Shakti Cloud · XE9680 node architecture
Shakti Cloud · XE9680 is operated by Shakti Cloud, Yotta Data Services Private Limited in India. 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
- #32
- HPL Rmax
- 84.31 PFlop/s
- Theoretical peak Rpeak
- 102.82 PFlop/s
- Ranked core count
- 294,336
Cluster · PowerEdge XE9680 · public profile
- Operator / site
- Shakti Cloud, Yotta Data Services Private Limited
- Country
- India
- Profile scope
- Ranked system / partition
- Data checked
- 14 September 2026
- Manufacturer
- DELL
- Ranked core count
- 294336
- Theoretical peak (PFlop/s)
- 102.82
- Operating system
- Ubuntu 22.04
PowerEdge XE9680 · public profile
Items marked ▧ come from the documented Dell PowerEdge XE9680 platform specification.
- System / node model
- PowerEdge XE9680
- CPU model
- Xeon Platinum 8480L 56C 2GHz
- CPU sockets per node
- 2
- Accelerator model
- NVIDIA H100 80GB
- Physical accelerators per node
- 8
- Accelerator memory
- 80 GB per accelerator
- Form factor
- 6U rack server · 6 power supply units (5+1 redundant)
Scope and uncertainty
Yotta publishes per-node figures for purchasable H100 SKUs but nothing scoped to the ranked cluster, and its own pages disagree between the bare-metal listing and the virtualised product. Its platform-wide "16,384 H100 GPUs" covers the whole estate. None of those figures is recorded as this system's configuration; accelerators per node follow the documented Dell PowerEdge XE9680 chassis. Node specifications follow the documented Dell PowerEdge XE9680 platform (6U rack, two sockets, eight accelerators); operator-specific deviations are not published.
Documented fields: 11 / 29
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 — 4 / 7
- ✓Manufacturer
- ✓Ranked core count
- ✓Theoretical peak (PFlop/s)
- ✕Measured power (kW)
- ✕Energy efficiency (GFlop/s per watt)
- ✓Operating system
- ✕Network topology
PowerEdge XE9680 · public profile — 7 / 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
Sources
Browse all cluster architecture pages →
CLUSTERATLAS