HSE cHARISMa Supercomputer Completes One Million Tasks
Since 2019, the cHARISMa supercomputer has been helping staff, teachers and students of HSE university to solve research tasks. In February 2023, it completed its millionth task—a computational experiment dedicated to studying the phenomenon of multiparticle localisation in quasi-one-dimensional quantum systems.
The experiment was conducted by HSE graduate student Murod Bakhovadinov at the Joint Department of Condensed Matter Physics with the Institute of Solid State Physics (RAS) together with the Laboratory for Condensed Matter Physics.
The HSE cHARISMa supercomputer (Computer of HSE for Artificial Intelligence and Supercomputer Modeling) is one of the most powerful supercomputer complexes in Russia.
To ensure the stable operation of complex computing equipment, the staff of the Supercomputer Modeling Unit develop tools to ensure ease-of-use of the computer. For example, in 2021, the JupyterHub service was introduced to simplify the preparation of computational tasks in the field of artificial intelligence, and in 2022, the innovative HPC TaskMaster software system was developed and implemented to assess task effectiveness.
Completing the millionth task on the supercomputer is a significant event for our team. Every day we carry out work to maintain, develop, and optimise the supercomputer. As a result, HSE University’s computing complex is technologically one of the most advanced in Russia today.
In what areas can the cHARISMa Supercomputer be applied?
The HSE cHARISMa Supercomputer helps scientists conduct research in various fields of science.
A popular field for applying supercomputer resources is the training of deep artificial neural networks.
These tasks concern the creation of artificial intelligence. Even those who are far from the field of computer technology have noticed the impact of the new neural networks Midjourney and ChatGPT on humanity. Training such artificial intelligence requires computational performance that only supercomputers have. Many HSE departments are engaged in research in the field of artificial intelligence, but the Faculty of Computer Science implements most research projects in this field.
A supercomputer allows you to study space faster.
Whether calculating the location of new planets or detecting anomalies in the movement of cosmic bodies, the supercomputer processes huge amounts of data received from telescopes in seconds. This saves decades of scientists' work. Each study requires the development of its own program that will help to operate the data.
Supercomputers are an important tool for studying living systems.
For example, HSE researchers conducted extensive studies of the COVID-19 genome together with specialists from the A.A. Smorodintsev Research Institute of Influenza, the Kharkevich Institute for Information Transmission Problems of the Russian Academy of Sciences, and Skoltech. With the help of cHARISMa, the researchers compared and analysed mutations of more than 200 Covid-19 genomes from patients from 25 Russian regions. And it was found that most of the new strains originated in European countries, and not in China.
The Human Brain
Artificial intelligence allows you to find flaws in the human brain.
Supercomputers help to study the human brain and identify the mechanisms that control human behaviour and perception. With the help of cHARISMa, researchers of the Centre for Cognition & Decision Making of the HSE Institute for Cognitive Neuroscience have studied the role of the prefrontal and parietal cortex of the human brain in decision-making and have published numerous academic papers on this topic.
The Educational Process
The supercomputer also helps solve tasks in the educational process.
More than 250 HSE students study supercomputing technologies on world-class equipment, gaining relevant skills for their future careers and research activities.
‘The cHARISMa supercomputer will continue to solve the most difficult tasks around the clock, expanding the boundaries of science, working for the benefit of the university and our whole country,’ says Pavel Kostenetskiy.
Whether researching how the human brain works, identifying the source of COVID-19, running complex calculations or testing scientific hypotheses, supercomputers can help us solve the most complex tasks. One of the most powerful supercomputers in the CIS is cHARISMa, which is now in its third year of operation at HSE University. Pavel Kostenetskiy, Head of the HSE University Supercomputer Modeling Unit, talks about how the supercomputer works and what kind of projects it works on.
The peak performance of the HSE cHARISMa supercomputer has doubled, reaching 2 petaflops (2 quadrillion floating-point operations per second). HSE University now outperforms the Kurchatov Institute in terms of computing power. The only more powerful university computers are MSU’s Lomonosov-2 and SPbPU’s Polytechnic. Thanks to the timely upgrade, cHARISMa has retained its respectable 6th position among the Top 50 most powerful computer systems in the CIS for three years.
Researchers from the HSE International Laboratory for Supercomputer Atomistic Modelling and Multi-scale Analysis, JIHT RAS and MIPT have compared the performance of popular molecular modelling programs on GPU accelerators produced by AMD and Nvidia. In apaper published by the International Journal of High Performance Computing Applications, the scholars ported LAMMPS on the new open-source GPU technology, AMD HIP, for the first time.
In July this year, there was an open vote to name the HSE’s supercomputer. Two names - Corvus (‘crow’ in Latin; the crow is HSE's mascot) and cHARISMa (Computer of HSE for Artificial Intelligence and Supercomputer Modelling) – received the most votes. The latter won by a narrow margin, with 441 people (one in three of those who took part in the vote) choosing this name.
A new supercomputer, which has been recently set up at MIEM, will allow the university to carry out high quality research in deep learning and mathematical modeling. The computer was ranked sixth in the April Top-50 ranking of supercomputers in Russia.