Fueled by an explosion of computer power, data-storage capacities, and sensor and simulation capabilities, extreme-scale data sets now contain petabytes to exabytes and are at the leading edge of today's boom in online commerce and Big Data scientific activities. The Extremely Large Databases (XLDB) effort attempts to tackle challenges related to such data sets.

Main activities include:

• identifying trends, commonalities and roadblocks related to managing and analyzing extreme-scale data sets

• bridging gaps between those in different communities who use extreme- scale data systems with appropriate researchers and solution providers worldwide

• facilitating development & growth of appropriate technologies including, but not limited to, databases.

To meet rapidly growing demand since XLDB's initial invitational workshop in 2007, annual open conference, satellite and topical events have been added. The open conference typically attracts ~200 attendees. Satellite events allow the US-centric XLDB community to better connect with international communities. Events have been organized in Geneva, Switzerland; Edinburgh, UK; Beijing, China, and Rio de Janeiro, Brazil. One topical event focusing on healthcare has also been held.

We are proposing organizing the 2017 XLDB event in Clermont-Ferrand, France. This is the very first time we will be organizing a full-conference outside of the USA.


1.5 days for main conference, and ½ to 1 day for Hackathon. Session list avalaible below.

Session: Modern data management

October 10, 2 pm


Detailed program is here

Session: Polystores

October 11, 8:45 am


Databricks logo
Spark logo
Flink logo
INRIA logo
Leanxcale logo

Detailed program is here

Session: Scaling Cloud to Big Data

October 11, 13:45 pm

Detailed program is here


Session: Earth and Space and Life sciences

October 11, 16:05 pm


Detailed program is here