• The Keck computational research cluster.
Information Systems & Technology

Research Technology Support

» Keck Computational Research Cluster

The Keck Computational Research Cluster

The Keck Computational Research Cluster is the premier computational resource available to Chapman researchers. Located in the Keck Center for Science and Engineering and extending into multiple public clouds, it provides CPU and GPU processing for research workloads of all kinds.

Cluster Summary (for grant applications):

“The Keck College High Performance Computing (HPC) cluster is available for researchers to run compute intensive, large memory programs quickly and efficiently. Located in Chapman University's Keck Center for Science & Engineering, the cluster contains over 590 Intel Xeon compute cores, 2.7TB of RAM, and direct access to all-flash and disk-storage SAN arrays. 16 Nvidia TESLA V100 cards are available for workloads that benefit from GPU accelerated processing. Access and management of the cluster and associated applications is supported by the University's IS&T Research Computing team.”

  • 13 physical on-premise servers
  • 592 Intel Xeon CPU cores
  • 2.7 Tb of RAM
  • 40,960 NVIDIA Turing GPU Cuda cores
  • 5,120 NVIDIA Turing GPU Tensor cores
One Deep-Learning Supermicro/Exxact node
  • 384Gb RAM
  • 48 Intel Xeon cores
  • 8 NVIDIA Tesla V100 SXM2 GPUs
Two Deep-Learning Asus nodes
  • 384Gb of RAM each
  • 40 Intel Xeon cores each
  • 4 NVIDIA Tesla V100 GPUs each
Two Machine-Learning Supermicro nodes
  • 4 NVIDIA GTX980 GPUs (2048 Pascal CUDA cores, 4Gb RAM) each
Seven General-Purpose Supermicro nodes
  • 256Gb of RAM
  • 72 Intel Xeon cores each
One Supermicro/Bright Computing head-node
  • 128Gb of RAM
  • 16 Intel Xeon cores

Up to 1000 additional on-demand nodes, instantiated as needed in AWS, Azure, or Google public clouds.