Supercomputers/Systems/Lomonosov
Russia · decommissioned · hpc
Lomonosov
Also known as MSU Lomonosov T-Platforms
Operated by Lomonosov Moscow State University at MSU Research Computing 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
- 901.90 TFlop/s
- Rpeak
- 1.70 PFlop/s
- Rmax ÷ Rpeak
- 53.0%
- Cores
- 78,660
- Power
- 2.80 MW
- Per watt
- 0.3 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 | - T-Platforms T-Blade2 (with T-Blade 1.1 and PowerXCell 8i nodes) | T-Platforms | - | Reported | top500.orgparallel.ru |
| Accelerator | - NVIDIA 2070 GPUs | NVIDIA | - | Reported | top500.orgparallel.ru |
| Accelerator | IBM PowerXCell 8i Accelerators Cell BE (PPE + 8 SPE) · 9C · 3.2 GHz · 65 nm · 92 W PowerXCell 8i accelerator nodes | IBM | - | Reported | top500.orgparallel.ru |
| CPU | Intel Xeon X5670 CPUs x86-64 · 6C · 2.93 GHz · 32 nm · 95 W Xeon X5670 6C 2.93GHz | Intel | - | Reported | top500.orgparallel.ru |
| Interconnect | Mellanox InfiniBand QDR Interconnect Fat tree · 40 Gb/s per 4x port Infiniband QDR | NVIDIA | - | Reported | top500.orgparallel.ru |
The read
Moscow State University's T-Platforms hybrid supercomputer, 26th on the November 2012 TOP500 after expansions with GPU and PowerXCell nodes. TOP500 lists 78,660 cores, Xeon X5670 6-core 2.93 GHz CPUs with NVIDIA 2070 GPUs and PowerXCell 8i accelerators on InfiniBand QDR at 901.9 TFlop/s Rmax, 1.70 PFlop/s Rpeak and 2,800 kW, and keeps listing it until November 2018. The MSU Research Computing Center's page confirms the T-Platforms build, Xeon X5570 and X5670 plus NVIDIA X2070 nodes, 30 PowerXCell nodes, QDR InfiniBand, 1.7 PFlop/s peak, 901.9 TFlop/s Linpack, 2009 installation and about 2.6 MW. Its initial 2009 configuration, a separate TOP500 entry, was 12th on the November 2009 list at 350.1 TFlop/s. Lomonosov-2 is a separate system in this dataset. No retirement date was found, so none is recorded; decommissioned reflects its disappearance from TOP500 after November 2018. TOP500 is the only source for Rpeak and cores, so the tier is reported.
Timeline
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
- 2026-10-02 Added Lomonosov, Moscow State University's T-Platforms hybrid system, 26th on the November 2012 TOP500
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 |
|---|---|---|
| parallel.ru | names system and part | Intel Xeon X5670, IBM PowerXCell 8i, Mellanox InfiniBand QDR |
| top500.org | names system and part | Intel Xeon X5670, IBM PowerXCell 8i, Mellanox InfiniBand QDR |
Checked 2026-10-09 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.