# Computing Resources ## expand\_more ITC computational resources are managed by [Faculty of Arts and Sciences Research Computing](https://www.rc.fas.harvard.edu/) (FASRC). ITC users have access to the [Cannon](https://www.rc.fas.harvard.edu/about/cluster-architecture/) cluster which has over 100,000 cores and 1000 GPU’s available for use. Information on the general use partitions for Cannon can be found on the [FASRC website](https://docs.rc.fas.harvard.edu/). In addition to Cannon, the ITC has purchased additional compute nodes for its own dedicated use. These compute nodes are split into three partitions. The first is the itc\_cluster partition which consists of 20 nodes each with two water cooled Intel 56-core Platinum 8480CL Sapphire Rapids processors with 9 GB of RAM per core, for a total of 1TB of RAM per node. This gives a total of 2,240 cores available for use and 20 TB of RAM. The nodes are interconnected with NDR Infiniband and are part of the larger Cannon Infiniband network. This partition has a run time limit of 7 days and is subject to normal fairshare rules. The second is the itc\_gpu partition which consists of 4 nodes each with two water cooled Intel 32-core Platinum 8358 Ice Lake processors with 32 GB of RAM per core, for a total of 2 TB of RAM per node, and 4 watercooled Nvidia A100 GPUs. This gives a total of 256 cores available for use, 8 TB of RAM, and 16 GPUs. This partition has a run time limit of 7 days, users must request at least one GPU to use this partition, and is subject to normal fairshare rules. The final is the itc\_gpu\_requeue partition which uses the same hardware as the itc\_gpu partition. Jobs in this partition can be preempted by jobs in the itc\_gpu partition. The partition has a 7 day time limit. There are no other restrictions on the use of this partition. Work in this partition is half the cost of work on itc\_gpu. The ITC has also purchased 200T worth of [Cluster Storage](https://docs.rc.fas.harvard.edu/kb/storage-service-center/) on Cannon. This storage is intended for groups and users who have not purchased their own resources. This storage is not snapshotted or backed up. Groups within the ITC have also purchased resources beyond those provided by FAS and ITC. These resources vary from group to group and may include machines not managed by RC. If you desire more information on the resources held by a specific group please contact them directly. To help ITC members utilize the cluster and the computational resources, the ITC has a member of FAS Research Computing, [Paul Edmon](https://www.rc.fas.harvard.edu/about/people/paul-edmon/) (pedmon@cfa), on [staff](https://www.rc.fas.harvard.edu/about/people/paul-edmon/). He is a trained astronomer with a background in high performance computing (HPC) and computational astrophysics. He is available to help with general HPC concerns. FAS Research Computing staff are also available for help on software installation, debugging, and problems with the cluster. Please contact FASRC at if help is needed. For more information, please look at the FAS Research Computing website at[ http://rc.fas.harvard.edu](http://rc.fas.harvard.edu/). To gain access to Cannon follow this guide: