Supercomputers/Systems/PITAGORA
Italy · operational · hpc
PITAGORA
Also known as Pitagora
Operated by CINECA .
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
- 27.90 PFlop/s
- Rpeak
- 36.97 PFlop/s
- Rmax ÷ Rpeak
- 75.5%
- Cores
- 99,456
- Power
- -
- Per watt
- - 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 | - Lenovo ThinkSystem SD650-N V3 (Booster) and SD665 V3 (DCGP) | Lenovo | - | Verified | top500.orgdocs.hpc.cineca.it |
| Accelerator | NVIDIA H100 SXM5 94GB Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 168 Booster nodes x 4 NVIDIA H100 SXM 94GB | NVIDIA | 672 estimated | Reported | docs.hpc.cineca.ittop500.org |
| CPU | Intel Xeon Gold 6548Y+ CPUs x86-64 · 32C · 2.5 GHz · Intel 7 · 250 W Intel Xeon Gold 6548Y+ 32C 2.5GHz, two per Booster node | Intel | - | Verified | top500.orgdocs.hpc.cineca.it |
| CPU | AMD EPYC 9005 (Turin) CPUs x86-64 · 192C · 2.7 GHz · TSMC N3E · 500 W 1,008 DCGP nodes with 2x AMD EPYC 9745 128c | AMD | - | Reported | docs.hpc.cineca.it |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR | NVIDIA | - | Reported | top500.org |
| Cooling | Direct liquid cooling, warm water Cooling Direct-to-chip cold plates, facility water loop · Removes 90+ percent of node heat to liquid Lenovo Neptune Direct Water-Cooling | Lenovo | - | Reported | media.enea.it |
The read
The CINECA Tier-1 system dedicated to fusion research, run with ENEA and EUROfusion for plasma-physics simulation and advanced-materials analysis, installed at the end of 2024 at CINECA's Casalecchio di Reno data centre near Bologna. CINECA documents two Lenovo partitions: a Booster of 168 SD650-N V3 nodes, each with two Xeon Gold 6548Y+ 32c and four NVIDIA H100 SXM 94GB, and a CPU-only DCGP of 1,008 SD665 V3 nodes with two AMD EPYC 9745 128c; Lenovo Neptune direct water cooling is used per the ENEA release. TOP500 lists the Booster (99,456 cores, Rmax 27.90 PFlop/s, Rpeak 36.97 PFlop/s, no power figure); it debuted at 44th on the November 2024 list with 55,104 cores, its best rank, and stood at 80th in June 2026. The ENEA release quotes about 55 PFlop/s for the full system. CINECA's page places it at Casalecchio di Reno rather than at the Bologna Technopole site recorded for Leonardo, so it is left unlocated.
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
- 2026-10-02 Added PITAGORA, the CINECA fusion-research system, 44th on the November 2024 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 |
|---|---|---|
| docs.hpc.cineca.it | names system and part | Intel Xeon Gold 6548Y+, AMD EPYC 9005 (Turin), NVIDIA H100 SXM5 94GB, NVIDIA InfiniBand NDR (Quantum-2), Direct liquid cooling, warm water |
| top500.org | names system and part | Intel Xeon Gold 6548Y+, NVIDIA H100 SXM5 94GB, NVIDIA InfiniBand NDR (Quantum-2) |
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.