High Performance Computing Center

High Performance Computing Center

RTU High Performance Computing (HPC) Center or Research Computing Center is an initiative under supervision of the Office of Vice-Rector for Research, which aims at providing support to application of e-science technologies in research, that is:

  • To ensure access to RTU HPC cluster (supercomputer);
  • To provide technical support to transfer of computing tasks to HPC;
  • To ensure research software for research and educational purposes;
  • To organize training and seminars.

HPC allows solving complicated computing tasks in a short period of time. Computing is carried out on high-performance computers (shared memory mainframe, computing cluster) made from many parallel processors. Modern HPC is an essential element of any contemporary university, it is used for various purposes ranging from solving engineering tasks in Mathworks MATLAB environment to Big Data analysis and machine learning.  

The majority of HPC systems, including the one available at RTU, are designed as computing clusters, which consist of numerous separate servers connected to one fast computer network (Infiniband). HPC cluster can be used for both parallel computing, providing parallel execution of a large task, and distributed computing, performing several independent tasks on separate servers or processor. RTU HPC cluster is additionally equipped with modern NVidia Tesla graphic accelerator (GPU). General technical specifications:

  • Number of computer cores: 732
  • Total memory: 2.6 TB
  • Data storage: 238 TB
  • Number of graphic processing units: 14
  • Total system performance: 35 TFLOPS

Services of HPC Center are available to any student of faculty member of RTU, we are also open for cooperation with other organizations. More information available at RTU HPC Center homepage.

HPC Center was established in June 2012 as a follow up to computing activities initiated by FP6 and FP7 projects BalticGrid I & II.