Ivannikov Memorial Workshop

Biography

Professor Assaf Schuster has been a faculty member of the Technion Computer Science Department since 1991. He has been interested in various aspects of parallel and distributed computing, publishing more than 170 papers. His algorithms on data-race detection were implemented in Intel’s Thread Checker, and his patents on distributed shared memory were sold by the Technion. His papers triggered a rewrite of the Java Memory Model. He has built scalable production systems to handle petabytes of storage with off-the-shelf hardware. In recent years, his research group has focused on big data and scalable, real-time knowledge discovery in distributed data streams. From 2010, Prof. Schuster has also been working to establish TCE – the Technion Center for Computer Engineering, which he heads. TCE has grown to become a center of activity for about 60 faculty from the Technion and other universities in Israel and abroad, dozens of industry leaders, and hundreds of graduate students.

Abstract

Following some real-world trends, the computer sciences are also following with a slow process of focus changes. Instead of the one-time offline algorithms operating on stationary data, we now see a surge of interest in online processing of streaming data. Unfortunately, the algorithms and technologies for online stream processing are lagging behind and the gap can be estimated in years of research. In this talk I will focus on Complex Event Processing (CEP), an algorithmic field whose goal is to find interesting patterns in rapid streams of events (or data). CEP is an already an industry of billions of $$s and is growing very fast. I will show that state-of-the-art algorithmic methods for CEP are fairly primitive as compared with other algorithmic fields in computer science. I will then provide an overview of recent methods we developed in an effort to bridge the gap.

Biography

Vladimir Voevodin (born May 25, 1962, Moscow) is a computer scientist, professor at Lomonosov Moscow State University, the Faculty of Computational Mathematics and Cybernetics (MSU CMC) , Deputy Director of MSU Research Computing Center, corresponding member of the Russian Academy of Sciences,[1] Professor, Doctor of Science.

Research area

Parallel computing, mathematical methods for research of program fine structures, methods for description and analysis of computer architecture, parallel programming technology, program optimization methods for supercomputers and parallel computing systems, the Internet-based technology and organization of distributed computing, metacomputing.

Awards and honours

Vladimir Voevodin won MSU Shuvalov Prize for his series of papers "Analytical and practical methods for investigation of fine structure of applications" in 2000. He was awarded the Russian Federation Government Prize in education in 2002 and Lomonosov Prize for teaching activity in 2015. He is also Honoured Worker of Higher Education of the Russian Federation and a winner of Russian Federation President contest of grants for young Doctors of Science.

Biography

Yakobovsky Mikhail Vladimirovich - the deputy director for scientific work of Keldysh Institute of Applied Mathematics RAS, the corresponding member of RAS, the doctor of physical and mathematical sciences, professor.

Abstract

The report is devoted to discussion of the algorithms aimed at a possibility of use of perspective computing systems of exaFLOPS and higher performance level for mathematical modeling of problems of mechanics of the continuous environment. ExaFLOPS computing systems, in view of it is expected the short period of their no-failure operation, will demand qualitatively new decisions for providing the possibility of carrying out long calculations. The algorithms providing independence of time of carrying out calculation of emergence during calculations of refusals of computing knots are considered.

Biography

Alexey Khoroshilov - Associate professor of System programming of faculty of Calculus mathematics and cybernetics of MSU, leading researcher of ISP RAS.

Main scientific interests: design methods and development of responsible systems, the formal methods of program engineering, methods of verification and validation, testing on the basis of models, requirement analysis methods, the Linux operating system.

Main scientific results: an involvement in creation of technology of development of tests on the basis of the formal UniTESK models and tools supporting her, development of the unified architecture of a test set and rules of creation of extensions of programming languages for development of tests on the basis of contract specifications, development of methods of creation of tests for mathematical libraries, development of specialized technology of fast creation of tests of working capacity. Author and coauthor more than 50 scientific operations.

Biography

Andrey Belevancev is the leading researcher of ISP RAS, the area manager of the analysis and optimization of programs.

He participated and directed projects on optimization of the compilers GCC and LLVM, the static Svace analyzer, other tools of the analysis of programs for improvement of quality and overall performance. Gives lectures on CMS MSU. Area of scientific interests: static analysis of programs for search of mistakes, understanding of programs, dynamic analysis of programs, methods of optimization of programs, planning of teams, heterogeneous computing systems.

Biography

Denis Turdakov is a head of the department in ISP RAS. He manages research in the areas of natural language processing, machine learning, data mining, social networking analysis, big data.  Denis is a member of the program committee and a reviewer of a number of international CS conferences and author of more than 40 scientific papers. He was awarded the RAS Medal for young scientists.

Abstract

The presentation describes results of industrial projects and competences of the Information systems department of the ISP RAS. The research group specializes in a broad range of data management and information systems problems. Interests of Information systems department include the development of system software for data analysis, information extraction, database management systems, distributed data processing and cloud computing technologies. In addition, research group is developing algorithms for statistical data analysis and machine learning, as well as software for particular problems in applied fields. Presentation includes  description of ISP RAS software projects for intelligent text analysis (Texterra system) and social networks analysis (TALISMAN).

Biography

Leading researcher at The Institute for System Programming of the Russian Academy of Sciences, PhD. Head of Binary Code Reverse Engineering Team. Associate professor at Moscow State University. In 1999-2007 V.A. Padaryan participated in the creation of an IDE for parallel Java programs for distributed memory computing systems. Since 2007 he managed projects for the binary (executable) code security analysis methods and tools. He is the author of more than 60 publications. Research Interests: compiler technologies, static and dynamic binary code analysis, emulation and virtualization, computer security, high performance computing.

Abstract

The talk is dedicated to hot problems of binary code security analysis and state-of-the-art ISP RAS technologies in this area. Key challenges encountered by software security analysts searching for vulnerabilities are enumerated. The authors propose ideas that can respond to these challenges through adaptation of classic compiler technologies to solving computer security problems. Based on these ideas, ISP RAS has developed a line of technologies: deterministic replay of VM, VM introspection engine, binary code analysis environment, automatic preliminary lifting of representation level, and specialized intermediate representations tuned to automatically check real-world software for exploitable bugs and interactively reconstruct algorithm schemes step by step.