Supercomputers/Systems/Circe
USA · operational · mixed
Circe
Also known as DGX-2H POD
Operated by NVIDIA .
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: 1263 of 1345 systems have a readable citation that names them, and 56 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
- 3.06 PFlop/s
- Rpeak
- 4.24 PFlop/s
- Rmax ÷ Rpeak
- 72.1%
- Cores
- 47,808
- 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 |
|---|---|---|---|---|---|
| Integrator | - NVIDIA DGX-2H POD, 36 DGX-2H servers | NVIDIA | - | Verified | top500.orgnextplatform.com |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA Tesla V100 SXM2, 16 per DGX-2H, 36 servers | NVIDIA | 576 reported | Reported | top500.orgnextplatform.com |
| CPU | Intel Xeon Platinum 8174 CPUs x86-64 · 24C · 3.1 GHz · 14 nm · 240 W Intel Xeon Platinum 8174 24C 3.1GHz hosts | Intel | - | Reported | top500.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds Mellanox InfiniBand EDR, eight 100 Gb/s interfaces per node | NVIDIA | - | Verified | top500.orgnextplatform.com |
The read
NVIDIA's first DGX-2H cluster, shown at SC18: 36 DGX-2H servers each with 16 Tesla V100 SXM2 GPUs and Xeon Platinum 8174 24C 3.1GHz hosts, joined by eight 100 Gb/s InfiniBand EDR links per node. TOP500 lists 47,808 cores at 3.057 PFlop/s Rmax, 4.24 PFlop/s Rpeak and an HPCG result of 199.196 TFlop/s, and The Next Platform independently gives 4.24 PFlop/s peak and 3.06 PFlop/s Linpack for the same 36-node machine. It debuted at rank 61 on the November 2018 list and last appeared at rank 90 on June 2020, which is the basis for the status date; the 96-node DGX SuperPOD that followed it is a separate row.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-09 Added Circe
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 | Intel Xeon Platinum 8174, NVIDIA Tesla V100, Mellanox InfiniBand EDR |
| nextplatform.com | names system, part and count | Intel Xeon Platinum 8174, NVIDIA Tesla V100, Mellanox InfiniBand EDR · counts: 576 |
Checked 2026-10-13 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.