Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation (Systems on Silicon) (Hardcover)

~ Scott Hauck (Author), André DeHon (Author)
Key Phrases: active pages, evolvable hardware, fixed order, Field-Programmable Gate Arrays, International Symposium, Custom Computing Machines (more...)

Editorial Reviews

Book Description

The performance of hardware, with the flexibility of software!

Product Description

The main characteristic of Reconfigurable Computing is the presence of hardware that can be reconfigured to implement specific functionality more suitable for specially tailored hardware than on a simple uniprocessor. Reconfigurable computing systems join microprocessors and programmable hardware in order to take advantage of the combined strengths of hardware and software and have been used in applications ranging from embedded systems to high performance computing. Many of the fundamental theories have been identified and used by the Hardware/Software Co-Design research field. Although the same background ideas are shared in both areas, they have different goals and use different approaches.This book is intended as an introduction to the entire range of issues important to reconfigurable computing, using FPGAs as the context, or "computing vehicles" to implement this powerful technology. It will take a reader with a background in the basics of digital design and software programming and provide them with the knowledge needed to be an effective designer or researcher in this rapidly evolving field.

. Treatment of FPGAs as computing vehicles rather than glue-logic or ASIC substitutes
. Views of FPGA programming beyond Verilog/VHDL
. Broad set of case studies demonstrating how to use FPGAs in novel and efficient ways

Product Details

• Hardcover: 944 pages
• Publisher: Morgan Kaufmann (November 16, 2007)
• Language: English
• ISBN-10: 0123705223
• ISBN-13: 978-0123705228
• Product Dimensions: 9.3 x 7.5 x 1.7 inches
• Shipping Weight: 3.6 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars  See all reviews (1 customer review)
• Amazon.com Sales Rank: #536,049 in Books (See Bestsellers in Books)

Customer Reviews

Most Helpful Customer Reviews

13 of 14 people found the following review helpful:

5.0 out of 5 stars The textbook we've been waiting for, April 5, 2008

By	wiredweird "wiredweird" (Earth, or somewhere nearby) - See all my reviews (TOP 100 REVIEWER)

Reconfigurable computing (RC), of one kind or another, has been around at least since Estrin's work in the 1960s. FGPAs created the real platform for it in the 1980s but, as one of the RC's founders noted, "10×-100× of performance ... has been at the cost of 10×-100× increase in difficulty in application development." Outside of a few niches in signal processing, this No Man's Land between circuit design and programming remained largely unexplored. That changed in the last few years, with the Stratix/Virtex generation of FPGAs. Quite abruptly, large numbers of researchers and developers found enough computing power to make the effort of RC worthwhile. As with any emerging technology, developments first appeared in academic journals and conference proceedings. There hasn't been a systematic introduction to RC's practice, potential, and problems.

This book is that introduction. The editors present 38 chapters, each written by established RC researchers and educators. They start with an introduction to the basics: what an FPGA is, what suits it to use as a computing platform, and how it compares to other commercial and research engines. The next covers some of the major tools used in FPGA programming. Unlike C, which linguistically captures the sequential nature of the von Neumann bottleneck, VHDL and Verilog inherently describe massive and fine-grained parallelism. These languages present challenges of their own, obviously, so other chapters describe experimental and commercial alternatives to at least parts of the RC programming problem.

Starting around page 300, the book gets into the real meat of RC. Where von Neumann models distribute an algorithm across time, RC distributes it across the space provided by the RC fabric. It even offers space-time tradeoffs of unprecedented kinds, as these authors show. The next section covers application development, including partitioning and topics that might startle some C programmers. Since RC can use data values of any width, from individual bits to thousands, the programmer not only can but must decide how many to use, subject to tradeoffs unique to RC. Then we see applications, the whole reason for computing of any kind. A few well-chosen case studies appear in sufficient detail that a practitioner could reproduce the work, or large parts of it. This section, I think, distinguishes this book from all others I've seen. It truly gives the reader some feel for the structure and development of RC applications.

This isn't the only RC book on the market, and certainly won't be the last. People already familiar with RC's arcana might pick a few fact from the text, or from the voluminous bibliographies. For someone already familiar with hardware or software (or, preferably, both) but new to RC, this offers the best introduction currently available. Despite some minor flaws in editing (including blunders with exponents in eq. 37.7), this has my highest recommendation.

-- wiredweird