Supercomputers/Systems/Siyuan-1
China · operational · mixed
Siyuan-1
Operated by Shanghai Jiao Tong University .
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
- 3.66 PFlop/s
- Rpeak
- 4.94 PFlop/s
- Rmax ÷ Rpeak
- 74.1%
- Cores
- 59,392
- 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 V2, Neptune liquid cooling | Lenovo | - | Reported | top500.orgnews.lenovo.com |
| Accelerator | - NVIDIA HGX A100, 23 GPU nodes | NVIDIA | - | Reported | docs.hpc.sjtu.edu.cn |
| CPU | Intel Xeon Platinum 8358 CPUs x86-64 · 32C · 2.6 GHz · 10 nm · 250 W Intel Xeon Platinum 8358 32C 2.6GHz, 938 CPU nodes | Intel | - | Reported | top500.orgdocs.hpc.sjtu.edu.cn |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds Mellanox HDR InfiniBand | NVIDIA | - | Reported | top500.org |
The read
Shanghai Jiao Tong University's Lenovo cluster (Siyuan-1) at the Yang Yuanqing Scientific Computing Center, Tsung-Dao Lee Institute, launched on 14 December 2021 and built in 120 days: 938 CPU nodes with Intel Xeon Platinum 8358 (Ice Lake) processors and 23 NVIDIA HGX A100 nodes, with Lenovo Neptune liquid cooling and HDR InfiniBand per TOP500. Lenovo quotes about 6 PFlop/s peak; TOP500's unnamed entry (ThinkSystem SD650 V2, 59,392 cores) gives Rmax 3.66 and Rpeak 4.94 PFlop/s, first listed 132nd in November 2021 and 342nd in November 2025. The university's documentation names the system and the node counts, but the TOP500 core count and Lenovo's peak describe only part of it, so figures are the TOP500 partition's and the tier is reported. TOP500 gives no power figure.
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 Siyuan-1 added, from TOP500 and Shanghai Jiao Tong University
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.sjtu.edu.cn | names system and part | Intel Xeon Platinum 8358 |
| top500.org | does not name this system | Intel Xeon Platinum 8358, 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.