Accelerating Data Science at the Edge Using FPGAs

Prof. Viktor K. Prasanna will introduce you to the Data Science Lab at the University of Southern California on Nov. 9 at 11:00. The lecture titled “Accelerating Data Science at the Edge Using FPGAs” demonstrates parallel architectures and algorithms based on FPGAs for different data analysis kernels. The lecture takes place in room TH:A-1455 and is in English.

Topic

Data Science has matured over the past few years with novel applications in diverse areas including health, energy, Autonomous X, etc. Many of these are cyber-physical-social systems with strict requirements of latency, throughput and energy efficiency. With recent dramatic advances in FPGAs, these devices are being used along with multi-core and emerging memory technologies to realise advanced platforms to accelerate a variety of complex applications.

This talk will review the work in the Data Science Lab at the University of Southern California (USC) and the promise of reconfigurable computing leading up to current trends in accelerators for Data Science. It will illustrate FPGA-based parallel architectures and algorithms for a variety of data analytics kernels in streaming graph processing and machine learning for “edge” processing.

While demonstrating algorithm-architecture co-design methodology to realise high-performance accelerators for graphs and ML, prof. Prasanna demonstrates the role of modelling and algorithmic optimisations to develop highly efficient IP cores. For graph embedding, he develops a novel computationally efficient technique using graph sampling and demonstrates scalable performance.

For CNN inferencing, we develop parallel frequency domain convolution algorithms and data layouts to realise high throughput and energy efficient designs using FPGAs. We conclude by identifying opportunities and challenges in exploiting emerging heterogeneous architectures composed of multi-core processors, FPGAs, GPUs and coherent memory.

About the Event

The lecture is free of charge, and registration is not required. The lecture is primarily intended for students and professional public with advanced knowledge of FPGA, parallel algorithms and architectures.

Event type
Lecture
Lecturer
Viktor K. PrasannaUniversity of Southern California (USC)
Date
November 9, 2018, 11:00–12:00
Place
Conference room TH:A-1455, Building A
Thákurova 7, Prague 6
Language
English
Video
Will not be recorded

About the Lecturer

Viktor Prasanna – profileViktor K. Prasanna is Charles Lee Powell Chair in Engineering in the Ming Hsieh Department of Electrical Engineering and Professor of Computer Science at the University of Southern California (USC). He is the director of the Center for Energy Informatics at USC and leads the FPGA and Data Science Labs. His research interests include parallel and distributed computing, accelerator design, reconfigurable architectures and algorithms and high-performance computing.

He served as the Editor-in-Chief of the IEEE Transactions on Computers during 2003–2006 and is currently the Editor-in-Chief of the Journal of Parallel and Distributed Computing. Prasanna was the founding Chair of the IEEE Computer Society Technical Committee on Parallel Processing. He is the Steering Co-chair of the IEEE International Parallel and Distributed Processing Symposium and the Steering Chair of the IEEE International Conference on High Performance Computing.

His work has received best paper awards at leading forums in parallel computing, HPC and FPGAs, including Computing Frontiers, International Parallel and Distributed Processing Symposium, ACM International Symposium on FPGAs, among others. He is a Fellow of the IEEE, the ACM and the American Association for Advancement of Science (AAAS). He is a recipient of the 2009 Outstanding Engineering Alumnus Award from the Pennsylvania State University. He received the 2015 W. Wallace McDowell award from the IEEE Computer Society for his contributions to reconfigurable computing.

People
Lecturer: Viktor K. Prasanna
Places
TH:A-1455
Person responsible for the content of this page
doc. Ing. Hana Kubátová, CSc., hana.kubatova@fit.cvut.czLecture Organizer


Last modified: 7.11.2018, 14:45