Overview
The MedicineBow Compute Environment (AKA MedicineBow) is a high performance computing (HPC) cluster that will provide enhanced GPU offerings to enable research in key areas including AI, machine, and deep learning, and enhanced modeling. ARCC works to maintain an expected uptime of 98% and multi-petabytes of storage available to researchers. Our resources allow researchers to perform a wide array of computation-intensive analyses on datasets of various sizes.Effective upon go-live, scheduled for July 15, 2024, MedicineBow will be securely accessible anywhere, anytime over the web using MedicineBow OnDemand, or over SSH with a ssh key and certificate for authentication.
MedicineBow hardware
To see a summary of the MedicineBow hardware click here.
MedicineBow Data Storage
MedicineBow’s storage is divided into three isolated filesystems to ensure that researchers have control of where their data is, and who can access it.
/home: for configuration files and software user specific installations.
/project: a collaborative area shared among project members.
Within every project file is 250GB available for project software installation within a directory called /software
/gscratch: a large and fast storage area to temporarily store large data sets while they are being processed. This area is not backed up and is subject to periodic purges of old data.
A page with specifics on MedicineBow Storage and Filesystem is accessible here. MedicineBow data and storage is subject to ARCC’s general storage policy detailing default allocation sizes, costs for storage increases, and purge policy.
Software
A summary of the MedicineBow software and MedicineBow software list is pending and will be available shortly.
Project and Account Requests
For research projects, UWyo faculty members (Principal Investigators or PIs) can request a research project on ARCC HPC (high performance computing) resources, using this form.
Note: you may also submit an initial set of users for your research project using the same form.
User Accounts require a valid UWyo email address and a UWyo-Affiliated PI sponsor. UWyo faculty members can sponsor their own accounts, while students, post-doctoral researchers, or research associates must use their PI as their sponsor. Users with a valid UWyo email address can be added in the project request or added later, using the Request a Change to Your Project form.
Non-UWyo external collaborators (Ex_Co) must be sponsored by a current UWyo faculty member. Ex_Co accounts can be requested here. Please supply the Ex_Co username when requesting they be added to a project.
Logging Into MedicineBow
Once access is granted, connection to ARCC HPC resources may be established either through OnDemand at https://medicinebow.arcc.uwyo.edu, or via SSH.
Note that SSH connections on MedicineBow require ssh key setup.
Directions for logging into MedicineBow over the web via OnDemand are available here.
Directions for setting up Password-Free SSH on MedicineBow are available here.
Condo Model
Our MedicineBow cluster follows a condominium-style model of resource management. Investors, which are individual researchers or groups of researchers, work with us at ARCC to purchase compute nodes and storage. Investors receive priority to their investment nodes. Nodes must be approved by ARCC before investments are purchased. (See node purchase estimates for examples)
Condo computing resources are used simultaneously by multiple users. When the investor-purchased resources aren’t in use by the investor defined users, those resources will be made available to the community. Within the condo model investors have priority on invested resources; This is implemented through preemption. General access to investor-owned resources can be immediately revoked when the investors wish to use their resources. The job will automatically be re-queued to ease the burden on users.
MedicineBow includes a number of non-investor resources. These nodes are available to the general research community for use on a first-come-first-serve basis.
Citing MedicineBow
As an upcoming resource, information on citing MedicineBow is forthcoming. In the meantime, please reference the citing section under Documentation and Help.