Supercomputers/Systems/HPC4
Italy · operational · hpc
HPC4
Operated by Eni at Eni Green Data 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
- 12.21 PFlop/s
- Rpeak
- 18.62 PFlop/s
- Rmax ÷ Rpeak
- 65.6%
- Cores
- 253,600
- Power
- 1.32 MW
- Per watt
- 9.3 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 | - HPE ProLiant DL380 Gen10, 1,600 nodes | Hewlett Packard Enterprise | - | Verified | top500.orgeni.com |
| Accelerator | NVIDIA Tesla P100 Accelerators CUDA (Pascal GP100) · 3,584C · 1.48 GHz · 16 nm · 300 W two NVIDIA Tesla P100 per node across 1,600 nodes | NVIDIA | 3,200 estimated | Verified | eni.comtop500.org |
| CPU | Intel Xeon Platinum 8160 CPUs x86-64 · 24C · 2.1 GHz · 14 nm · 150 W two 24-core Xeon Platinum 8160 per node across 1,600 nodes | Intel | 3,200 estimated | Verified | eni.comtop500.org |
| Interconnect | Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds Mellanox InfiniBand EDR | NVIDIA | - | Reported | top500.org |
| Operating system | Red Hat Enterprise Linux Operating systems Linux distribution · Open source, commercial support subscription RHEL 7.4 | Red Hat | - | Reported | top500.org |
The read
Eni's HPE ProLiant DL380 Gen10 cluster at the Green Data Center in Ferrera Erbognone, 1,600 nodes each with two 24-core Intel Xeon Platinum 8160 CPUs and two NVIDIA Tesla P100 GPUs on Mellanox EDR InfiniBand, with a 15 PB storage subsystem. Launched January 18, 2018; Eni's own release states 18.6 PFlop/s peak, matching TOP500's 18.62 PFlop/s Rpeak and 12.21 PFlop/s Rmax across 253,600 cores, so the tier is verified. Eni's release also states that combined with the older HPC3 system the company then had 22.4 PFlop/s of total peak capacity, a company-wide figure rather than HPC4 alone. First appeared on the June 2018 TOP500 list at rank 13 and was still listed as of November 2025 at rank 144. Distinct from the later Dell-built HPC5 (2020) and HPE Cray EX4000 HPC6/HPC7 (2024) already in this dataset.
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
- 2026-09-27 HPC4 added, Eni's HPE ProLiant/Tesla P100 supercomputer at the Green Data Center, predecessor to HPC5/HPC6/HPC7
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 | Intel Xeon Platinum 8160, NVIDIA Tesla P100, Mellanox InfiniBand EDR |
| eni.com | names system and part | NVIDIA Tesla P100, 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.