Presented By O'Reilly and Cloudera
Make Data Work
March 13–14, 2017: Training
March 14–16, 2017: Tutorials & Conference
San Jose, CA
Shoumik Palkar

Shoumik Palkar
Graduate Student, Stanford University


Shoumik Palkar is a second-year PhD student in the Infolab at Stanford University, where he works with Matei Zaharia on high-performance data analytics. He holds a degree in electrical engineering and computer science from UC Berkeley.


11:50am12:30pm Thursday, March 16, 2017
Shoumik Palkar (Stanford University)
Modern data applications combine functions from many libraries and frameworks and cannot achieve peak hardware performance due to data movement across functions. Shoumik Palkar offers an overview of Weld, an optimizing runtime that enables optimizations across disjoint libraries, and explains how to integrate it into frameworks such as Spark SQL for performance gains with no changes to user code. Read more.