CLUSTERCluster · DGX A100 · 2022 first phase
- Operator / site
- Meta
- Country
- United States
- Profile scope
- January 2022 first-phase snapshot
- Data checked
- 14 September 2026
- Network topology
- Two-level Clos, no oversubscription
Meta Research SuperCluster
Meta
CPU Accelerator Interconnect
i
Reading this map
Meta Research SuperCluster node architecture
Meta Research SuperCluster is operated by Meta in United States. This profile covers January 2022 first-phase snapshot. Specifications are listed below; anything the operator has not published is itemised in the documented-fields list.
DGX A100 · 2022 first phase
Items marked ▧ come from the documented NVIDIA DGX A100 platform specification.
- System / node model
- NVIDIA DGX A100
- Compute nodes of this type
- 760
- CPU model
- AMD EPYC 7742
- CPU sockets per node
- 2
- Accelerator model
- NVIDIA A100
- Physical accelerators per node
- 8
- Accelerator ↔ accelerator link
- NVLink / NVSwitch
- On-node fabric
- NVLink 3 through NVSwitch, 600 GB/s GPU-to-GPU
- CPU ↔ accelerator link
- PCIe 4.0
- Network interfaces per node
- 8
- Interface model
- NVIDIA Quantum InfiniBand (1,600 Gb/s fabric)
- Interface-to-accelerator topology
- One adapter per GPU
- Form factor
- 6U rackmount
Scope and uncertainty
January 2022 first-phase snapshot: 760 DGX A100 systems / 6,080 GPUs. Later expansion plans are not counted as installed hardware. CPU and on-node links follow the documented DGX A100 platform; installed memory variant is not published. Node specifications follow the documented NVIDIA DGX A100 platform (6U rackmount); operator-specific deviations are not published.
Documented fields: 14 / 25
Every field this catalog checks. Fields listed above have a value; the remainder are shown here. A field marked absent is not publicly available in the sources we could verify, which does not mean the hardware is missing. Fields that cannot apply, such as benchmark results for an unranked system, are excluded from the total.
Cluster — 1 / 3
- Manufacturer
- Ranked core count
- Theoretical peak (PFlop/s)
- Measured power (kW)
- Energy efficiency (GFlop/s per watt)
- Operating system
- Network topology
DGX A100 · 2022 first phase — 13 / 22
- System / node model
- Compute nodes of this type
- CPU model
- CPU sockets per node
- Cores per socket
- Physical CPU cores
- CPU note
- Accelerator model
- Physical accelerators per node
- Host / unified memory
- Accelerator memory
- Accelerator ↔ accelerator link
- On-node fabric
- CPU ↔ accelerator link
- Network interfaces per node
- Interface model
- Interface speed
- Interface-to-accelerator topology
- Aggregate scale-out per node
- GPUDirect RDMA
- Management / storage networking
- Local storage
- NVMe data disks
- Max remote data disks
- Uncached disk IOPS
- Uncached disk throughput (MBps)
- Form factor