What do you think?
Rate this book
Computer Engineering: A DEC View of Hardware Systems Design
This book has been written for practicing computer designers, whether their domain is microcomputers, minicomputers, or large computers. The book uses the case study method to show how all the different factors (technology push, the marketplace, manufacturing, etc.) form the real-world constraints and opportunities which influence computer engineering. For examples, we have used 30 DEC computers, plus some PDP-11-based machines built at Carnegie-Mellon University.
- GenresReference
585 pages, Hardcover
First published January 1, 1978
1 person is currently reading
27 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 2 of 2 reviews
June 8, 2015
Not as interesting as I thought it would be. It's a somewhat good read if you're interested in minicomputers; I haven't found many books on the subject.
October 9, 2019
C. Gordon Bell's Computer Engineering: A DEC View of Hardware Systems Design is a classic book of the field. DEC was a pioneering computer systems company, from 1957 to 1998. This is an excellent book written by excellent engineers. Reading it reminded me of the joy I felt as a teenager, reading a PDP handbook.
This book starts with an academic yet vivid view on computer systems, from seven different perspectives. (When have you seen more than one view in an engineering or scientific paper? This book goes back to the roots of design, to a period where requirements were not oversimplified. No Apple, then.)
The introduction and a couple of appendices introduce two key notations, the processor-memory-switch (PMS) and the instruction set processor (ISP). The PMS notation is particularly useful, and in the book it is the basis of all discussions related to computer structure (organization for a computer engineer, architecture for a (software) computer systems researcher). ISP is a bit convoluted by today's standards, but is used occasionally to depict code, instructions, and implementation of the instructions (architecture for a computer engineer, API or simply interface for a (software) computer systems researcher). Confused? Then you really need to read and internalize this notation.
In five core parts, the book covers the components designed by DEC into increasingly more integrated packages, the PDP series described in computer engineering detail (one chapter on PDP-8), the design and evolution of the PDP-11 machine-family (think about the families of related/compatible technologies IBM System/360, Intel 80x86, Microsoft Windows, etc.), the evolution of various tech families inside DEC (including a chapter on the multi-(micro)processor Cm*), and a full part on the less-known PDP-10. This is high quality engineering material, written by real engineers building real (and very successful) products.
It's difficult to explain how good this book is, because there's as far as I see no modern comparison. Think Turing Award winners John L. Hennessy and David Patterson's Computer Architecture: A Quantitative Approach but more groundbreaking, more scientific, more long-term thinking. (Not Hennessy and Patterson's fault, perhaps, because this book covers an era before the Intel and PC standardization of the mid-1970s to the mid-2000s.) This does not mean this book is perfect, but it is an excellent exponent of the topic and period that it covers, down to the intoxicating focus on the DEC world and ita 'not invented here' aversion.
This book starts with an academic yet vivid view on computer systems, from seven different perspectives. (When have you seen more than one view in an engineering or scientific paper? This book goes back to the roots of design, to a period where requirements were not oversimplified. No Apple, then.)
The introduction and a couple of appendices introduce two key notations, the processor-memory-switch (PMS) and the instruction set processor (ISP). The PMS notation is particularly useful, and in the book it is the basis of all discussions related to computer structure (organization for a computer engineer, architecture for a (software) computer systems researcher). ISP is a bit convoluted by today's standards, but is used occasionally to depict code, instructions, and implementation of the instructions (architecture for a computer engineer, API or simply interface for a (software) computer systems researcher). Confused? Then you really need to read and internalize this notation.
In five core parts, the book covers the components designed by DEC into increasingly more integrated packages, the PDP series described in computer engineering detail (one chapter on PDP-8), the design and evolution of the PDP-11 machine-family (think about the families of related/compatible technologies IBM System/360, Intel 80x86, Microsoft Windows, etc.), the evolution of various tech families inside DEC (including a chapter on the multi-(micro)processor Cm*), and a full part on the less-known PDP-10. This is high quality engineering material, written by real engineers building real (and very successful) products.
It's difficult to explain how good this book is, because there's as far as I see no modern comparison. Think Turing Award winners John L. Hennessy and David Patterson's Computer Architecture: A Quantitative Approach but more groundbreaking, more scientific, more long-term thinking. (Not Hennessy and Patterson's fault, perhaps, because this book covers an era before the Intel and PC standardization of the mid-1970s to the mid-2000s.) This does not mean this book is perfect, but it is an excellent exponent of the topic and period that it covers, down to the intoxicating focus on the DEC world and ita 'not invented here' aversion.
Displaying 1 - 2 of 2 reviews