2015: Momentum, Moments and Memories

Greetings of the season from the Intel Science and Technology Center for Big Data.  As 2015 comes to a close, we thought we would share some moments and memories that were captured here in the ISTC for Big Data blog and elsewhere during the year.  

January 2015

ISTC for Big Data researchers aspire to work on applications that matter to the world, such as data-driven medical diagnosis and treatment.  On January 13, a workshop on medical big data at MIT CSAIL brings together computer scientists and clinicians to brainstorm new data sets and software – and to learn from each other.

In late January, ISTC Principal Investigators and students from Brown, Carnegie Mellon and Portland State universities and MIT CSAIL present work at the 2015 New England Database Day.

ISTC co-founder Sam Madden offers his roadmap for the ISTC in 2015 and beyond.

RDBMSes Can't Scale to 1,000 Cores NEDBS 2015

Want to see something really scary? (From New England Database Day 2015)

February 2015

Transportation and urban planning are awash with data, including real-time data collected from sensors. Researcher Kristin Tufte of Portland State University writes about this classic “big data variety” and “big data velocity” problem and work going on at Portland State University on real-world transportation data. The S-Store project – a streaming OLTP system for big velocity applications – demonstrates the possibilities in a bike-sharing application.

ISTC co-founder Michael Stonebraker of MIT CSAIL and Principal Investigator (PI) Ugur Cetintemel of Brown University receive the 2015 ICDE 10-Year Most Influential Paper Award, in recognition of their pioneering paper about databases, “‘One Size Fits All’: An Idea Whose Time Has Come and Gone” (presented at ICDE 2005). See them talk about the work on this short video

March 2015

ISTC co-founder Michael Stonebraker is awarded the Association for Computing Machinery’s prestigious A.M.Turing Award, often referred to as the “Nobel Prize for computing.” ACM says that Professor Stonebraker “invented many of the concepts that are used in almost all modern database systems … and founded numerous companies successfully commercializing his pioneering database technology work.” Professor Stonebraker proceeds to travel the world delivering his Turing Talk, “The Land Sharks are on the Squawk Box (How Riding a Bicycle across America and Building Postgres Have a Lot in Common).”  Watch it on YouTube.

April 2015

We need better, broadly available information-management tools designed with end-users – not data experts – in mind, says semantic web/HCI expert and ISTC PI  David Karger of MIT CSAIL

Conventional wisdom about in-memory data management systems says that even the best will eventually hit a “Memory Wall,” where performance is constrained by the time it takes to get data from primary storage. Newly minted PhD Holger Pirk of MIT CSAIL writes that the bigger obstacle to true interactive data management may be the “Brain Wall.” Read his post.

May 2015

The mainstreaming of next-generation hardware technologies – such as Non-Volatile Memory (NVM) and many-core CPU architectures – offers potential for all kinds of new big data applications. But will online transaction processing (OLTP) database systems rise to the challenge? ISTC PI Andy Pavlo of Carnegie Mellon writes about the most interesting challenges – and what he and his fellow researchers are doing to overcome them – in the May-June issue of IEEE Computing. Read the research team’s blog post, “Let’s Talk about Storage and Recovery Methods for Non-Volatile Memory Databases.”

June 2015

ISTC PI Arvind and fellow researchers from MIT CSAIL, MIT and Quanta Research Cambridge, prove that it’s possible to cut the cost and power consumption of big data applications by using flash memory as a replacement for conventional RAM. 

ISTC PI Jeffrey Heer and his team at the University of Washington‘s Interactive Data Lab think that we need better tools for everyone – not just skilled designers – to create effective visualizations and better understand their data. They offer Vega, a declarative visualization grammar. Similar to how SQL provides a language for expressing database queries, Vega provides a language for describing visualizations.  You can download Vega on Github.

July 2015

Authors Daniel A. Reed and ISTC PI Jack Dongarra of University of Tennessee, Knoxville and Oak Ridge National Laboratory publish their article “Exascale Computing and Big Data,” in Communications of the ACM.

August 2015

At the 2015 HP Big Data Conference opening session, ISTC for Big Data co-founder Michael Stonebraker gives attendees a lot to think about: from the power of transformational technologies like column-store databases and next-generation data curation, to how to weed through the big data hype. His spirited Q&A with HP SVP Colin Mahony starts at 43:00 in this video.

September 2015

At VLDB 2015, a multi-institution team of more than a dozen ISTC researchers unveils a new big data federation architecture, named BigDAWG.

In her VLDB 2015 keynote, ISTC PI Magda Balazinska of the University of Washington asks the controversial question “Big Data Research: Will Industry Solve All the Problems?”

A team from Brown University wins the Best Demo Award at VLDB 2015 for their work: “Vizdom: Interactive Analytics through Pen and Touch.”   VizDom is just one of the innovative technologies from ISTC researchers and students pushing the boundaries of visual interactive analysis.

Vizdom, a new system for interactive analytics, running on an interactive whiteboard. (Photo courtesy of Brown University Data Management Research Group.)

Vizdom, a new system for interactive analytics, running on an interactive whiteboard. (Photo courtesy of Brown University Data Management Research Group.)

October 2015

The ISTC continues to add talented researchers to the faculty. New in 2015 are Principal Investigators Aaron J. Elmore of the University of Chicago; Jennie Duggan of Northwestern University, and Matei Zaharia of MIT CSAIL, co-creator of Apache Spark; and researcher Vijay Gadepally of MIT CSAIL and MIT Lincoln Laboratory.

New PIs 2015

November 2015

ISTC co-founder and 2014 Turing Award winner Michael Stonebraker delivers his Turing lecture for the Association for Computing Machinery China and CNCC in Beijing

Jack Dongarra, Piotr Luszczek and Thomas Herault of the University of Tennessee’s Innovative Computing Laboratory write about the importance of interface sharing between data storage and analytics.

December 2015

The latest edition of “Readings in Database Management” (popularly known as “the Red Book”) – the first in 10 years – is published online and it’s free. It features some spirited discourse between its founding editors, ISTC co-founder Michael Stonebraker of MIT and Joe Hellerstein of UC Berkeley, who are joined this year by new editor Peter Bailis of MIT CSAIL.  See Chapter 11: “A Biased Take on a Moving Target: Complex Analytics” and Chapter 12: “A Biased Take on a Moving Target: Data Integration” by Professor Stonebraker, with commentary by Professor Hellerstein.

To keep up with the latest news and research from the ISTC for Big Data in 2016, bookmark the ISTC for Big Data Blog and follow us on Facebook, Twitter and Google+.

Happy New Year!

This entry was posted in Analytics, Big Data Applications, Big Data Architecture, Data Management, Databases and Analytics, DBMS, High-Performance Computing, ISTC for Big Data Blog, Storage, Streaming Big Data, Visualizing Big Data and tagged , , , , , , , , , , , , , , , , , , , . Bookmark the permalink.

Leave A Reply

Your email address will not be published. Required fields are marked *


5 − = two