate and Professor of Chemistry. More information about his life and impact on Purdue is available in an ITaP Biography of Herbert C. Brown.

Brown-GPU Detailed Hardware Specification

All Brown-GPU nodes had 24 processor cores, 96 GB of RAM, and 100 Gbps Infiniband interconnects.
Front-Ends Number of Nodes Processors per Node Cores per Node Memory per Node Retires in
With GPU 1 Two Sky Lake CPUs @ 2.60GHz with three Tesla P100 GPUs 24 192 GB 2023
Sub-Cluster Number of Nodes Processors per Node Cores per Node Memory per Node Retires in
A 15 Two Sky Lake CPUs @ 2.60GHz with three Tesla P100 GPUs 24 192 GB 2023

Brown-GPU nodes ran CentOS 7 and use Moab Workload Manager 8 and TORQUE Resource Manager 5 as the portable batch system (PBS) for resource and job management.


Purdue University, 610 Purdue Mall, West Lafayette, IN 47907, (765) 494-4600

© 2017 Purdue University | An equal access/equal opportunity university | Copyright Complaints | Maintained by ITaP Research Computing

Trouble with this page? Disability-related accessibility issue? Please contact us at online@purdue.edu so we can help.