Supercomputers/Systems/Ubilink H100 Cluster
Taiwan · operational · ai training
Ubilink H100 Cluster
Operated by Ubilink.AI .
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
- 45.82 PFlop/s
- Rpeak
- 69.34 PFlop/s
- Rmax ÷ Rpeak
- 66.1%
- Cores
- 143,360
- Power
- 1.07 MW
- Per watt
- 43.0 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 | - 128 ASUS ESC N8-E11 servers | ASUS | 128 reported | Verified | press.asus.comtop500.org |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 1,024 NVIDIA HGX H100 SXM5 80GB GPUs | NVIDIA | 1,024 reported | Verified | press.asus.comtop500.org |
| CPU | Intel Xeon Platinum 8462Y+ CPUs x86-64 · 32C · 2.8 GHz · Intel 7 Intel Xeon Platinum 8462Y+ 32C 2.8GHz | 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 | - | Verified | press.asus.comtop500.org |
The read
Ubilink's ASUS-built NVIDIA H100 cluster in Taiwan. ASUS's 19 November 2024 release states 128 ESC N8-E11 servers with 1,024 NVIDIA HGX H100 SXM5 80 GB GPUs on InfiniBand NDR400, 45.82 PFlop/s at 66.08% efficiency, 31st on the November 2024 TOP500 and 44th on the Green500; TOP500 lists Xeon Platinum 8462Y+ 32C hosts, 143,360 cores, 69.34 PFlop/s Rpeak and 1,066 kW, and RHEL 8.9. The operator Ubilink was created from Foxlink, Ubitus and Shinfox Energy and offers public cloud and LLM-training rental. TOP500 ranks run 31st, 41st, 46th and 56th through June 2026. No page fetched gives the city, so the site is left blank.
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
- 2026-10-02 Added the Ubilink H100 Cluster in Taiwan
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 |
|---|---|---|
| press.asus.com | names system, part and count | NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) · counts: 1024 |
| top500.org | names system and part | Intel Xeon Platinum 8462Y+, NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) |
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.