June 17, 9.00-10.00
Kathryn S McKinley, Senior Staff Researcher, Google Cloud
Title: Capacity Efficiency in the Cloud
Abstract: The promise of cloud computing is affordable, available, and secure computing resources managed by experts. To achieve this promise, providers face end-to-end challenges, from efficiently running customer virtual machines (VM) on multicore hardware to mapping VM workloads to machines to predicting workloads and growth. Improving VM performance and packing, even by 1%, directly reduce capacity requirements and thus data center costs. This talk overviews analysis and kernel tracing tools that Google uses to optimize performance, understand workloads, limit resource stranding, and dynamically verify mitigations to recent Intel hardware speculation errors. It highlights optimization opportunities, showing many workloads change slowly over time, but unpredictable bursts and new workloads are common.
After technical questions, I will show how myths, such as the sole genius, are counter productive to science and innovation. In contrast, social science shows diverse teams achieve better outcomes in controlled and uncontrolled studies. I will put these results in the context of my personal research experiences. I challenge you to build diverse research teams and mentor the next generation, so that your team will produce more innovative work.
Bio: Kathryn S. McKinley is a Senior Staff Research Scientist at Google (2017-present). She received her BA, MS, and PhD from Rice University. Her research interests span programming languages, compilers, runtime systems, operating systems, cloud systems, and architecture with a focus on performance, parallelism, and memory systems. She and her collaborators have produced software systems widely used in industry and academia: the DaCapo Java Benchmarks (31,800+ downloads), the TRIPS Compiler, the Hoard memory manager (used by OS X), the MMTk memory management toolkit, the Immix garbage collector (in Jikes RVM, Haxe, Rubinius, and Scala), incremental parallelism in Bing, and the SHIM profiler. Her research papers have garnered five historical impact awards and ten were recognized with best conference and best in area awards. She has graduated 22 PhD students. She and her husband have three sons. Dr. McKinley is an IEEE Fellow and ACM Fellow.
June 18, 9.00-10.00
Indranil Gupta, Professor, & Associate-Head, Department of Computer Science, University of Illinois, Urbana-Champaign
Title: The Future of Technology Will Not Be Technological…
Abstract: Distributed Systems designers and builders excel at addressing the goals of scale, reliability, security, and fault-tolerance. These challenges are however only a subset of a much broader set of needs and wants that users have from computer systems. This talk will attempt to show how these broader goals could serve as a source of innovative avenues and exciting new problems for distributed systems research.
Bio: Indranil Gupta (Indy) is a Professor of Computer Science at the University of Illinois at Urbana-Champaign, and Associate-Head of the department. He works on all interesting problems in the distributed systems arena, ranging from algorithms to implementation to production systems, and in multiple areas including cloud and cluster computing, P2P systems, IoT, machine learning, and many others. He won the NSF CAREER Award in 2005; best paper awards at IEEE IC2E 2018, IEEE/ACM CCGrid 2017, IEEE IC2E 2016, IEEE ICAC 2015, BigMine 2012; and several teaching awards at Illinois. He has participated in multiple industry production systems, and his work has been adopted by companies small to large. He has previously worked at Microsoft Research, IBM Research, and Google.
June 19, 9.00-10.00
Patrizio Pelliccione, Associate Professor at Chalmers | University of Gothenburg (Sweden) and University of L’Aquila (Italy)
Title: Software Engineering for ML/AI
Abstract: ML and AI are increasingly dominating the high-tech industry. Organizations and technology companies are leveraging their big data to create new products or improve their processes to reach the next level in their market. However, ML and AI are not a silver bullet and Software 2.0 is not the end of software developers or software engineering.
In this talk I will argument on how software engineering can help ML and AI to become the key technology for (autonomous) systems of the near future. Software engineering best practices and achievements reached in the last decades might help, e.g., (i) democratising the use of ML/AI, (ii) composing, reusing, chaining ML/AI models to solve more complex problems, and (iii) supporting for reasoning about correctness, repeatability, explainability, traceability, fairness, ethics, while building an ML/AI pipeline.
Bio: Patrizio Pelliccione is Associate Professor at the Department of Computer Science and Engineering at Chalmers | University of Gothenburg (Sweden) and Associate Professor at the Department of Information Engineering, Computer Science and Mathematics – University of L’Aquila (Italy) – double affiliation. He got his PhD in 2005 at the University of L’Aquila (Italy) and from February 1, 2014 he is Docent in Software Engineering, title given by the University of Gothenburg (Sweden). His research topics are mainly in software engineering, software architectures modelling and verification, autonomous systems, and formal methods. He has co-authored more than 130 publications in journals and international conferences and workshops in these topics. He has been on the program committees for several top conferences, he is a reviewer for top journals in the software engineering domain, and he organized as program chair international conferences like ICSA2017 and FormaliSE 2018. He is very active in European and National projects. He is the PI for Co4Robots (http://www.co4robots.eu/) H2020 EU project for the University of Gothenburg and he is active researcher and Software Technology cluster co-leader of WASP (https://wasp-sweden.org/). In his research activity he has collaborated with several industries such as Volvo Cars, Volvo AB, Ericsson, Jeppesen, Axis communication, Systemite AB, Thales Italia, Selex Marconi telecommunications, Siemens, Saab, TERMA, etc. More information is available at http://www.patriziopelliccione.com.
June 19, 15.30-16.15
Robert Szabo, Master Researcher, Cloud Systems and Platforms, Ericsson Research, Ericsson (Hungary)
Title: End-to-end orchestration automation in distributed cloud: resource, service and multi-stakeholders aspects
Abstract: Edge computing provides compute and storage resources with adequate connectivity (networking) close to the devices generating / terminating traffic. The benefit is the ability to provide new services with strict requirements on, e.g., latency, bandwidth or on local break-out possibilities. Many use-cases for 5G (IoT, connected cars, Industry 4.0, …) span the device, access-, distributed-, national- or global sites. This requires a solution that can handle any workload, anywhere in the network, with end-to-end orchestration. Distributed cloud goes along with automated deployment of applications at just the right location in the network to optimize resource efficiency and user experience. Distributed clouds, however, may well span across multiple providers, both infrastructure and online service providers, and may include enterprises or end customer resources too. In such scenarios, autonomous systems shall self-organize themselves into situational orchestration structures (hierarchies) to enable end-to-end automation. Last but not least applications are built on top of multiple-layers of services, which may be managed on their own (XaaS paradigm). How distributed resources and managed services from multiple-stakeholders may be brought together for end-to-end service automation is discussed based on results and insights gained from a proof of concept research prototype.
Bio: Róbert Szabó, PhD, is a master researcher at Ericsson Research, Hungary since 2013. At Ericsson, he was the technical coordinator of the EU-FP7 integrated project: Unifying Cloud and Carrier Networks (UNIFY) /2013-2016/ and he was the project coordinator of the H2020 5G-PPP 5G Exchange (5GEx) innovation action /2015-2018/. Dr. Szabo has an associate professor position (part time) at the Dept. of Telecommunications and Media Informatics (TMIT), Budapest University of Technology and Economics (BME). He was the president of the Telecommunications Section of the Scientific Association for Infocommunications (HTE), Hungary /2005-2007/. He was the deputy head of the TMIT, BME (2008-2010). He was the head of the High Speed Networking Lab (HSNLab), at BME /2007-2012/. His researches were supported by the János Bolyai Scholarship of the Hungarian Academy of Science (MTA). He was a member of the Future Internet Award jury /2010- 2013/. He is co-author of over 80 publications. He supervised the work of 3 graduated PhD students at TMIT, BME.