Supercomputers/Systems/Kyushu VPP700/56
Japan · operational · hpc
Kyushu VPP700/56
Also known as Kyushu University Computer Center VPP700
Operated by Kyushu University .
Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1540 systems have a readable citation that names them, and 64 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
- 110.0 GFlop/s
- Rpeak
- 123.2 GFlop/s
- Rmax ÷ Rpeak
- 89.3%
- Cores
- 56
- 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 | - Fujitsu VPP700/56 | Fujitsu | - | Reported | top500.orgiii.kyushu-u.ac.jp |
| CPU | - Fujitsu VPP700 vector processing elements, 56 PEs, 2.2 GFlop/s and 2 GB each | Fujitsu | 56 reported | Reported | iii.kyushu-u.ac.jptop500.org |
| Interconnect | - Full distributed crossbar | Fujitsu | - | Reported | top500.orgiii.kyushu-u.ac.jp |
| Operating system | Fujitsu UXP Operating systems Unix (SVR4-derived), Fujitsu-customised · Proprietary Fujitsu UXP/V | Fujitsu | - | Reported | top500.orgiii.kyushu-u.ac.jp |
The read
Fujitsu VPP700 model 56 at the Computer Center of Kyushu University: 56 vector processing elements on a full distributed crossbar, running UXP/V, Rmax 110 and Rpeak 123.2 GFlop/s. TOP500 first lists it in November 1996 at rank 9 (94.3 GFlop/s, before tuning) and keeps it through November 2000 (rank 189); the same 110 GFlop/s figure appears in every appearance from June 1997 (https://www.top500.org/system/172395/). The centre's own news bulletin No. 549 (autumn 1996, https://iii.kyushu-u.ac.jp/doc/publish/cc_news/No.501%EF%BD%9E550/549.pdf) announces the choice of the VPP700/56 and service from 7 January 1997, with the old VP2600/10 kept in parallel operation until 28 February 1997; its table gives 56 PEs, 2.2 GFlop/s and 2 GB per PE (123.2 GFlop/s and 112 GB in total). Bulletin No. 550 (December 1996) adds that users could run on at most 32 of the 56 PEs at once and that each PE has two inter-PE communication units of up to 570 MB/s. The machine replaced the VP2600/10 that TOP500 lists at the same university in 1993 (https://www.top500.org/system/172262/); the centre's later systems belong to the RIIT line (kyushu-riit). TOP500 gives a 137 MHz clock. The first-operational date is the announced start of service; the list entry predates it by two months.
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
- 2026-10-18 Added Kyushu VPP700/56 (kyushu-university)
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.