Partnership for an Advanced Computing Environment
The Partnership for an Advanced Computing Environment (PACE) provides leading-edge high performance computing (HPC) resources with technical support services, infrastructure, software, and more.
How can PACE help you?
Is your research limited by the time it takes simulate or analyze results? Do you want to simulate much larger systems or problems?
If so, then PACE may be able to help!
PACE Services
✓ CPU/ GPU Compute Capacity
✓ Individual & Shared Project Storage
✓ Classroom & Teaching Resources
✓ Software (Open-source packages such as Python, R; Singularity/Apptainer container support; some licensed software)
✓ User Support & No-Cost Consultation Sessions
✓ Monthly Trainings, Workshops, & Other Learning Events
✓ User Documentation & Video Recordings
Get Started with PACE
Visit our Get Started with PACE page to learn more about using our compute and storage resources.
User Documentation
Guides are available for all of PACE systems as well as commonly used software tools and stacks. Search PACE’s Knowledge Base article for helpful guides and other resources.
Next Maintenance Date
PACE maintenance is tentatively scheduled for:
• October 6-8, 2025
• January 13-15, 2026
Service Status
Upcoming Events
Every month, PACE offers a variety of workshops, trainings, and other events to help advance the computational skillset of the Georgia Tech community. To see a full list of upcoming workshops and to register for an event, visit the Trainings, Workshops, and other Events page.
Recent Updates
-
Phoenix Login Outages
Summary: An issue with DNS caused researchers to receive error messages when attempting to ssh to Phoenix or to open a shell in Phoenix OnDemand…
-
Phoenix project storage outage, impacting login
Summary: An outage of the metadata servers on Phoenix project storage (Lustre) is preventing access to that storage and may also prevent login by ssh,…
-
Degraded performance on Phoenix storage
Dear Phoenix users, Summary: The project storage system on Phoenix (/storage/coda1) is slower than normal, due to heavy use and hard drive failures. The rebuild…