Supercomputers/Systems/Cassava AI Factory
South Africa · operational · ai training
Cassava AI Factory
Operated by Cassava Technologies at Africa Data Centres CPT1 .
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
- 77.79 PFlop/s
- Rpeak
- 102.2 PFlop/s
- Rmax ÷ Rpeak
- 76.1%
- Cores
- 285,696
- 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 | - HPE Cray XD670 | Hewlett Packard Enterprise | - | Reported | top500.org |
| Accelerator | NVIDIA H200 SXM Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W NVIDIA H200 SXM5 141GB | NVIDIA | - | Reported | top500.org |
| CPU | Intel Xeon Platinum 8558 CPUs x86-64 · 48C · 2.1 GHz · Intel 7 Xeon Platinum 8558 48C 2.1GHz | 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 NDR | 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 | 12,000 accelerators | 2025-11 | Operator stated | Founder says Cassava acquired 12,000 NVIDIA GPUs for sites in five countries; shipments landed in Cape Town. Per-site split not stated, so this is programme-wide. | connectingafrica.com |
The read
The only system in this dataset on the African continent. Cassava originally targeted a mid-2025 go-live; independent reporting as late as May 2026 described the Cape Town site as still preparing to go live, and its only TOP500 appearance is the June 2026 list, so the original target should be read as missed and superseded rather than met. Exact hardware configuration is confirmed only by TOP500 itself, not by Cassava's own public statements.
Timeline
- 2025-03 Announced source
- 2026-06 List debut at #36 (June 2026) source
- 2026-06 First operational 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
Change history
- 2026-10-04 Added AI datacenter metrics for cassava-ai-factory
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 H200 SXM, Intel Xeon Platinum 8558, NVIDIA InfiniBand NDR (Quantum-2) |
| itweb.co.za | names system only | - |
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.