Chapter 3

From Algorithms to Architectures

Abstract

Devising a suitable circuit architecture for a set of signal or data processing applications is one of the most exciting challenges for any VLSI designer. Depending on the details, a hardwired circuit may be orders of magnitude more efficient than a software running on a general-purpose microprocessor, both in terms of throughput and power dissipation. We give a list of criteria that identify favorable situations and that help devise hardware-friendly processing algorithms. Almost all known methods for tailoring VLSI architectures to specific needs are then discussed and compared. These not only include iterative decomposition, pipelining, replication, time sharing, algebraic transforms, ...

Get Top-Down Digital VLSI Design now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.