Supercomputers/Systems/Ginsburg (Columbia)
USA · operational · hpc
Ginsburg (Columbia)
Also known as Columbia Ginsburg HPC cluster
Operated by Columbia University .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- -
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- 9,152
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Accelerator | - 18 GPU nodes with two NVIDIA RTX 8000 GPUs each | NVIDIA | 36 reported | Reported | columbiauniversity.atlassian.net |
| Accelerator | - 4 GPU nodes with two NVIDIA V100S GPUs each | NVIDIA | 8 reported | Reported | columbiauniversity.atlassian.net |
| Accelerator | - 9 GPU nodes with two NVIDIA A40 GPUs each | NVIDIA | 18 reported | Reported | columbiauniversity.atlassian.net |
| Accelerator | - 8 GPU nodes with two NVIDIA A100 GPUs each | NVIDIA | 16 reported | Reported | columbiauniversity.atlassian.net |
| CPU | - Intel Xeon Gold 6226 2.9 GHz, two 16-core CPUs per node, 286 nodes | Intel | - | Reported | columbiauniversity.atlassian.net |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds 100 Gb/s HDR InfiniBand between compute nodes | NVIDIA | - | Reported | columbiauniversity.atlassian.net |
AI datacenter metrics
Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.
| Metric | Value | As of | Basis | Note | Source |
|---|---|---|---|---|---|
| Accelerators | 78 accelerators | 2026-10 | Operator stated | Our sum of 39 GPU nodes with two GPUs each (36 RTX 8000, 8 V100S, 18 A40, 16 A100). | columbiauniversity.atlassian.net |
The read
Columbia's shared HPC cluster. The technical page (updated 30 December 2025) states 286 nodes with 9,152 cores (two 16-core Intel Xeon Gold 6226 CPUs per node), made up of 191 standard nodes, 56 high-memory nodes and 39 GPU nodes with two GPUs each: 18 with RTX 8000, 4 with V100S, 9 with A40 and 8 with A100 (78 GPUs by our arithmetic). Interconnect is 100 Gb/s HDR InfiniBand and storage is 1.1 PB of Lustre. The page does not give a commissioning date. No FLOPS figure is published.
Timeline
No dated events recorded.
Change history
- 2026-10-07 Added Ginsburg (Columbia)
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| columbiauniversity.atlassian.net | names system and part | NVIDIA InfiniBand HDR |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.