35364 - Digital Architectures for Signal Processing M

Course Unit Page

Academic Year 2019/2020

Learning outcomes

Analysis of algorithms for image compression and speech processing from the perspective of the digital system designer. Definitions of the specifications derived from these algorithms. Spec mapping on various computational architectures. Examples of digital signal processing algorithms suitable for parallel architectures such as GPUs and multiGPUs.  Elements of instructions scheduling. Impact of word length on some filtering algorithms.

Course contents

Analysis of algorithms for signal processing applied to image compression, speech processing and biomedical image processing. 
Analysis of architectures for DSP based on dedicated and programmable devices 
 Parallelism and signal processing: algorithms for parallelism extraction Mapping of signal processing algorithms on different hardware architectures 
Impact of word length on various DSP algorithms   
Lab work: programming of multiGPU machines for DSP

Readings/Bibliography

K. K. Parhi - VLSI Digital Signal Processing Systems - Wiley - 1999

Teaching methods

Classroom lessons
Lab work

Assessment methods

Discussion of course material

Teaching tools

Lab tools for DSP programming

Office hours

See the website of Roberto Guerrieri