Japan · decommissioned · hpc

Cygnus

Operated by University of Tsukuba at Tsukuba Center for Computational Sciences .

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: 1.58 PFlop/s
Rpeak: 2.40 PFlop/s
Rmax ÷ Rpeak: 65.8%
Cores: 27,520
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	- NEC LX cluster, 80 nodes (48 Deneb GPU nodes, 32 Albireo GPU-FPGA nodes)	NEC 6701TSE	-	Reported	top500.org ccs.tsukuba.ac.jp
Accelerator	NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA Tesla V100 PCIe 32GB, four per node across 80 nodes	NVIDIA NVDANASDAQ	320 estimated	Reported	ccs.tsukuba.ac.jp top500.org
CPU	- Intel Xeon Gold 6126 12C 2.6GHz, two per node	Intel INTCNASDAQ	-	Reported	top500.org ccs.tsukuba.ac.jp
Interconnect	NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds InfiniBand HDR100, four channels per node	NVIDIA NVDANASDAQ	-	Reported	top500.org ccs.tsukuba.ac.jp

The read

The University of Tsukuba's NEC accelerated cluster of 80 nodes, each with two Intel Xeon Gold 6126 (12-core) CPUs and four NVIDIA Tesla V100 PCIe GPUs on InfiniBand HDR100; 32 of the nodes (Albireo) also carry two Intel Stratix 10 FPGAs, which the centre called the first GPU-FPGA supercomputer opened for public use. The centre's design paper gives 2.4 PFlop/s double-precision peak, matching TOP500's Rpeak; TOP500 lists 27,520 cores and Rmax 1.58 PFlop/s, 264th on its June 2019 debut and on five lists to June 2021. Tsukuba's supercomputer page records the shutdown in March 2025. The design paper predates service, and no power figure or exact start date was found, so those are blank.

Timeline

2019 First operational source
2019-06 List debut at #264 (June 2019) source
2025-03 Decommissioned source

Public list appearances

Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.

#264: TOP500, June 2019 →

Site & facility

Tsukuba Center for Computational Sciences

Location: Tsukuba, Japan
Commissioned: 1996

museum.ipsj.or.jp netlib.org

Change history

2026-10-02 Cygnus added, from TOP500 and the University of Tsukuba

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 Tesla V100, NVIDIA InfiniBand HDR
ccs.tsukuba.ac.jp	names system only	· counts: 320

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.