No impact incident

Dartmouth College: HPC - GPU Intermittent issues

Sep 28, 2026, 18:50 UTC
started
14:07 UTC
resolved October 6, 2026
7 days 19 h
duration

Affected: HPC

Current status of Dartmouth College: Operational — live Dartmouth College status

Timeline

  1. Sep 28, 2026, 18:50 UTC
    identified
    We have identified an issue affecting several of our GPU‑compute nodes. The problem causes intermittent loss of GPUs (the devices may disappear and re‑appear under load). Our HPC team has identified the the root cause and working on a permanent fix. Thank you for your patience.
  2. Oct 6, 2026, 14:07 UTC
    resolved
    We have identified and resolved the issue with the GPU nodes, all of the nodes that had issues have been fixed.

Updates as published by Dartmouth College (original).

Other services with incidents at the same time

More Dartmouth College incidents