Ada Cloud
ADA CLOUD
ADA is the HPC Cloud platform of the Fenix infrastructure, deployed within the Tier-1 GALILEO100 supercomputing ecosystem in 2021 as part of the ICEI Human Brain Project. It was designed to provide a flexible and powerful cloud environment capable of supporting complex scientific workflows that require interactive computing, customized software stacks, cloud-native services, and integration with traditional HPC simulations.
System Architecture
The CINECA HPC cloud infrastructure, named ADA cloud is based on OpenStack Zed.
OpenStack Nodes
- 71, CPU-only, interactive OpenStack nodes each with 2 x CPU Intel CascadeLake 8260, with 24 cores each, 2,4 GHz, 768GB RAM and 2TB SSD storage.
- 5, GPU equipped, interactive OpenStack nodes each with 2 x GPU Nvidia V100 (Volta) PCIe3 with 32 GB RAM per node and the same CPU and storage specifics as the CPU-only nodes.
All OpenStack interactive nodes have Hyperthreading x2 enabled.
Storage
- 1 PB Ceph storage raw dedicated (full NVMe/SSD)
This cloud infrastructure is tightly connected both to the LUSTRE storage of 20 PB raw capacity, and to the GSS storage of 6 PB seen by all other infrastructure. This setup enables the use of all available HPC systems (Tier-0 Marconi, Tier-1 Galileo100), addressing HPC workloads in conjunction with cloud resources.
ADA CLOUD
Model: Dual-Socket Dell PowerEdgeCloud
Platform: OpenStack version Wallaby
Internal Network: Ethernet 100GbE
Nodes: 68 Cloud compute
Processors: 2xCPU 8260 Intel CascadeLake (24c, 2.4Ghz)
Cores: 48 cores/node, Hyperthreading x2
RAM: 768GB DDR4
+
Nodes: 3 Cloud controller
Processors: 2xCPU 8260 Intel CascadeLake (24c, 2.4Ghz)
Cores: 48 cores/node, Hyperthreading x2
RAM: 768GB DDR4