Princeton Research Computing

Enabling high-impact research by bringing education and advanced computing
to the Princeton community

Systems

Princeton Research Computing operates four large clusters and several smaller systems.

Services

Supporting faculty, researchers and students with in-person and online help, software engineering, visualization and consulting on a wide range of research software tools.

Learn

An extensive educational, training, and outreach program in research computing, led by PICSciE, is available on campus and online.

Research

Research computing at Princeton University engages academic departments and disciplines across the natural sciences, engineering, social sciences, and humanities. 

Announcements

Machine Learning in Physics Seminar Series

A seminar series highlighting research on both physics-inspired approaches to understanding ML and the use of ML for physics applications.  Wednesdays 4:30 - 5:30pm in Jadwin Hall, Room A10 with light refreshments after the presentation from 9/27-11/29.  Register now!

Information Session for PICSciE's Graduate Certificate in Computational Science & Engineering, 10/9/23

Professor Michael Mueller, the program director of the graduate certificate will be available to answer questions. This will take place at 103 Maeder 12-1pm.  Register here.

Help Session

Weekly Help Sessions (Tuesdays)
Oct 3, 2023, 10:30 am

Research News

Facts and Figures

1500+

Accounts (faculty, staff, and students) from more than 50 academic departments, centers, programs, and institutional partners such as PPPL and GFDL currently use Princeton Research Computing's high-performance computing systems.

≈2,000

Students, postdocs, staff, and faculty members from over 45 departments and centers registered to attend computing and data science-centric workshops and mini-courses in the past year.

50+

Graduate students from over 20 academic departments are enrolled in PICSciE's Graduate Certificate in Computational Science and Engineering program.

90,000+

Over 90,000 CPU-cores and 500 GPUs provide 10.2 PFLOPS of computational power.