{"id":3175,"date":"2017-10-24T14:37:32","date_gmt":"2017-10-24T21:37:32","guid":{"rendered":"https:\/\/www.hmc.edu\/cis\/?page_id=3175"},"modified":"2026-05-15T02:33:09","modified_gmt":"2026-05-15T09:33:09","slug":"research-computing","status":"publish","type":"page","link":"https:\/\/www.hmc.edu\/cis\/arcs\/research-computing\/","title":{"rendered":"Research Computing"},"content":{"rendered":"\n

Academic and Research Computing Services (ARCS) helps Harvey Mudd faculty, students, and staff identify, access, and use computing resources for research and instruction.<\/p>\n\n\n\n

Research computing needs vary widely. Some projects run comfortably on a laptop. Others need more memory, more CPU cores, GPUs, shared storage, specialized software environments, or access to regional and national supercomputing systems. ARCS can help you understand which resource fits your project and how to get started.<\/p>\n\n\n\n

Not sure where to start?<\/strong>
Email ARCS<\/a> with a brief description of your research or instructional project. Helpful details include what software you are using, the size of your data, whether you need CPU, GPU, memory, or storage resources, and any relevant course or research deadlines.<\/p>\n\n\n\n

The Hardware Ladder at a Glance<\/strong><\/h2>\n\n\n\n

A useful way to think about research computing is through the\u00a0Hardware Ladder<\/strong>. Projects often begin on a personal machine and move to larger or more specialized systems as their needs grow.<\/p>\n\n\n\n

Each rung increases available compute resources, but also changes how the system is accessed and used. The table below summarizes the structure.<\/p>\n\n\n\n

Rung<\/strong><\/th>Resource<\/th>Scale & Capability<\/th>Access Model<\/th>Friction Level<\/th><\/tr><\/thead>
1<\/td>Personal machine<\/td>Local CPU\/GPU, limited memory<\/td>You already have one<\/td>None<\/td><\/tr>
2<\/td>Project Iris<\/strong> (single-node server \/ VM)<\/td>Hundreds of GB of RAM, 32+ cores, dedicated GPUs<\/td>Direct VM lease; students can get accounts without a faculty PI<\/td>Low<\/td><\/tr>
3<\/td>Hopper<\/a>
(CMC consortial cluster)<\/td>		Multi-node, SLURM-scheduled<\/td>Account request; research use<\/td>Moderate<\/td><\/tr>
4<\/td>Laguna<\/a>
(USC CARC regional cluster)<\/td>		Many nodes; browser-accessible via OnDemand<\/td>PI-based; compute-hour credits<\/td>Moderate\u2013high<\/td><\/tr>
5<\/td>ACCESS<\/a>
(national supercomputers)<\/td>		50+ national systems, specialized AI\/ML, enormous scale<\/td>Allocation application; credit-based<\/td>High<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Each rung is suited to a different class of workload. Moving up the ladder provides more capability, but typically requires more planning, coordination, and familiarity with the system.<\/p>\n\n\n\n

Rung 1 \u2014 Your Laptop<\/strong><\/h3>\n\n\n\n

Most projects begin on a personal machine. Laptops are well-suited for development, prototyping, small datasets, and early-stage analysis. The environment is fully controlled, iteration is fast, and there is no shared infrastructure to manage.<\/p>\n\n\n\n

Common signs that a workload has outgrown a laptop include long runtimes, memory limitations, datasets that exceed local storage, or the need for hardware such as GPUs that are not available locally. When these constraints become routine, it is usually time to move to the next rung.<\/p>\n\n\n\n

Rung 2 \u2014 A Single-Node Server or VM<\/strong><\/h3>\n\n\n\n

Rung 2 provides a step up in resources without introducing the full complexity of a shared cluster. This typically includes more memory, more CPU cores, persistent environments, and remote access via SSH.<\/p>\n\n\n\n

At HMC, this layer has historically consisted of departmental or faculty-managed systems (for example, Knuth and Teapot in CS, Hyper in Math, and Gandalf and Galadriel in Chemistry). While effective, these resources are not uniformly available across departments.<\/p>\n\n\n\n

Project Iris is designed to provide a consistent, institution-wide version of this rung.<\/p>\n\n\n\n

Project Iris: an institution-wide Rung 2<\/strong><\/h4>\n\n\n\n

Project Iris<\/strong> is an on-campus HPC service being deployed by ARCS. It provides access to virtual machines on shared HMC-managed hardware for both research and instructional use.<\/p>\n\n\n\n

System overview.<\/strong> The initial node includes two AMD EPYC 9965 CPUs (384 cores total), 3 TB of RAM, 60 TB of NVMe storage, and an NVIDIA RTX 4500 Blackwell GPU (32 GB). It will be housed in the McGregor Data Center, with capacity to expand to additional nodes over time.<\/p>\n\n\n\n

A GPU-focused second node is planned but has been deferred due to current hardware pricing. The deployment strategy is phased: establish the service, support initial users, and expand based on demonstrated demand.<\/p>\n\n\n\n

Why virtual machines?<\/strong> Iris uses Proxmox to deliver compute resources as virtual machines rather than shared user accounts on a single system. Each VM functions as an independent environment.<\/p>\n\n\n\n

This model provides:<\/p>\n\n\n\n