Domain Specific Accelerator (DSA) architectures for Signal Processing, Communications and Machine Learning

Speaker:  Kiran Gunnam – Austin, TX, United States
Topic(s):  Architecture, Embedded Systems and Electronics, Robotics

Abstract

This lecture covers an introduction to Domain-Specific architectures for Communications, Signal Processing, and Machine Learning Systems. Various topics include pipelining and parallel processing, retiming, unfolding, folding, systolic architecture design, and algorithmic transformations. The emphasis is on how to design high-speed, low-area, and low-power DSA architectures for a broad range of applications. This lecture also covers the state-of-the-art in machine learning accelerators and emerging opportunities.

About this Lecture

Number of Slides:  45
Duration:  60 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.