Everything open source
May 16–17, 2016: Training & Tutorials
May 18–19, 2016: Conference
Austin, TX

CarbonData : A new Hadoop-native file format for faster data analysis

Jihong MA (Huawei)
1:50pm–2:30pm Wednesday, 05/18/2016
Location: Meeting Room 16A
Average rating: ****.
(4.00, 1 rating)

Are you working with the Hadoop ecosystem but still puzzled how to accelerate big data analytics? Jihong Ma explains why you should check out CarbonData, an indexed and columnar store file format designed for fast analytics, and outlines how it can help speed up queries an order of magnitude faster over petabytes of data.

Huawei CarbonData will be donated to the Apache Software Foundation for continued development and adoption by the greater big data community.

This session is sponsored by Huawei.

Photo of Jihong MA

Jihong MA


Jihong Ma is currently a principle architect at Huawei’s US software lab, where she works on CarbonData, an open source efficient data format for big data analytics. Jihong previously worked at the IBM Spark Technology Center, where she contributed to Apache Spark. She also participated in the development of an M/R-based distributed machine-learning system that has since become Apache SystemML. She has extensive experience in SQL database query processing and is a key member of the DB2 LUW Compiler team. Jihong holds an MS in computer science from the University of Wisconsin—Madison.