DGX SaturnV

Name: NVIDIA (undisclosed US site)
Address: USA

RSS for this system Your watchlist

Also known as NVIDIA DGX Saturn V

Operated by NVIDIA at NVIDIA (undisclosed US site) .

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: 4.00 PFlop/s
Rpeak: 7.41 PFlop/s
Rmax ÷ Rpeak: 54.0%
Cores: 87,040
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	- NVIDIA DGX-1, 124 nodes in the 2016 configuration	NVIDIA NVDANASDAQ	124 reported	Reported	nextplatform.com top500.org
Accelerator	NVIDIA Tesla P100 Accelerators CUDA (Pascal GP100) · 3,584C · 1.48 GHz · 16 nm · 300 W NVIDIA Tesla P100 SXM2, 992 GPUs (8 per DGX-1)	NVIDIA NVDANASDAQ	992 reported	Reported	nextplatform.com top500.org
Accelerator	NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA Tesla V100 (from the November 2021 TOP500 listing)	NVIDIA NVDANASDAQ	-	Reported	top500.org
CPU	- Xeon E5-2698v4 20C 2.2GHz	Intel INTCNASDAQ	-	Verified	top500.org nextplatform.com
Interconnect	Mellanox InfiniBand EDR Interconnect Fat tree · 100 Gb/s per 4x port · About 0.9 microseconds 100 Gb/s EDR InfiniBand, fat tree	Mellanox NVDANASDAQ rolls up to NVIDIA	-	Verified	top500.org nextplatform.com

The read

NVIDIA's in-house deep-learning cluster. In November 2016 it debuted at rank 29 on the TOP500 with 60,512 cores of Xeon E5-2698 v4, 3.31 PFlop/s Rmax and 349.5 kW, and topped the Green500 at 9.46 GFlops/W; The Next Platform describes it as 124 DGX-1 nodes with 992 Tesla P100 GPUs on EDR InfiniBand, used for self-driving-car, chip-defect and analytics work. TOP500's system page shows the same machine re-listed from November 2021 as a Tesla V100 system with 87,040 cores, 4.00 PFlop/s Rmax and 7.41 PFlop/s Rpeak, and it still appears at rank 354 in June 2026; those latest figures are recorded here. The V100 GPU count is not published, and a separate later 'Saturn V Volta' system (660 DGX-1V) was described in 2017 and is not covered by this row.

Timeline

2016-11 List debut at #29 (November 2016) source
2016-11 First operational source

Public list appearances

Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.

#29: TOP500, November 2016 →

Site & facility

NVIDIA (undisclosed US site)

Location: USA
Commissioned: 2020

nvidia.com

Change history

2026-10-01 Added DGX SaturnV (NVIDIA)

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
top500.org	names system and part	NVIDIA Tesla P100, NVIDIA Tesla V100, Mellanox InfiniBand EDR
nextplatform.com	names system and part	NVIDIA Tesla P100, NVIDIA Tesla V100, Mellanox InfiniBand EDR

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.