Computer Syst

Our society depends today on computer systems. The Internet, banking, healthcare, energy management, ICT operations of SMEs and large organizations, media and web services, online games and social media, and even governance, are elements of a Digital Economy in which massive computer systems, such as modern datacenters, serve as factories producing services with massive consumption. Post-Moore computer systems, in which both hardware and software have experienced rapid change from (internal) amplification towards (external) diversification, proliferation, and commoditization, have already resulted in a diversity of radically new designs serving new ways to create and consume digital artifacts. It is this change that drives the need for a new research discipline at the core of modern computer science.

A new discipline: The emerging discipline of Massivizing Computer Systems is concerned with the design, implementation, deployment, analysis, and benchmarking of computer systems for which the resources, users, and/or workloads are massive in nature. This is a rich research field, with key challenges including: elasticity, which greatly extends the goals of scalability; dependability, which means giving operational guarantees that go beyond trivial quality of service and SLAs; heterogeneity, which focuses on the combinatorial, almost Cambrian, diversity explosion of hardware, middleware, and applications; pro-social relationships, focusing on the implicit and explicit, coincidental or structural, technology or personally driven, relationships developing in large-scale communities of users of our systems; ecosystem orchestration, which means understanding, managing, and scheduling in the complex, often multi-layered and non-trivially distributed system of systems (network of networks); efficiency, which we see as overcoming these challenges with care for use of natural resources, while making the resulting computer systems available to everyone in our society.

Mission: Our group is Massivizing Computer Systems, that is, making somputer systems scalable, reliable, performant, etc., yet forming efficient, engineered ecosystems available to everyone. Our group aims to achieve this by conducting groundbreaking, impactful research, by educating the new generation of top-quality and socially responsible individuals, and by making innovation available to industry and society at large to improve the lives of millions.

Strategy and key results: Our key strategy is to develop the best people, and motivate them to create the most innovative and impactful results. We lead a unique recruitment and training programme, which focuses on recruiting and hiring young talent people in the Netherlands and worldwide, and then (unique in the Netherlands) on developing this talent into the best professionals they can become through an intensive talent-development programme. We innovate in the process of computer science, by combining rigorous approaches to experimental science, with modern software engineering and innovative international collaborations. We innovate in the process of teaching, through an unique, award-winning technique based on gamification. We go the extra mile in linking with the industry, to find applications of our research in real-world settings; this also greatly benefits our graduates, who can more easily find high-skill high-reward jobs. We try to embed in the society, offering training programs and consultancy to key actors in the modern society, from large corporations to newly arrived legal-immigrants with difficult backgrounds.

People: We focus much on our people, with a flat organizational structure (everybody's opinion is heard) and a diverse, inclusive team. We have a large team, and a network of long-term collaborators across Europe and the US of A. Our core team includes people selected from the top of each year's computer-science cohort in the Netherlands; for example, Georgios Andreadis has won the Netherlands-wide Young Talent Incentive Award for Informatics and Computer Science, 2016.

Application areas: Our research is inspired by real-world applications, in domains with societal impact such as e-science, business-critical workloads, online gaming, and (future) massivized education. Additionally, much like mathematics and many natural sciences, computer science also feeds unto itself: our work is applied in computer science, supporting important emerging paradigms such as big data, cloud computing, datacenter technology, microservice-based software engineering, modern performance engineering, etc.

Key partners: The VU CompSys department has a broad expertise in computer systems, extending greatly the scope and capabilities offered by our group. We also have close ties and a strong ongoing collaboration with TU Delft's Software Technology department. We have a broad international network at the top of our research field, with strong connections extending also across the distributed computing systems and performance engineering communities. We collaborate with many of the world's top-10 cloud computing companies, including Salesforce.com, SAP, Google Inc., Oracle, IBM TJ Watson Research Center, global leaders in middleware and hardware, such as Intel and Huawei, innovative companies in datacenter technology in the Netherlands, such as Solvinity and Nerdalize, etc. We also focus on leadership roles in the private-public partnership: we hold the (elected) Chair of the SPEC Research Cloud Group and the lead in analytics of the LDBCouncil.

Awards and Recognition: Our group has received much attention in the past decade. Alexandru Iosup has been inducted in 2016 in the Young Academy of the Netherlands Academy of Arts and Sciences; across all disciplines of science, 5 new researchers under the age of 40 are inducted for 5 years, every year. In research, we have received the Netherlands Award for ICT Research 2016, which is awarded yearly to one researcher under the age of 40 by NWO (Dutch equivalent to US NSF) and the national organization ICT Research Platform Nederland (IPN); we have also received many best-paper awards and nominations. In education, we have received the Dutch Higher-Education Teacher of the Year 2015, which is awarded yearly to one professor active at university, applied university, or high school level by the Minister of Education and the national student organization ISO; we have also received several other education prizes. In community service, we have received the SPEC SPECtacular award three times (last in 2017), hold elected and selected roles in organizing the community, such as the role of Program Chair of the flagship conference HPDC 2017, and the role of General Chair of ICPE 2016. Our team also leads in the organization of major hackathon activities for juniors, national events in computer systems, etc.

Publications, Open-Source Software, Open-Access Data: We publish in the top conferences and journals in the field, and our work is highly cited. Our curated list of publications, indicating focus on quality and productivity, is publicly available online. (Although bibliometrics do not tell the whole story, they still count for an awful lot of hiring and promotion decisions, so here is an example of the very good position we are in this area.) Conducting modern computer systems also leads to modern kinds of publications: we publish much free/open-source software artifacts and we have co-founded four open-access data archives, including the Grid Workloads Archive, to provide public access to workload and resource-operation traces from large-scale distributed computing environments.

More details from our web page:https://atlarge-research.com/