Graham: Difference between revisions
No edit summary |
No edit summary |
||
| Line 26: | Line 26: | ||
| "Bigmem3000" nodes || 3 nodes || 16 cores/sockets, 4 sockets/node, 3 TB of memory. | | "Bigmem3000" nodes || 3 nodes || 16 cores/sockets, 4 sockets/node, 3 TB of memory. | ||
|- | |- | ||
| "GPU Base" nodes || 160 nodes || 16 cores/socket, 2 sockets/node, 128 GB of memory, 2 NVIDIA | | "GPU Base" nodes || 160 nodes || 16 cores/socket, 2 sockets/node, 128 GB of memory, 2 NVIDIA GPUs. | ||
|- | |- | ||
| "Cloud" nodes || 60 nodes || 16 cores/socket, 2 sockets/node, 256 GB of memory. | | "Cloud" nodes || 60 nodes || 16 cores/socket, 2 sockets/node, 256 GB of memory. | ||
| Line 36: | Line 36: | ||
<!--T:7--> | <!--T:7--> | ||
All of the above nodes will have local (on-node) storage. | All of the above nodes will have local (on-node) storage ranging from 300GB to 960GB SATA SSD drives. | ||
<!--T:8--> | <!--T:8--> | ||
| Line 45: | Line 45: | ||
<!--T:10--> | <!--T:10--> | ||
The completed system is expected to have | The completed system is expected to have around 35,000 cores. | ||
<!--T:11--> | <!--T:11--> | ||
The delivery and installation schedule is not yet | The delivery and installation schedule is not yet confirmed. | ||
<!--T:14--> | <!--T:14--> | ||
Revision as of 16:59, 12 January 2017
Graham (GP3)
GRAHAM is a heterogeneous cluster, suitable for a variety of workloads, and located at the University of Waterloo. It is named after Wes Graham, the first director of the Computing Centre at Waterloo. It was previously known as "GP3" and is still identified as such in the 2017 RAC documentation.
System evaluation is not yet completed as of November 2016. Anticipated specifications, based on Waterloo's RFP and bids received, include the following. This information is NOT GUARANTEED and might not be complete. It is provided for planning purposes.
The parallel filesystem, interconnects and external persistent storage (NDC-Waterloo) will be the same as Cedar's. There is a slightly different mix of compute nodes.
Node types and characteristics
| "Base" compute nodes | 800 nodes | 16 cores/socket, 2 sockets/node, 128 GB of memory. |
| "Bigmem512" nodes | 24 nodes | 16 cores/socket, 2 sockets/node, 512 GB of memory. |
| "Bigmem3000" nodes | 3 nodes | 16 cores/sockets, 4 sockets/node, 3 TB of memory. |
| "GPU Base" nodes | 160 nodes | 16 cores/socket, 2 sockets/node, 128 GB of memory, 2 NVIDIA GPUs. |
| "Cloud" nodes | 60 nodes | 16 cores/socket, 2 sockets/node, 256 GB of memory. |
| "TDS Base" nodes | 4 | 16 cores/socket, 2 sockets/node, 128 GB of memory. |
| "TDS Cloud" nodes | 5 | 16 cores/socket, 2 sockets/node, 128 GB of memory. |
All of the above nodes will have local (on-node) storage ranging from 300GB to 960GB SATA SSD drives.
Compute Canada is not currently able to disclose the specific CPU model or specifications.
Graham will have GPU's, but Compute Canada is not currently able to disclose specific details. The RFP used NVIDIA K80 as a baseline specification.
The completed system is expected to have around 35,000 cores.
The delivery and installation schedule is not yet confirmed.