Supercomputer "VU HPC Saulėtekis" cluster BullSequana X1000

Unit: Faculty of Physics

Keywords: Supercomputer, cluster BullSequana X1000

Responsible person: Dr. Mindaugas Mačernis, +370 5 236 6049

Distributed memory cluster.

 In total, the maximum utilization is 143 computing nodes per task (one node contains 64 computational cores with the processor instructions AVX-512, AVX2 AVX, SSE4.2, 376 GB of RAM). The expected physical availability of computing nodes: 80%.

Nodes are connected by an IB network with a speed of 100 Gbps with other nodes of the cluster nodes and clusters.

The entire system uses high-performance file systems: 46TB (100 Gbps speed in the IB network) and 289 TB (40 Gbps speed in the IB network). The maximum file size for the task is 200TB.

Task queues: SLURM
Operating System: Red Hat Enterprise Linux release 8.4

Architecture: Sequana X1000.

 

Applicability

OpenMP and MPI type
calculations while selecting the number of nodes, cores, and memory required for the task in the Linux RHEL8 environment. A virtual machine with a Windows environment according to special needs.