cc_staff
3
edits
HPC4Health: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
''Background'' | <big>'''''Background'''''</big> | ||
In the 2020 RAC, HPC4Health is part of a pilot project for the allocation of resources on a cluster provided by HPC4Health. | In the 2020 RAC, HPC4Health is part of a pilot project for the allocation of resources on a cluster provided by HPC4Health. | ||
| Line 8: | Line 8: | ||
Service configuration will be as per Compute Canada standards (Slurm, CVMFS); by request, specific technical configurations could also be considered. Availability and support is not yet fully determined and may change during the allocation year, but the platform is anticipated to be supported to the same degree as other host sites. | Service configuration will be as per Compute Canada standards (Slurm, CVMFS); by request, specific technical configurations could also be considered. Availability and support is not yet fully determined and may change during the allocation year, but the platform is anticipated to be supported to the same degree as other host sites. | ||
<big>'''''Requirements'''''</big> | |||
Pre-consultation with HPC4Health is required in order for an allocation request to be considered. Contact rac@computecanada.ca to arrange a consultation. | |||
In order to be eligible for HPC4Health resources, RAC awardees will be required to: | |||
# Sign a collaboration agreement with the University Health Network | |||
# Not act as a health information network provider under PHIPA (i.e., not to use HPC4Health resources to share the data to collaborators or through the web) | |||
# Use two factor authentication to log into the services | |||
Once awarded, recipients of the HPC4Health RAC resources will require consultation with the HPC4Health team to coordinate signing of the collaboration agreement and confirmation that recipients will not act as health information network providers. | Once awarded, recipients of the HPC4Health RAC resources will require consultation with the HPC4Health team to coordinate signing of the collaboration agreement and confirmation that recipients will not act as health information network providers. | ||
| Line 23: | Line 25: | ||
''Infrastructure For RAC 2020'' | <big>'''''Infrastructure For RAC 2020'''''</big> | ||
HPC4Health is allocating 500 CPU cores and 60TB of storage to the RAC pilot project. | HPC4Health is allocating 500 CPU cores and 60TB of storage to the RAC pilot project. | ||
Compute node specifications: | Compute node specifications: | ||
7 compute nodes with 38 cores and 230GB RAM | |||
7 compute nodes with 38 cores and 125GB RAM | * 7 compute nodes with 38 cores and 230GB RAM | ||
10 GE interconnects | |||
60TB of scale-out NFS accessible storage | * 7 compute nodes with 38 cores and 125GB RAM | ||
* 10 GE interconnects | |||
* 60TB of scale-out NFS accessible storage | |||
HPC4Health does not provide clients with tape backups, backups are the responsibility of the user | HPC4Health does not provide clients with tape backups, backups are the responsibility of the user | ||