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.
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.
Keywords | XSEDE, SDSC, comet-gpu, Globus, File Transfer, GCS |
Quality Level | Production |
Audience | xsede.org |