Modern big data workflows are characterized by computationally intensive kernels. The simulated results are often combined with knowledge extracted from AI models to ultimately support decision-making. These energy-hungry workflows are increasingly executed in data centers with energy-efficient hard-ware accelerators since FPG As are well-suited for this task due to their inherent parallelism. We present the H2020 project EVEREST, which has developed a system development kit (SDK) to simplify the creation of FPGA-accelerated kernels and manage the execution at runtime through a virtualization environment. This paper describes the main components of the EVEREST SDK and the benefits that can be achieved in our use cases.

Abstract Web search is a crucial technology for the digital economy. Dominated by a few gatekeepers focused on commercial success, however, web publishers have to optimize their content for these gatekeepers, resulting in a closed ecosystem of search engines as well as the risk of publishers sacrificing quality. To encourage an open search ecosystem and offer users genuine choice among alternative search engines, we propose the development of an Open Web Index (OWI). We outline six core principles for developing and maintaining an open index, based on open data principles, legal compliance, and collaborative technology development. The combination of an open index with what we call declarative search engines will facilitate the development of vertical search engines and innovative web data products (including, e.g., large language models), enabling a fair and open information space. This framework underpins the EU‐funded project OpenWebSearch.EU, marking the first step towards realizing an Open Web Index.

Today digital revolution is having a dramatic impact on the pharmaceutical industry and the entire healthcare system. The implementation of machine learning, extreme-scale computer simulations, and big data analytics in the drug design and development process offers an excellent opportunity to lower the risk of investment and reduce the time to the patient.

SUMMARY: Access pathways in enzymes are crucial for the passage of substrates and products of catalysed reactions. The process can be studied by computational means with variable degrees of precision. Our in-house approximative method CaverDock provides a fast and easy way to set up and run ligand binding and unbinding calculations through protein tunnels and channels. Here we introduce pyCaverDock, a Python3 API designed to improve user experience with the tool and further facilitate the ligand transport analyses. The API enables users to simplify the steps needed to use CaverDock, from automatizing setup processes to designing screening pipelines. AVAILABILITY AND IMPLEMENTATION: pyCaverDock API is implemented in Python 3 and is freely available with detailed documentation and practical examples at https://loschmidt.chemi.muni.cz/caverdock/.

Developing and optimizing software applications for high performance and energy efficiency is a very challenging task, even when considering a single target machine. For instance, optimizing for multicore-based computing systems requires in-depth knowledge about programming languages, application programming interfaces (APIs), compilers, performance tuning tools, and computer architecture and organization. Many of the tasks of performance engineering methodologies require manual efforts and the use of different tools not always part of an integrated toolchain. This paper presents Pegasus, a performance engineering approach supported by a framework that consists of a source-to-source compiler, controlled and guided by strategies programmed in a Domain-Specific Language, and an autotuner. Pegasus is a holistic and versatile approach spanning various decision layers composing the software stack, and exploiting the system capabilities and workloads effectively through the use of runtime autotuning. The Pegasus approach helps developers by automating tasks regarding the efficient implementation of software applications in multicore computing systems. These tasks focus on application analysis, profiling, code transformations, and the integration of runtime autotuning. Pegasus allows developers to program their strategies or to automatically apply existing strategies to software applications in order to ensure the compliance of non-functional requirements, such as performance and energy efficiency. We show how to apply Pegasus and demonstrate its applicability and effectiveness in a complex case study, which includes tasks from a smart navigation system.

High-Performance Big Data Analytics (HPDA) applications are characterized by huge volumes of distributed and heterogeneous data that require efficient computation for knowledge extraction and decision making. Designers are moving towards a tight integration of computing systems combining HPC, Cloud, and IoT solutions with artificial intelligence (AI). Matching the application and data requirements with the characteristics of the underlying hardware is a key element to improve the predictions thanks to high performance and better use of resources. We present EVEREST, a novel H2020 project started on October 1, 2020, that aims at developing a holistic environment for the co-design of HPDA applications on heterogeneous, distributed, and secure platforms. EVEREST focuses on programmability issues through a data-driven design approach, the use of hardware-accelerated AI, and an efficient runtime monitoring with virtualization support. In the different stages, EVEREST combines state-of-the-art programming models, emerging communication standards, and novel domain-specific extensions. We describe the EVEREST approach and the use cases that drive our research.

The ANTAREX project developed an approach to the performance tuning of High Performance applications based on an Aspect-oriented Domain Specific Language (DSL), with the goal to simplify the enforcement of extra-functional properties in large scale applications. The project aims at demonstrating its tools and techniques on two relevant use cases, one in the domain of computational drug discovery, the other in the domain of online vehicle navigation. In this paper, we present an overview of the project and of its main achievements, as well as of the large scale experiments that have been planned to validate the approach.

Designing and optimizing applications for energy-efficient High Performance Computing systems up to the Exascale era is an extremely challenging problem. This paper presents the toolbox developed in the ANTAREX European project for autotuning and adaptivity in energy efficient HPC systems. In particular, the modules of the ANTAREX toolbox are described as well as some preliminary results of the application to two target use cases. 1

The ANTAREX project relies on a Domain Specific Language (DSL) based on Aspect Oriented Programming (AOP) concepts to allow applications to enforce extra functional properties such as energy-efficiency and performance and to optimize Quality of Service (QoS) in an adaptive way. The DSL approach allows the definition of energy-efficiency, performance, and adaptivity strategies as well as their enforcement at runtime through application autotuning and resource and power management. In this paper, we present an overview of the ANTAREX DSL and some of its capabilities through a number of examples, including how the DSL is applied in the context of one of the project use cases.

International audience

Robot Soccer is a very attractive platform in terms of research. It contains a number of challenges in the areas of robot control, artificial intelligence and image analysis. This article presents a look at the overall architecture of the game and describes some results of our experiments in analysis and optimization of strategies using sequence extraction. We have extracted sequences of game situations from the log of a game played in our simulator, as they occurred during the game. Afterwards, these sequences were compared by methods LCS, LCSS and T-WLCS, which are usually used for sequence comparison in the sequence alignment area. Using these methods, we are able to visualize the relations between the sequences of game situations and clusters of similar game situations in a graph. In conclusion, a possible description improvement of these game situations is introduced. Therefore, a possible strategy improvement to ensure a smoother and faster performing of actions defined by these situations is described.

Extraction of social networks from log files and social network analysis then requires the usage of data mining methods focused on areas such as data clustering or pattern mining. Our research is focused on log files where one log file attribute is an originator of the recorded activity and the originator is also a person. Hence, based on the similar attributes of people, we are able to construct models which explain certain aspects of a persons behaviour. Moreover, we can extract user profiles based on person behaviour in the web applications. Working with large user profiles, usually acquired from the web log files, the dimension reduction from original high dimensional space to 2D space could be done using Kohonen SOM. The SOM also provides clusters of similar web profiles of particular users. For large SOM learning it is appropriate to use parallel computing environment. Our version of scalable parallel SOM learning algorithm and experiment with web user profiles are presented in this paper.

Strategy is a kernel subsystem of the robot soccer game. According to the strategy description in our work, there are loop strategies which are likely to get robots in a trap of executing repeated actions. In this paper, we propose method using eigenvalues to judge the existence of loop strategies in our rules set. We present the concept of condition-decision relation matrix by which the loop strategies can be found, too. The experiment illustrates our method.

Spectral clustering is a data mining method used for finding patterns in high dimensional datasets. It has been applied effectively to solve many problems in signal processing, bioinformatics, etc. In this paper spectral clustering was implemented to find students’ patterns of behavior in an elearning system, to explore the relationship between the similarity of students’behavior and their academic performance.

Human activities are contributing to more frequent natu- ral extremes and climate change, which also come from the atmosphere, water or the Earths crust. With the in- creasing development of infrastructure, the impacts of these changes and extremes leave more perceivable dam- age and increasing loss of lives and property. With the use of modern resources and technology we are able to minimize the impact of these extreme phenomena. There are in fact two main approaches professional and non- professional both meant from the aspect of data collec- tion and information processing itself. The advantages of social networks have been increasingly utilized dur- ing the natural disasters as a way of communicating im- portant information. This article describes the aim of our research to create a hybrid system which would both enable the collection of data from the professional and non-professional public as well as communicate with other types of systems, to utilize and then process the data and use the data to predict new dangers. The prin- ciple is based on collecting data (knowledge, experience, etc.) from both main approaches to disaster management (professional and nonprofessional) and then applying this information to achieve new solutions. The practical ap- plication of a DIP system shows that it can be used for describing the risk of future natural disasters and enables us to deduce the threat imposed by them. Analyzing this data can help create new solutions in the fight to mini- mize the damage incurred by these disasters. INTRODUCTION Climate change as well as the occurrence of natural ex- tremes, whose sources come from the atmosphere, water or even the Earths crust, are the results of the natural vari- ability of the atmosphere and the evolution of the Earth. These continual changes, caused not only by natural pro- cesses, are increasingly influenced by human activities. In natural ecosystems, these changes and extremes, in- cluding their occurrences and effects, are part of their natural development. But with the increasing develop- ment of infrastructure these changes and extremes leave more perceivable damage, i.e. loss of lives and property. Ecosystems and human society are both getting grad- ually equipped to adapt to recent and current climate. But there are fears that further adaptation to accelerat- ing changes will be much more difficult. In a short time it can have big consequences for the fundamental values of life, the food or water system or public health, espe- cially in many underdeveloped and economically disad- vantaged countries. For almost all of the world there is an increased risk of extreme weather, with subsequent in- creased risk of disasters associated with them. As stated by the World Meteorological Organization, over the past 30 years, nearly 7500 natural disasters worldwide took the lives of more than two million people. Of that 72.5 percent of the disasters were caused due to weather, cli- mate change or water hazards. In the context of the ongoing process of global warming and global climate change, the question arises to what extent these changes affect meteorological and hydrological extremes causing floods. Floods are one of the most significant natural ex- tremes in the Czech Republic, and are largely the result of anthropogenic factors, as well as meteorological and physical-geographical factors. Anthropogenically burProceedings 24th European Conference on Modelling and Simulation ©ECMS Andrzej Bargiela, Sayed Azam Ali David Crowley, Eugene J.H. Kerckhoffs (Editors) ISBN: 978-0-9564944-0-5 / ISBN: 978-0-9564944-1-2 (CD) dened landscape is losing its ability to maintain stability and dynamic balance. We may not be able to control the winds and rains yet, but in the modern era we fortunately have new tools and kinds of technology, which give us the opportunity to minimize the impact of these extreme phenomena. For example, by providing relevant and comprehensive infor- mation for decision support, i.e. creating forecasts for the situation, with the aim of limiting the adverse effects of natural phenomena and their consequences through mod- ern computer and internet technologies. These activities can be supported by both professionals and nonprofes- sionals in the field, as well as by various levels of public safety administrations, and may reveal solutions for deal- ing with future disasters. In fact there are two main approaches to disaster man- agement meant from the aspect of data collection and in- formation processing itself. On the one hand there are some systems which enable the entry of data relative to disaster management and make it possible to trace it af- terwards (NEDIES, 2010). These systems are very gen- eral and have almost no specialization. They are at the level of chronicles or encyclopedias. There are even sys- tems, which, through the combination of GPS and mo- bile phone applications, allow for the entry of informa- tion about the events right from the location (Ohya et al., 2007). Often these are only data storages which are pub- licly accessible but with no other use. On the other hand, there are models individually spe- cialized for each natural phenomenon floods (Von- drak el al., 2008), landslides etc., possibly for prescrip- tions and methodologies of how to integrate more mis- cellaneous models and to create joint interface such as OpenMI (Gregersen et al., 2007). Nevertheless, these systems are not publicly accessible. Our aim was to create a hybrid system which would both enable the collection of data from the professional and non-professional public, and would be capable of communicating with the other types of systems, to utilize and process their data, and on the basis of this collected data would be capable of predicting new dangers. Through research it was found out that advantages of social networks have been more and more utilized during natural disasters as a way of communicating important information (Palen et al., 2007). That information can be broadcasted quicker than by way of other news media. Faster communication of information could be the key point for protecting or even saving the lives of the people living in the area affected by a disaster. It could seem that information provided by people in social networks may not be exact or reliable, but in the fact it is just the opposite. News coming from the admin- istration authorities and big news media are often delib- erately distorted (Palen et al., 2007). But it is not only because of that that social networks can help during the crises; they can help to bring people together through the flow of intensive information, and people can solve the problems together and also better resist the catastrophes and recover from their effects (Palen et al., 2007). Be- sides social networks such as Facebook, Twitter, MyS- pace and others that are used to that purpose, there is also the emergence of social networks specifically designed for crisis situations. The first example of them is the social network IGLOO (IGLOO, 2007) which together with its members com- ing from more than 200 countries and the global connec- tion of varied organizations aiming to solve complicated problems. Recently this network has connected more than 200,000 research workers, academics and special- ists from various spheres including education and admin- istration worldwide. Thus, it improves communication and co-operation which results in the better effectiveness of the crisis management and of Rotary’s reaction to the natural disasters. Another social network is the Gustav Information Cen- ter, which was created in the days when Hurricane Gus- tav was approaching the Gulf of Mexico. This social net- work provided people with the necessary information to assist in organizing the help of volunteers and also in the evacuation of people before the storm. The network in- cluded links to other resources, as well as lists of volun- teers, evacuation routes, blogs, photos and videos from the Gulf Coast, and many more resources to help during the hurricane (Edwards et al., 2009). Microblogging and the Microsoft Vine warning sys- tem are other tools which will help to predict disasters such as Hurricane Katrina, earthquakes, pandemics or to manage critical and emergency situations of any kind (MS Vine, 2010). People will choose the field of certain problems and then they will be informed by way of short status messages and security alerts by using either a Vine desktop client or via email. The client will be able to link-up with Facebook and Twitter and will also have the opportunity to monitor the location of his or her relatives on a map background in a similar manner as Google Lat- itude function in mobile Google Maps for smart phones. Vine is currently available only in America. It should be a sort of system of last communication, which people would use to communicate with family when the tele- phone or mobile network fails (MS Vine, 2010).

Floods are the most frequent natural disasters affecting the Moravian-Silesian region. Therefore a system that could predict flood extents and help in the operative disaster management was requested. The FLOREON system was created to fulfil these requests. This article describes utilization of HPC (high performance computing) in running multiple hydrometeorological simulations concurrently in the FLOREON system that should predict upcoming floods and warn against them. These predictions are based on the data inputs from NWFS (numerical weather forecast systems) (e.g. ALADIN) that are then used to run the rainfall-runoff and hydrodynamic models. Preliminary results of these experiments are presented in this article.

The robot soccer game, as a part of standard applications of distributed system control in real time, provides numerous opportunities for the application of AI. Real-time dynamic strategy description and strategy learning possibility based on game observation are important to discover opponent’s strategies, search tactical group movements and synthesize proper counter-strategies. In this paper, the game is separated into physical part and logical part including strategy level and abstract level. Correspondingly, the game strategy description and prediction of ball motion are built up. The way to use this description, such as learning rules and adapting team strategies to every single opponent, is also discussed. Cluster analysis is used to validate the strategy extraction.