Russia · operational · hpc

Lobachevsky

Also known as UNN Lobachevsky GPU cluster

Operated by Lobachevsky University at UNN Supercomputer Center .

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: 289.50 TFlop/s
Rpeak: 348.66 TFlop/s
Rmax ÷ Rpeak: 83.0%
Cores: 5,310
Power: 201.78 kW
Per watt: 1.4 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
Accelerator	- NVIDIA Tesla K20 (Kepler), three per GPU node on 120 Linux nodes	NVIDIA NVDANASDAQ	-	Reported	hpc-education.unn.ru
CPU	- Intel Xeon E5-2660v2 10C 2.2GHz (TOP500 listing; the university page states dual Xeon E5-2660 8C nodes)	Intel INTCNASDAQ	-	Reported	top500.org
Interconnect	Mellanox InfiniBand FDR Interconnect Fat tree · 56 Gb/s per 4x port · About 1 microsecond Infiniband FDR (TOP500 listing)	NVIDIA NVDANASDAQ	-	Reported	top500.org
Operating system	CentOS Operating systems Linux distribution, RHEL-compatible rebuild · Open source, community-maintained CentOS (TOP500 listing)	The CentOS Project IBMNYSE rolls up to IBM	-	Reported	top500.org

The read

The GPU blade cluster of Lobachevsky State University of Nizhny Novgorod, listed by TOP500 as Intel Xeon E5-2660v2 10C 2.2GHz hosts with NVIDIA K20 GPUs on InfiniBand FDR under CentOS, 5,310 cores at 289.50 TFlop/s Rmax and 348.66 TFlop/s Rpeak on 201.78 kW, installed in 2014. It debuted on the November 2014 list at rank 189, its best placing, and was last listed at rank 490 in June 2016, which is the basis for the status date. The university's own resources page describes the 2013 machine somewhat differently, as 120 Linux nodes of dual Xeon E5-2660 with three K20 GPUs each plus ten Xeon Phi 5110P nodes and a Windows segment of Tesla M2090 nodes, with a 573 TFlop/s peak, so the TOP500 figures are used for the measured and peak numbers and the CPU generation is left as listed by TOP500. Both pages are from different organizations but describe the same machine with differing detail, so the tier is reported.

Timeline

2014 First operational source
2014-11 List debut at #189 (November 2014) source

Public list appearances

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

#189: TOP500, November 2014 →

Site & facility

UNN Supercomputer Center

Location: Nizhny Novgorod, Russia

top500.org hpc-education.unn.ru

Change history

2026-10-04 Lobachevsky added, the TOP500-listed NVIDIA K20 GPU blade cluster of Lobachevsky State University of Nizhny Novgorod (289.5 TFlop/s Rmax, best rank 189 in November 2014)

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
hpc-education.unn.ru	names system and part	Mellanox InfiniBand FDR, CentOS
top500.org	names system and part	Mellanox InfiniBand FDR, CentOS

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