Supercomputers/Systems/Marconi-100
Italy · decommissioned · hpc
Marconi-100
Also known as MARCONI100
Operated by CINECA at CINECA (Marconi100 site) .
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
- 21.64 PFlop/s
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- 347,776
- Power
- 1.48 MW
- Per watt
- 14.7 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 Power AC922 | IBM | - | Verified | indico.euro-fusion.orgtop500.org |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W 4 NVIDIA Volta V100 GPUs per node, 980 nodes | NVIDIA | 3,920 estimated | Verified | indico.euro-fusion.orgtop500.org |
| CPU | IBM POWER9 22C CPUs POWER · 22C · 3.07 GHz · 14 nm · 190 W two 16-core IBM POWER9 per node, 980 compute nodes | IBM | - | Verified | indico.euro-fusion.orgtop500.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds Mellanox InfiniBand EDR DragonFly+ | NVIDIA | - | Verified | indico.euro-fusion.orgtop500.org |
| Storage | IBM Spectrum Scale ESS (GPFS) Storage Parallel filesystem (GPFS), erasure-coded declustered RAID · 250 PB on Summit (Alpine) · About 2.5 TB/s 8PB raw GPFS storage | IBM | - | Reported | fusion.bsc.es |
| Operating system | Red Hat Enterprise Linux Operating systems Linux distribution · Open source, commercial support subscription Red Hat Enterprise Linux Server release 7.6 | Red Hat | - | Verified | indico.euro-fusion.orgtop500.org |
The read
CINECA's IBM Power AC922 accelerated cluster: 980 nodes of two 16-core POWER9 CPUs and four NVIDIA V100 GPUs on dual-rail InfiniBand EDR, ninth on the June 2020 TOP500. A CINECA slide deck and TOP500 agree on the hardware, but CINECA's peak of about 32 PFlop/s differs from TOP500's 29.35, so no peak is recorded. CINECA's own notice gives 30 June 2023 as the end of production, with storage kept until 9 February 2024, so June 2023 is used as the end date. The May 2020 start comes from a Barcelona fusion group's description of the machine as operational then. No page we fetched names the machine's town, so no coordinates are recorded. TOP500 is the only source for Rmax, so the tier is reported.
Timeline
- 2020-05 First operational source
- 2020-06 List debut at #9 (June 2020) source
- 2023-06 Production phase ended June 30 ahead of final data removal source
- 2023-06 Decommissioned source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
Where sources disagree
We record conflicts instead of picking a winner quietly. All open questions.
- Peak performance: nearly 32 PFlop/s (CINECA slides) against 29.35 PFlop/s (TOP500). No peak is recorded.
Change history
- 2026-09-20 Added with a rank pointer; hardware confirmed by CINECA and TOP500, peak conflict logged
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 |
|---|---|---|
| indico.euro-fusion.org | does not name this system | - |
| top500.org | names system and part | IBM POWER9 22C, Mellanox InfiniBand EDR, IBM Spectrum Scale ESS (GPFS) |
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.