Supercomputers/Systems/MareNostrum P9 CTE
Spain · operational · hpc
MareNostrum P9 CTE
Also known as MareNostrum 4 POWER9 racks
Operated by Barcelona Supercomputing 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
- 1.02 PFlop/s
- Rpeak
- 1.49 PFlop/s
- Rmax ÷ Rpeak
- 68.3%
- Cores
- 19,440
- Power
- 85.8 kW
- Per watt
- 11.9 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 POWER9 nodes (Power System AC922), 54 nodes in three racks | IBM | 54 reported | Reported | bsc.estop500.org |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA Tesla V100, four per server across 54 servers | NVIDIA | 216 estimated | Reported | bsc.estop500.org |
| CPU | IBM POWER9 22C CPUs POWER · 22C · 3.07 GHz · 14 nm · 190 W IBM POWER9 3.1GHz, two per server across 54 servers | IBM | 108 estimated | Reported | bsc.estop500.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds Mellanox EDR network | Mellanox NVDANASDAQ
rolls up to NVIDIA | - | Reported | bsc.estop500.org |
The read
The POWER9 emerging-technology block of MareNostrum 4: three racks of 54 IBM POWER9 nodes (listed by TOP500 as Power System AC922), each with two POWER9 processors of 20 cores at 3.1GHz and four NVIDIA Volta GPUs, on a Mellanox EDR network, delivered by IBM on 29 December 2017 and in operation from May 2018. BSC reports 1.01 PFlop/s on Linpack at 85.8 kW (11.77 GFlops/Watt) and 1.48 PFlop/s peak; the June 2018 Green500 row (ninth place) gives 1,018 TFlop/s Rmax and 11.865 GFlops/Watt. It re-ran in 2019 at 18,360 cores and 14.131 GFlops/Watt (fourth on the June 2019 Green500). Last TOP500 appearance was November 2019. Trade press counts 2,160 CPU cores across the 54 nodes; TOP500 lists the CPU as a 22-core part.
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
- 2026-10-07 Added MareNostrum P9 CTE
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 |
|---|---|---|
| bsc.es | names system and part | IBM POWER9 22C |
| top500.org | names system and part | IBM POWER9 22C, NVIDIA Tesla V100, Mellanox InfiniBand EDR |
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.