Supercomputers/Systems/Minerva
USA · operational · mixed
Minerva
Also known as Mount Sinai Minerva; Minerva Scientific Computing Environment
Operated by Icahn School of Medicine at Mount Sinai .
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
- 7.91 PFlop/s
- Rpeak
- 9.99 PFlop/s
- Rmax ÷ Rpeak
- 79.2%
- Cores
- 28,080
- Power
- 170.91 kW
- Per watt
- 46.3 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 | - Lenovo ThinkSystem SD650 V3 (TOP500); SR780a V3 DGX for B200 nodes | Lenovo | - | Reported | top500.orglabs.icahn.mssm.edu |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W NVIDIA H100 SXM5 80GB (page headline total 236 H100 across the environment) | NVIDIA | - | Verified | top500.orglabs.icahn.mssm.edu |
| Accelerator | NVIDIA B200 SXM Accelerators CUDA (Blackwell) · TSMC 4NP · 1,000 W 48 NVIDIA B200 in 6 Lenovo SR780a V3 DGX nodes (added Feb 2026 per Minerva page) | NVIDIA | 48 reported | Reported | labs.icahn.mssm.edu |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Infiniband NDR400 | NVIDIA | - | Reported | top500.org |
The read
The Minerva Scientific Computing Environment of the Icahn School of Medicine at Mount Sinai, created in 2012 and upgraded most recently in November 2024 and February 2026; the TOP500 entry dates from the 2024 H100 expansion. TOP500 lists a Lenovo ThinkSystem SD650 V3 system (Xeon Platinum 9242 48-core 2.3 GHz as recorded, NVIDIA H100 SXM5 80 GB, InfiniBand NDR400, Linux): 28,080 cores, Rmax 7.91 PFlop/s, Rpeak 9.99 PFlop/s and 170.91 kW. The Minerva hardware page describes the whole environment as 25,584 Intel cores, 408 GPUs (48 B200, 236 H100, 32 L40S, 44 A100, 48 V100), 452 TB of memory and 46 PB of raw GPFS storage; H100 nodes include 47 nodes of four H100 SXM5 80 GB with Xeon 8568Y+ CPUs and the B200 nodes are six Lenovo SR780a V3 DGX nodes with eight GPUs each. The core counts and CPU model differ between TOP500 and the Minerva page and are not reconciled. TOP500 ranks: 147th (November 2024), 175th (June 2025), 205th (November 2025), 229th (June 2026). The physical data hall is not stated in the fetched pages.
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 Minerva, Mount Sinai's biomedical H100 cluster
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 |
|---|---|---|
| labs.icahn.mssm.edu | names system, part and count | NVIDIA H100 SXM5, NVIDIA B200 SXM, NVIDIA InfiniBand NDR (Quantum-2) · counts: 48 |
| top500.org | names system, part and count | NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) · counts: 48 |
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
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.