CLUSTERCluster · Standard CPU
- Operator / site
- San Diego Supercomputer Center
- Country
- United States
- Profile scope
- Standard CPU and GPU partitions
- Data checked
- 14 September 2026
- Operating system
- Rocky Linux
- Network topology
- Hybrid fat-tree
Expanse
San Diego Supercomputer Center
CPU Accelerator Interconnect
i
Reading this map
Expanse node architecture
Expanse is operated by San Diego Supercomputer Center in United States. This profile covers Standard CPU and GPU partitions. Specifications are listed below; anything the operator has not published is itemised in the documented-fields list.
Standard CPU
- Compute nodes of this type
- 728
- CPU model
- AMD EPYC 7742 · 64 cores
- CPU sockets per node
- 2
- Cores per socket
- 64
- Physical CPU cores
- 128
- Host / unified memory
- 256 GB DRAM
- Interface speed
- 100 Gb/s (HDR100 to compute nodes)
- Local storage
- 1 TB NVMe
- Form factor
- 13 SDSC Scalable Compute Units
V100 GPU
- Compute nodes of this type
- 52
- CPU model
- Intel Xeon Gold 6248 · 20 cores
- CPU sockets per node
- 2
- Cores per socket
- 20
- Physical CPU cores
- 40
- Accelerator model
- NVIDIA V100
- Physical accelerators per node
- 4
- Host / unified memory
- 384 GB DRAM
- Accelerator memory
- 32 GB per GPU
- Accelerator ↔ accelerator link
- NVLink
- Interface speed
- 100 Gb/s (HDR100 to compute nodes)
- Local storage
- 1.6 TB NVMe
Scope and uncertainty
Standard CPU and GPU partitions only. Four large-memory nodes are excluded from this profile pending detailed verification.
Documented fields: 23 / 40
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 — 2 / 3
- Manufacturer
- Ranked core count
- Theoretical peak (PFlop/s)
- Measured power (kW)
- Energy efficiency (GFlop/s per watt)
- Operating system
- Network topology
Standard CPU — 9 / 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
V100 GPU — 12 / 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