Talk on "D2P: Creating Distributed Dynamic Programming Codes Automatically"
Speaker: Nikhil Hegde.
Title: D2P: Creating Distributed Dynamic Programming Codes Automatically.
Abstract:Dynamic Programming (DP) algorithms are common targets for parallelization, and, as these algorithms are applied to larger inputs, distributed implementations become necessary. However, creating distributed-memory solutions involves the challenges of task creation, program and data partitioning, communication optimization, and task scheduling. In this work we present D2P, an end-to-end system for automatically transforming a specification of any recursive DP algorithm into distributed-memory implementation of the algorithm. When given a pseudo-code of a recursive DP algorithm, D2P automatically generates the corresponding MPI-based implementation. Our evaluation of the generated distributed implementations shows that they are efficient and scalable. Moreover, D2P-generated implementations are faster than implementations generated by recent general distributed DP frameworks, and are competitive with (and often faster than) hand-written implementations.
Speaker Bio: Nikhil Hegde is a PhD candidate in the School of Electrical and Computer Engineering at Purdue University, USA advised by Prof. Milind Kulkarni. He obtained his master's degree from IIT Madras in 2005, and bachelor's degree from B.M.S.College of Engineering, Bangalore in 2002, both in Computer Science and Engineering. He is interested in the broad areas of high-performance computing, and programming languages. Currently, his research focuses on distributed-memory parallelism of irregular applications. He also has over eight years of professional experience working in the industry developing hardware, middleware, and software.
Event Date: 01th March, 2019(Friday)
Event Time: 3:00 PM to 4:00 PM
Venue: Room 119
IIT Dharwad, Karnataka