Venado node architecture
Venado is operated by DOE/NNSA/LANL in United States. This profile covers Ranked system / partition. Specifications are listed below; anything the operator has not published is itemised in the documented-fields list.
Published benchmark (TOP500 · June 2026)
- HPL rank
- #26
- HPL Rmax
- 98.51 PFlop/s
- Theoretical peak Rpeak
- 130.44 PFlop/s
- Ranked core count
- 481,440
- Measured power
- 1662 kW
- Energy efficiency
- 59.27 GFlop/s per watt
Cluster · Grace–Hopper (CG1)
- Operator / site
- DOE/NNSA/LANL
- Country
- United States
- Profile scope
- Ranked system / partition
- Data checked
- 14 September 2026
- Manufacturer
- HPE
- Ranked core count
- 481440
- Theoretical peak (PFlop/s)
- 130.44
- Measured power (kW)
- 1662
- Energy efficiency (GFlop/s per watt)
- 59.2719614921781
- Operating system
- Linux
Grace–Hopper (CG1)
Items marked ▧ come from the documented NVIDIA GH200 Grace Hopper Superchip platform specification.
- System / node model
- HPE Cray EX254n (Blanca Peak blade)
- Compute nodes of this type
- 640
- CPU model
- NVIDIA Grace · 72 cores
- CPU sockets per node
- 4
- Cores per socket
- 72
- Physical CPU cores
- 288
- Accelerator model
- NVIDIA GH200 Superchip
- Physical accelerators per node
- 4
- Host / unified memory
- 480 GB LPDDR5 (120 GB per socket)
- Accelerator memory
- 96 GB per GPU
- CPU ↔ accelerator link
- NVLink-C2C · 900 GB/s coherent CPU ↔ GPU
- Network interfaces per node
- 4
- Interface model
- HPE Cray Cassini (Slingshot 11)
- Interface speed
- 200 Gb/s per socket
- Interface-to-accelerator topology
- A dedicated Slingshot adapter per Grace Hopper superchip
Grace–Grace (C2)
Items marked ▧ come from the documented NVIDIA GH200 Grace Hopper Superchip platform specification.
- System / node model
- HPE Cray EX254n (Paradise blade)
- Compute nodes of this type
- 920
- CPU model
- NVIDIA Grace · 72 cores
- CPU sockets per node
- 2
- Cores per socket
- 72
- Physical CPU cores
- 144
- Host / unified memory
- 240 GB LPDDR5 (120 GB per socket)
- Network interfaces per node
- 2
- Interface model
- HPE Cray Cassini (Slingshot 11)
- Interface speed
- 200 Gb/s per socket
Scope and uncertainty
Venado has two partitions, which the ranking submission collapses into one entry. Both follow LANL presentation decks published through OSTI. Three figures are disputed and are recorded conservatively: the deck labels the accelerator "H200 with 96GB HBM2" while TOP500 names a GH200 Superchip, so only the 96 GB capacity is carried; LANL gives 3.4 and 3.45 GHz against TOP500's 3.1 GHz; and LANL writes the Slingshot rate as 200GB/s where Slingshot 11 ports are 200 Gb/s. The TOP500 core count of 481,440 does not reconcile with the partitions as published, which total 316,800 CPU cores. Network topology and node-local storage are not published for Venado. Node specifications follow the documented NVIDIA GH200 Grace Hopper Superchip platform (Superchip module — nodes per system and per-node superchip counts are operator-specific); operator-specific deviations are not published.
Documented fields: 31 / 44
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 — 6 / 7
- ✓Manufacturer
- ✓Ranked core count
- ✓Theoretical peak (PFlop/s)
- ✓Measured power (kW)
- ✓Energy efficiency (GFlop/s per watt)
- ✓Operating system
- ✕Network topology
Grace–Hopper (CG1) — 15 / 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
Grace–Grace (C2) — 10 / 15
- ✓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
Sources
Browse all cluster architecture pages →
CLUSTERATLAS