Supercomputers/Systems/Rorqual
Canada · operational · mixed
Rorqual
Also known as Rorqual (GPU)
Operated by Calcul Québec at McGill Calcul Quebec Data Centre .
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
- 6.97 PFlop/s
- Rpeak
- 19.79 PFlop/s
- Rmax ÷ Rpeak
- 35.2%
- Cores
- 47,952
- Power
- 228.42 kW
- Per watt
- 30.5 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 | - Dell PowerEdge XE8640 (GPU nodes) and PowerEdge R6525 (CPU nodes) per TOP500 | Dell Technologies | - | Reported | top500.org |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 324 GPUs, NVIDIA H100 SXM5 80GB per TOP500 (Calcul Quebec states 324 GPUs without naming the model) | NVIDIA | 324 reported | Reported | calculquebec.catop500.org |
| CPU | - Intel Xeon Gold 6448Y 32C 2.1GHz (GPU nodes) | Intel | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds InfiniBand HDR200 | NVIDIA | - | Reported | top500.org |
The read
Calcul Quebec's national system at the McGill-Calcul Quebec data centre in Montreal, replacing Beluga as part of the Digital Research Alliance of Canada's national infrastructure. Calcul Quebec states 137,000 CPU cores, 587 TB of RAM, 69 PB of disk and 324 GPUs; the Alliance dates its launch to 10 July 2025 and describes a water-based cooling design. TOP500 lists separate GPU and CPU entries; the row carries the GPU entry (Dell PowerEdge XE8640, Xeon Gold 6448Y 32C, NVIDIA H100 SXM5 80GB, InfiniBand HDR200, AlmaLinux 9.5, 47,952 cores, 228 kW), which ranked 192nd on the June 2025 list, its best rank, and 247th on the June 2026 list; the CPU entry (EPYC 9654, PowerEdge R6525) ranked 242nd in June 2025. Rmax is only about a third of Rpeak in that submission. The core count is the GPU partition's, not the 137,000-core whole system. The same Alliance news item places it at McGill, while the existing Narval row sits at the Ecole de technologie superieure.
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
- 2026-10-02 Added Rorqual, Calcul Quebec's Montreal H100 research system, 192nd on the June 2025 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 |
|---|---|---|
| calculquebec.ca | names system only | · counts: 324 |
| top500.org | names system and part | NVIDIA H100 SXM5, 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.