Supercomputers/Systems/Rockfish
USA · operational · hpc
Rockfish
Operated by Johns Hopkins 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
- 1.89 PFlop/s
- Rpeak
- 3.11 PFlop/s
- Rmax ÷ Rpeak
- 60.8%
- Cores
- 32,352
- Power
- 369 kW
- Per watt
- 5.1 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 |
|---|---|---|---|---|---|
| Integrator | - Lenovo ThinkSystem SD530 | Lenovo | - | Reported | top500.org |
| Accelerator | - GPU nodes with NVIDIA A100 in 40 GB and 80 GB variants (ARCH lists 18 A100 nodes) | NVIDIA | - | Reported | arch.jhu.edu |
| CPU | - Dual 24-core Intel Xeon Gold 6248R 3.0 GHz (Cascade Lake) per compute node | Intel | - | Verified | top500.orgarch.jhu.edu |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds Mellanox InfiniBand HDR100 (1:1.5 topology) | NVIDIA | - | Verified | arch.jhu.edutop500.org |
| Storage | - About 13 PB across three IBM GPFS parallel file systems | IBM | - | Reported | arch.jhu.edu |
The read
Johns Hopkins University's NSF-funded (MRI award 1920103) community-shared cluster operated by ARCH, a Lenovo ThinkSystem SD530 machine with dual 24-core Xeon Gold 6248R (Cascade Lake) nodes on InfiniBand HDR100. TOP500 lists 32,352 cores, 1.89 PFlop/s Rmax, 3.11 PFlop/s Rpeak and 369 kW, with a best rank of 414th in June 2022. The ARCH page describes a later, expanded configuration (more nodes, Sapphire Rapids and Emerald Rapids nodes, 18 NVIDIA A100 nodes in 40 GB and 80 GB variants, L40S nodes and about 13 PB across three IBM GPFS file systems) and quotes 3.3 PFlop/s peak and 2.1 PFlop/s Rmax, which do not match the TOP500 figures used here. Core counts and node totals therefore differ by date.
Timeline
- 2022-06 List debut at #414 (June 2022) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-02 Added Rockfish (Johns Hopkins University)
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 |
|---|---|---|
| top500.org | names system and part | NVIDIA InfiniBand HDR |
| arch.jhu.edu | names system only | - |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Latency-optimised versus throughput-optimised processors, NUMA, and the end of the host-to-device copy.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.