Supercomputers/Systems/Narval
Canada · operational · hpc
Narval
Operated by Calcul Québec at École de technologie supérieure (Calcul Québec) .
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
- 5.89 PFlop/s
- Rpeak
- 12.17 PFlop/s
- Rmax ÷ Rpeak
- 48.4%
- Cores
- 76,320
- Power
- 311.14 kW
- Per watt
- 18.9 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 | - Dell PowerEdge XE8545, built by Dell Canada and CDW Canada | Dell Technologies | - | Verified | top500.orgcalculquebec.ca |
| Accelerator | NVIDIA A100 SXM4 40GB Accelerators CUDA (Ampere GA100) · 6,912C · 1.41 GHz · 7 nm · 400 W 632 NVIDIA A100 40GB GPUs (the user portal separately counts 636 across a slightly larger 80,720-core total) | NVIDIA | 632 reported | Reported | calculquebec.cadatacenterdynamics.com |
| CPU | - AMD EPYC 7413 24C 2.65GHz | AMD | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand HDR Interconnect Fat tree or dragonfly+ · 200 Gb/s per port · About 0.6 microseconds InfiniBand HDR100 at 100Gb/s to every node | NVIDIA | - | Verified | top500.orgportail.narval.calculquebec.ca |
The read
One of the Digital Research Alliance of Canada's (formerly Compute Canada) national systems, housed at the École de technologie supérieure in Montreal alongside the older Béluga cluster and run by Calcul Québec on behalf of McGill, Université de Montréal, Université Laval and Université de Sherbrooke. A Dell PowerEdge XE8545 cluster of AMD EPYC 7413 CPUs and NVIDIA A100 40GB GPUs on 100Gb/s InfiniBand HDR100, commissioned in December 2021 and 83rd on the November 2021 TOP500 at 5.89 PFlop/s. Calcul Québec's own announcement and Data Center Dynamics's coverage both give 632 A100 GPUs; the user portal's hardware page instead states 636 GPUs across 80,720 total cores against TOP500's 76,320, which reads like it is counting a handful of login or service nodes outside the ranked HPL partition rather than a real disagreement, so no single GPU count is treated as verified and the conflict is logged.
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
École de technologie supérieure (Calcul Québec)
- Location
- Montreal, Canada
- Commissioned
- 2021
Where sources disagree
We record conflicts instead of picking a winner quietly. All open questions.
- GPU count: 632 A100 GPUs (Calcul Québec launch announcement) against 636 GPUs across 80,720 cores (user portal hardware page). The portal total looks like it includes a few service or login nodes outside TOP500's ranked HPL partition of 76,320 cores; no single figure is recorded as verified.
Change history
- 2026-09-23 Added with a rank pointer on the edition where it ranked highest
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: 632 |
| top500.org | names system and part | NVIDIA A100 SXM4 40GB, 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.