Supercomputers/Systems/Puhti
Finland · decommissioned · mixed
Puhti
Operated by CSC .
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
- 1.71 PFlop/s
- Rpeak
- 2.69 PFlop/s
- Rmax ÷ Rpeak
- 63.6%
- Cores
- 40,000
- Power
- 585 kW
- Per watt
- 2.9 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 | - Bull Sequana X1000 | Bull | - | Reported | top500.org |
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA V100 32GB, four per node in 80 AI-partition nodes | NVIDIA | - | Reported | docs.csc.fi |
| CPU | - Intel Xeon Gold 6230 20C 2.1GHz Cascade Lake, two per CPU node | Intel | - | Reported | docs.csc.fitop500.org |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds Mellanox HDR100 InfiniBand at 100 Gbps | NVIDIA | - | Verified | docs.csc.fitop500.org |
The read
CSC's general-purpose Bull Sequana X1000 supercomputer for Finnish researchers: 682 CPU nodes with dual 20-core Cascade Lake Xeons (1.8 PFlop/s) plus an 80-node AI partition with four NVIDIA V100 32GB GPUs per node (2.7 PFlop/s), on 100 Gbps HDR InfiniBand with 4.8 PB of Lustre. CSC's documentation reports the computing services shut down on 31 July 2026. TOP500 lists 40,000 cores and 1.71 PFlop/s Rmax, 280th on the June 2020 list.
Timeline
- 2019 First operational source
- 2020-06 List debut at #280 (June 2020) source
- 2026-07-31 Decommissioned source
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 Puhti, CSC's Bull Sequana supercomputer
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.csc.fi | names system and part | NVIDIA InfiniBand HDR |
| top500.org | names system and part | NVIDIA InfiniBand HDR |
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.