The Comet GPU resource features 36 K80 GPU nodes, and 36 P100 nodes, and supports many commercial and community developed applications. Each K80 GPU node also features 2 Intel Haswell processors of the same design and performance as the standard compute nodes (described separately under the Comet resource). Each P100 GPU node also features 2 Intel Broadwell processors with 14 cores/socket (28 cores on the node). The GPU nodes are available through the Slurm scheduler for either dedicated or shared node jobs (i.e., a user can run on 1 or more GPUs/node and will be charged accordingly). Like the Comet standard compute nodes, the GPU nodes feature a local SSD which can be specified as a scratch resource during job execution – in many cases using SSD’s can alleviate I/O bottlenecks associated with using the shared Lustre parallel file system.

• Access Collection: https://app.globus.org/file-manager?origin_id=e4852a98-57b8-11e9-a620-0a54e005f950
• Usage documentation: https://www.globus.org/data-transfer
• Support Contact: help@xsede.org
• Organization: San Diego Supercomputer Center