Course

Unit I

Accelerated Computing – GPUs – Overview of GPU Architectures – CUDA – OpenCL – Case Studies IoT and Cloud Architectures – Use Cases – VLSI Design Challenges for IoT– Power – Area and Security – Intel Dashboard Framework.

Unit II

Overview of Cloud Computing – Introduction to Hadoop Framework – Case Study – FPGA Architectures for Neural Networks and Bioinformatics – Review of Neural Networks and Deep Learning.

Unit III

Data Precision and Implementation Issues – Case Studies of Regression Implementation – FPGA and Reconfigurable Architectures for Bioinformatics – Database Search – Sequencing and Alignment.

References

1. David B. Kirk, Wen-Mei W. Hwu, Programming Massively Parallel Processors: A Hands-on Approach, Second Edition, Morgan Kauffman, 2016.
2. Bertil Schmidt, Bioinformatics: High Performance Parallel Computer Architectures, CRC Press, 2011

 Learning Objectives

LO1    To introduce new paradigms in computing.

LO2    To familiarize various aspects and issues in implementation of machine learning
             systems.

LO3    To impart background on application of FPGAs and unconventional computing
             platforms for machine learning.

LO4    To provide exposure to using state of the art computing tools.

Course Outcomes

CO1    Ability to understand high performance machine learning architectures.
CO2    Ability to apply computing paradigms for machine intelligence problems.

CO3    Ability to suggest solutions and platforms for dataflow intensive problems.

CO4    Ability to evaluate the use of diverse technologies to design efficient applications. 

CO-PO Mapping

References

1. David B. Kirk, Wen-Mei W. Hwu, Programming Massively Parallel Processors: A Hands-on Approach, Second Edition, Morgan Kauffman, 2016.
2. Bertil Schmidt, Bioinformatics: High Performance Parallel Computer Architectures, CRC Press, 2011