JOY ARULRAJ

I am a fifth-year Ph.D. candidate in the Parallel Data Lab at Carnegie Mellon University working in database systems. In my dissertation work, I studied and built a new non-volatile memory database system, called Peloton, under the advisement of Andy Pavlo. My research is supported by the Carnegie Mellon Presidential Fellowship and a Samsung Ph.D. Fellowship.

I earned an M.S. from the University of Wisconsin, Madison, where I was fortunate to be advised by Shan Lu. For my B.E., I studied Computer Science and Engineering at the College Of Engineering, Guindy under the guidance of Prof. Ranjani Parthasarathi.

At CMU, I am a member of the Database Group and the Speakers Club. I enjoy playing squash.
My picture

APPLICATION MATERIALS

I am on the academic job market in 2018.


RESEARCH AGENDA

For the first time in 25 years, device manufacturers have created a new memory technology. This non-volatile memory technology blurs the gap between volatile memory and durable storage. My current research investigates how to rearchitect the DBMS from the ground-up to take advantage of non-volatile memory.

In the future, I plan to continue my research in the field of data management, with a focus on building systems for accelerating data science and lowering the barrier to entry for users. I will accomplish this by leveraging emergent heterogeneous hardware architectures and machine learning algorithms in my work.

REPRESENTATIVE PUBLICATIONS

  • Write-Behind Logging
    Joy Arulraj, Matthew Perron, and Andrew Pavlo
    VLDB 2017
    [paper] [slides] [code] [project]
  • BzTree: A High-Performance Latch-free Range Index for Non-Volatile Memory
    Joy Arulraj, Justin Levandoski, Umar Farooq Minhas, and Per-Ake Larson
    VLDB 2018
    [paper]
  • Let’s Talk About Storage & Recovery Methods for Non-Volatile Memory Database Systems
    Joy Arulraj, Andrew Pavlo, and Subramanya R. Dulloor
    SIGMOD 2015
    [paper] [slides] [code] [project]
  • Bridging the Archipelago between Row-Stores and Column-Stores for Hybrid Workloads
    Joy Arulraj, Andrew Pavlo, and Prashanth Menon
    SIGMOD 2016
    [paper] [slides] [code] [project]
  • How to Build a Non-Volatile Memory Database Management System
    Joy Arulraj and Andrew Pavlo
    SIGMOD 2017 (Tutorial)
    [webpage] [paper] [slides] [project]


NEWS


CONTACT

Computer Science Department
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA 15213

Office: Gates Hillman Center 9022
Email: jarulraj@cs.cmu.edu
Twitter: @joy_arulraj
Blog: jarulraj
DBLP: jarulraj
Scholar: jarulraj
GitHub: jarulraj