2020 Virtual Conference
The 2020 edition of the EcoCloud Annual Event will be virtual and will bring a strong lineup of distinguished speakers and select experts from our affiliates and EcoCloud researchers with topics ranging from alternative data-centric compute paradigms to optics in the cloud, server security and intelligent object stores. The program is designed to accommodate the EcoCloud community online from diverse time zones. Join us from your office, home or through your mobile and connect with the EcoCloud community during this event.
All times are Central European Time (CET)
Day 1: Tuesday October 27th, 2020
|Session I: Networking (Chair: Katerina Argyraki)|
|17:00-17:20||Optics for the Cloud: Challenges and Opportunities||Hitesh Ballani, Microsoft|
|17:20-17:30||Q&A with Hitesh Ballani|
|17:30-17:50||Photonic-Chip Based Soliton Microcombs||Tobias Kippenberg|
|17:50-18:00||Q&A with Tobias Kippenberg|
|Session II: Edge Computing (Chair: David Atienza)|
|18:00-18:20||Accelerating Data Lakes with Intelligent Cloud Object Stores||Javier Picorel, Huawei|
|18:20-18:30||Q&A with Javier Picorel|
|18:30-18:35||Energy-aware Design & Management of Multi-Processor SoC||Marina Zapater|
|18:35-18:40||Applied Reinforcement Learning for Runtime Management of Multicore Platforms||Arman Iranfar|
|18:40-18:45||Rethinking General Purpose Decentralized Computing||Enis Ceyhun Alp|
|18:45-18:50||Communication-efficient Decentralized Machine Learning||Anastasia Koloskova|
|18:50-19:00||Q&A Session with Marina Zapater, Arman Iranfar, Anastasia Koloskova, and Enis Ceyhun Alp|
Day 2: Wednesday October 28th, 2020
|Session III: Security/Resilience (Chair: Mathias Payer)|
|17:00-17:20||Speculative Execution Attacks as the New Memory Corruption||Anil Kurmus, IBM|
|17:20-17:30||Q&A with Anil Kurmus|
|17:30-17:35||Taming your ISA Abstractions||Atri Bhattacharyya|
|17:35-17:40||Decentralized Proximity Tracing at a Glance||Wouter Lueks|
|17:40-17:45||Experimental Aspects of Digital Proximity Tracing||Daniele Antonioli|
|17:45-17:50||Design choices for Digital Contact-Tracing Systems||Ludovic Barman|
|17:50-18:00||Q&A Session with Daniele Antonioli, Atri Bhattacharyya, Wouter Lueks, and Ludovic Barman|
|18:00-19:00||New Compute Models to Power the Data Revolution||Richard Uhlig, Intel|
New Compute Models to Power the Data Revolution
Rich Uhlig, Intel Labs
This talk will cover research topics on new computing models ranging from research in quantum computing, neuromorphic computing, compute-near memory, silicon photonics, trusted-execution environments, graph analytics, etc.
Rich Uhlig is the managing director of Intel Labs and an Intel senior fellow. Prior to this role, Rich was the director of Systems and Software Research in Intel Labs, where he led research efforts in virtualization, cloud-computing systems, software-defined networking, big-data analytics, machine learning and artificial intelligence. He joined Intel in 1996 and led the definition of multiple generations of virtualization architecture for Intel processors and platforms, known collectively as Intel Virtualization Technology (Intel® VT). Rich earned his Ph.D. in computer science and engineering from the University of Michigan.
Speculative Execution Attacks as the New Memory Corruption: A Systems and Software Challenge for the Next Decade
Anil Kurmus, IBM Research Zurich
Spectre and Meltdown are the first of numerous transient attacks, which demonstrate that subtle CPU design and implementation issues can result in real world attacks, leaking sensitive information from systems. In this talk, we survey some Spectre-like attacks, and discuss approaches to understand, mitigate and prevent them. We draw a parallel with memory corruption and argue that a similar challenge to achieving memory safety awaits system and software researchers in designing efficient solutions to speculative execution attacks.
Anil Kurmus is a security researcher at the IBM Research Zurich laboratory. His interests are mainly on systems security, software security, microarchitecture security, storage systems, and applied cryptography, both in terms of offensive and defensive research. He holds a PhD degree (Dr.-Ing) from Technische Universitat Braunschweig (2014), and a Master’s degree (Diplome d’Ingenieur) from Telecom ParisTech (2009). His work, often in collaboration with excellent students visiting IBM Research, has been published in top systems security conferences.
Accelerating Data Lakes with Intelligent Cloud Object Stores
Javier Picorel, Huawei
Cloud object stores such as Amazon S3, Azure Blob, Alibaba OSS, and Huawei OBS have become some of the exascale and most widely used storage systems on the planet. Besides the traditional benefits of the clouds, cloud object stores are especially attractive because they allow users to scale computing and storage resources separately. As a result, many organizations now use cloud object stores to manage large data lakes with popular big data solutions. Unfortunately, in disaggregated architectures the network that connects the computation and storage layers can quickly become a major performance bottleneck. In this talk, I will discuss a new feature in Huawei OBS, OBS Select, which pushes limited computation in the shape of a subset of SQL down to the requested objects. Furthermore, I’ll also discuss future challenges and opportunities of future intelligent cloud object stores.
Javier Picorel is a research scientist leading the Infrastructure-as-a-Service (IaaS) team in Huawei’s Munich Research Center, which focuses on the hardware and software platform design and efficiency for Huawei Cloud’s portfolio, along with shaping and roadmapping the business layout and technology focus of Huawei’s public cloud. He is broadly interested in TCO-efficient cloud infrastructures through the vertical integration of hardware and software layers in the end of semiconductor technology scaling. He received a PhD in computer science from EPFL in 2017 and he is also the recipient of several awards in Huawei.
Optics for the Cloud: Challenges and Opportunities
Hitesh Ballani, Microsoft Research
Hitesh Ballani is a Senior Principal Researcher at Microsoft Research in Cambridge, UK. His research aims to build systems and networks for next-generation data centers. His current focus is on developing optical technologies for the cloud. Previously, he worked on a Quality-of-Service architecture for networked storage that ships in Windows Server. He graduated with a PhD in Computer Science from Cornell University in 2009 and then joined Microsoft.