2020 Northwest Database Society Annual Meeting
The Northwest Database Society Annual Meeting brings together researchers and practitioners from the greater Pacific Northwest for a day of technical talks and networking on the broad topic of data management systems.
This year, the meeting will be hosted by Amazon. It will be a full-day event. There will be two keynotes, several sessions of shorter presentations by members of our community, a poster session, and significant break time for unstructured discussion. There will be breakfast, lunch, coffee breaks, and a post-conference reception.
Where: Amazon Day 1 Building - 2112 6th Ave Seattle, WA 98121
When: Friday, January 24th
Check In: Please check in at reception. Check in will begin at 8 am in the reception area.
Registration: If you plan to attend the event, then please register here. Although there is no registration fee, you must register to attend. Breakfast, lunch, coffee breaks, and a post-conference reception will be sponsored by Amazon Web Services.
Talk submission: If you would like to present at the meeting, please submit a title and short description/abstract here. Please note that talk submission and registration are separate.
Parking: We recommend parking in the building garage. The entrance/exit is on 6th Ave, and one garage exit on Blanchard. Please note that no free parking is available. If you are able, we recommend taking public transportation. We are walking distance from the Westlake Light Rail Station.
Hashtag: Please use the event hashtag for social media posts! #NWDSMeeting
8:00am - 9:00am: Check-in and Breakfast
9:00am - 10:00am: Keynote - Sudipta Sengupta (AWS)
TITLE: The Domain Specialization Opportunity for Deep Learning Across Accelerators, Frameworks, and Compilers
ABSTRACT: Deep Learning is ushering in a new era of Artificial Intelligence with machines approaching human level accuracy on tasks across diverse application area such as vision, languages, speech, and recommendations. Deep learning compute usage is growing many times faster than compute capacity did at the peak of Moore’s Law. Deep learning computation is structured as mixed-precision linear algebra, hence can benefit from domain specific acceleration to fuel its growth and optimize for performance, cost, and power. Domain specific languages for deep learning, also known as frameworks, raise the programming abstraction to the lingua franca of model graphs/operators/tensors, increase productivity for scientists and practitioners in all fields within and outside of computing, and provide portability across heterogeneous hardware platforms. Compiler technology is needed for bridging the gap between high-level compute specification and low-level accelerator instructions for performance efficiency. In this talk, we take a glimpse into the deep learning opportunity across accelerators, frameworks, and compilers, survey the innovation/products/services at Amazon AWS AI across the stack, and, as a specific example, dive deep into our experience integrating deep learning accelerators with frameworks such as TensorFlow, MXNet, and PyTorch.
10:00am - 10:30am: Break and Posters
10:30am – 10:50am: Eugene Kogan (MemSQL): MemSQL - Operational Analytics at Scale
10:50am – 11:10am: Brandon Haynes (University of Washington): LightDB++: A DBMS for the Visual World
11:10am – 11:30am: Marc Bowes (Amazon): Amazon Quantum Ledger Database
11:30am – 11:50am: David Maier (Portland State University): Urban Data Systems
11:50am – 1:30pm: Lunch and posters
1:30pm - 2:30pm: Keynote - Phil Bernstein (Microsoft Research)
TITLE: Adding Data Management to Orleans – A Journey
ABSTRACT: For the past eight years, I’ve worked on adding database features to the Orleans object-oriented programming framework: replication, geo-distribution, transactions, and indexing. The challenge is how to do it when storage is a plug-in service that you don’t control. In this talk, I’ll describe the journey, summarizing the main technical ideas and recounting the ups and downs of a friendly collaboration with a product group. Along the way, I’ll discuss where database system research problems come from and the special challenges of industrial research.
3:00pm - 3:20pm: Muthu Annamalai (Facebook): Akkio: Managing Datastore Locality at Scale
3:20pm - 3:40pm: Tianzheng Wang (Simon Fraser University): Evaluating index structures on persistent memory
3:40pm - 4:00pm: Alekh Jindal (Microsoft): Peregrine: Workload Optimization for Cloud Query Engines
4:00pm - 4:20pm: Luna Dong (Amazon): Demeter: Harvesting knowledge from the semi-structured web
4:20pm - 4:40pm: Srikanth Kandula (Microsoft Research): Pushing Data-Induced Predicates Through Joins in Big-Data Clusters
5:00pm - 6:30pm: Happy Hour and Networking
Keynote Speaker Bios
Sudipta Sengupta is leading new initiatives in Artificial Intelligence/ Machine Learning at Amazon AWS as Senior Principal Technologist. Previously, he headed an end-to-end innovation agenda at Microsoft Research, spanning cloud networking, storage, and data management. Before that, he was at Lucent Bell Labs working on networked systems. He has shipped his research in many industry-leading, award-winning products and services. Sudipta is ACM fellow and IEEE fellow. He received the IEEE William R. Bennett Prize, the IEEE Leonard G. Abraham Prize, and the ACM SIGCOMM Test of Time award for his work spanning Internet and data center networking. His success in taking research ideas from conception to production has been recognized by the Microsoft Research Technology Transfer Award and the Bell Labs President’s Teamwork Achievement Award. Sudipta holds a Ph.D. and an M.S. in EECS from MIT and a B.Tech. in Computer Science and Engineering from the Indian Institute of Technology, Kanpur, India. He was awarded the President of India Gold Medal at IIT-Kanpur for graduating at the top of his class across all disciplines.
Philip A. Bernstein is a Distinguished Scientist at Microsoft Research. He has published over 150 papers and two books on the theory and implementation of database systems, especially on transaction processing and data integration. He is an ACM Fellow, a AAAS Fellow, a winner of ACM SIGMOD’s Codd Innovations Award, and a member of the Washington State Academy of Sciences and the U.S. National Academy of Engineering. He received a B.S. degree from Cornell and M.Sc. and Ph.D. from University of Toronto.