Supercomputers/Systems/CHPC Blue Gene/P
South Africa · operational · hpc
CHPC Blue Gene/P
Also known as CSIR Blue Gene/P, Meraka Blue Gene/P
Operated by CHPC .
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
- 23.86 TFlop/s
- Rpeak
- 27.85 TFlop/s
- Rmax ÷ Rpeak
- 85.7%
- Cores
- 8,192
- Power
- 63 kW
- Per watt
- 0.4 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 | - IBM Blue Gene/P Solution (TOP500 listing; donated by IBM, project-managed by IBM with Business Connexion as integrator per ITWeb) | IBM | - | Reported | top500.orgitweb.co.za |
| CPU | IBM PowerPC 450 850MHz CPUs PowerPC · 4C · 0.85 GHz · 90 nm IBM PowerPC 450 4C 850MHz, 8,192 cores (TOP500 listing) | IBM | - | Reported | top500.org |
| Interconnect | - Proprietary Blue Gene/P interconnect (TOP500 listing) | IBM | - | Reported | top500.org |
The read
An IBM Blue Gene/P donated to South Africa and hosted at the Centre for High Performance Computing in Cape Town, billed at its unveiling as the most powerful supercomputer in Africa. ITWeb dates the unveiling to 8 October 2008 and describes a 14-teraflop machine of 1,024 nodes with four processors each, project-managed by IBM with Business Connexion as integrator and designed to work alongside an IBM E1350 system already at the centre. Brand South Africa (https://www.brandsouthafrica.com/stay-updated/quick-facts/2008/africas-biggest-supercomputer/) dates the launch to 15 October 2008, puts the donation at about US$2 million within a US$120 million IBM investment in sub-Saharan Africa, and says the Meraka Institute of the CSIR managed it for African research institutions. TOP500 lists 8,192 cores of PowerPC 450 4C 850MHz with a proprietary interconnect, 23.86 TFlop/s Rmax, 27.85 TFlop/s Rpeak and 63 kW, ranked 128th on the November 2008 list (the list table itself shows 23.41 TFlop/s Rmax). That is twice the 4,096 processors in the press accounts, so the listed machine may be an expanded configuration; the difference is unresolved and TOP500 is the source for the figures here. November 2008 is its only list appearance found, which is the basis for the status date. The CHPC site row in this dataset covers the later Lengau installation, so this system is left unlocated.
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 CHPC Blue Gene/P
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 |
|---|---|---|
| itweb.co.za | names system only | - |
| top500.org | names system and part | IBM PowerPC 450 850MHz |
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.