The Bianca Cluster
Bianca is a research system dedicated for analyzing sensitive personal data. Bianca is part of the NAISS-SENS project.
Bianca provides each project with a virtualized "UPPMAX cluster environment" utilizing OpenStack as virtualization platform.
Bianca provides 4480 cores in the form of 204 dual CPU (Intel Xeon E5-2630 v3) Huawei XH620 V3 nodes with 128GB memory, 75 "fat" nodes have 256 GB of memory, 15 nodes with 512 GB of memory, and ten nodes with two NVIDIA A100 40GB GPUs each.
We have the SweGen/1000 Genomes dataset as well as UKBB institutional genetics dataset available, as well as other common datasets. See accessing swegen and our data page for details for requesting access.
Since Bianca is designed to handle sensitive personal data security is a key aspect of the configuration. In order to ensure that the data is safe we have implemented a series of security measures including, but not limited to:
- One virtualized cluster per project, no resources are shared between projects.
- Separate storage volumes per project.
- Detailed logging of file transfers in and out of the cluster.
- Two factor authentication
- No internet access inside the clusters.
- Locked racks for the hardware
- Destruction of broken hard drives
Uppsala University has decided on the following KRT classifications for Bianca:
- 321 for project directories
- 322 for home directories
- 204 compute nodes with single or dual CPUs and one 4TB mechanical drive or 1TB SSD
- Each CPU has 8 cores
- 75 compute nodes, 256 GB memory each.
- 15 compute nodes, 512 GB memory each
- 10 compute nodes each equipped with 2xNVIDIA A100 (40GB) GPUs
- Total number of CPU cores is 4800
- Login nodes have 2vCPU each and 16GB memory
- Dual 10 Gigabit Ethernet for all nodes