Computing Clusters
Grace
Grace is a cluster available for shared use by the Faculty of Arts and Sciences (FAS). It is our largest and most versatile cluster, consisting of various compute nodes connected through low-latency InfiniBand and several shared storage filesystems. The cluster is named after Grace Murray Hopper, a computer scientist and one of the first three modern “programmers.” Hopper is best known for her trailblazing contributions to developing computer languages. She earned her Ph.D. in Mathematics from Yale in 1934. Learn more about Grace.
McCleary
McCleary is a shared-use resource for the Yale School of Medicine (YSM), life science researchers across disciplines, and projects associated with the Yale Center for Genome Analysis. It comprises various compute nodes networked over ethernet and linked to several shared storage filesystems. Yale’s first direct-to-chip liquid-cooled cluster is paving the way for a more sustainable future for the YCRC and the Yale research computing community. It is named after Beatrix McCleary Hamburg, the first female African American Yale School of Medicine graduate in 1948. Learn more about McCleary.
Milgram
Milgram compute nodes and its dedicated storage system are specifically designed for processing and storing sensitive data and are fully aligned with the Health Insurance Portability and Accountability Act (HIPAA). The system is used by researchers at the Yale Psychology Department and other researchers whose projects involve patient-related information. Milgram is named after Dr. Stanley Milgram, a psychologist whose work focused on behavioral motivations behind social awareness in individuals and obedience to authority figures. Several of his experiments conducted during his professorship at Yale University became famous and are still widely studied today. Learn more about Milgram.
Misha
Misha is a cluster of various types of compute nodes designed explicitly for interdisciplinary research projects at the Wu Tsai Institute. The Institute is a new initiative to bring neuroscience and data science together to advance the understanding of human cognition. The cluster is named after Dr. Misha Mahowald, an American computational neuroscientist who was inducted into the Women in Technology International Hall of Fame for her development of the Silicon Eye and other computational systems in the field of neuromorphic engineering. Learn more about Misha.
Bouchet
Our first installation at MGHPCC is a new HPC cluster called Bouchet. Bouchet is named for Edward Bouchet (1852-1918), the first self-identified African American to earn a doctorate from an American university, a PhD in physics at Yale University in 1876.
The Bouchet HPC cluster will be available in beta in Fall 2024. The first installation of nodes, approximately 4,000 direct-liquid-cooled cores, will be dedicated to tightly coupled parallel workflows, such as those run in the “mpi” partition on the Grace cluster. Later this year, we will acquire and install a large number of general-purpose compute nodes as well as GPU-enabled compute nodes. Learn more about Bouchet.
Storage
We maintain several high performance storage systems. Listed below are these shared filesystems and the clusters where they are available. We distinguish where clusters store their home directories with an asterisk. The directory /home will always point to your home directory on the cluster you logged into. For more information about storage quotas and purchasing storage see the Cluster Storage(link is external) page.
Scratch, Project, etc Storage(link is external)
