Supercomputers/Systems/NIPA (Kakao)
South Korea · operational · ai training
NIPA (Kakao)
Operated by Kakao at Kakao (Ansan) .
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
- 69.10 PFlop/s
- Rpeak
- 78.65 PFlop/s
- Rmax ÷ Rpeak
- 87.9%
- Cores
- 36,720
- 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 | - Supermicro SYS-A22GA-NBRT | Supermicro | - | Reported | top500.org |
| Accelerator | NVIDIA B200 SXM Accelerators CUDA (Blackwell) · TSMC 4NP · 1,000 W 2,040 NVIDIA B200 GPUs (of a planned 2,424); omitted from TOP500's own listing | NVIDIA | - | Verified | top500.orgkakaocorp.com |
| CPU | Intel Xeon 6 6900P (Granite Rapids) CPUs x86-64 · 128C · 2 GHz · Intel 3 · 500 W Xeon 6960P 72C 2.7GHz | Intel | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR400 | NVIDIA | - | Reported | top500.org |
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 | 2,040 accelerators | 2025-12 | Operator stated | Kakao: infrastructure done for 255 nodes (2,040 B200 GPUs), about 84 percent of 2,424 planned, at Kakao Ansan data center. | kakaocorp.com |
The read
Kakao's share of the same NIPA national GPU program that also funds NHN Cloud's two clusters. TOP500's own record for this system is anomalous: it lists only a CPU (Intel Xeon 6960P) and no accelerator at all, an omission inconsistent with its Rpeak figure. Kakao's own corporate page and an independent Korean outlet (AI Times) both confirm 2,040 NVIDIA B200 GPUs; the core count recorded here is TOP500's own CPU-only figure, carried as-is rather than corrected, with the accelerator fact sourced independently.
Timeline
- 2025-08 Announced source
- 2026-01 First operational source
- 2026-06 List debut at #39 (June 2026) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
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.
Every source cited on this page was readable, and none of them mentions this system. They are cited at page granularity, normally because no stable deep link could be found. That is a real weakness in this row and it is why the system carries a confidence tier below verified. See how this check works.
| Cited source | Result | Found on the page |
|---|---|---|
| top500.org | does not name this system | Intel Xeon 6 6900P (Granite Rapids), NVIDIA InfiniBand NDR (Quantum-2) |
| kakaocorp.com | does not name this system | NVIDIA B200 SXM |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.