"VU HPC" Saulėtekis location
BullSequana X1000 GPU cluster of supercomputer “VU HPC Saulėtekis”.
There are 64 compute cores per node with AVX-512, AVX2 AVX, SSE4.2 processor instructions; 4 Tesla V100 GPU cards, 376 GB RAM. Nodes connect IB networks. Expected physical availability of compute nodes: 50%.
Nodes connect 100 Gbps speed IB networks with other nodes cluster nodes and clusters.
The entire system uses a high-performance file system: 46TB (100 Gbps speed on the IB network) and 289 TB (40 Gbps speed on the IB network). Maximum file size for a task is 200TB.
Task queues: SLURM
Operating system: Red Hat Enterprise Linux 8.4 release
Architecture: Sequana X1000.
Possibilities of use:
OpenMP and MPI type calculations with NVidia GPU technology choosing the amount of nodes, cores and memory required for the task, in a Linux RHEL8 environment.
BullSequana X1000 cluster of supercomputer “VU HPC Saulėtekis”.
Total maximum utilization of 143 compute nodes per task (one node has 64 compute cores with AVX-512, AVX2 AVX, SSE4.2 CPU instructions, 376 GB RAM). Expected physical availability of computing nodes: 80%.
Nodes connect 100 Gbps speed IB networks with other nodes cluster nodes and clusters.
The entire system uses a high-performance file system: 46TB (100 Gbps speed on the IB network) and 289 TB (40 Gbps speed on the IB network). Maximum file size for a task is 200TB.
Task queues: SLURM
Operating system: Red Hat Enterprise Linux 8.4 release
Architecture: Sequana X1000.
Possibilities of use:
OpenMP and MPI-like computations for task-selecting node cores and memory amounts in a Linux RHEL8 environment. Virtual machine with Windows environment according to special needs.