Customer Reviews

Computer Organization and Design: The Hardware/Software Interface

5 star:		(18)
4 star:		(12)
3 star:		(7)
2 star:		(5)
1 star:		(6)

 

 

This book is one of the standard textbooks for Computer Organization. However the approach of instruction taken by the authors is unconventional, and a reader might or might not find it useful. Here are the points that will be useful to prospective buyers: 1. If this book was ASSIGNED as a course requirement, have no fear. With a good instructor in class as your primary source, the book is fairly easy to understand. Besides, the exercises are well ranked in order of difficulty, and sufficiently varied across levels of difficulty. And they are usually interesting. 2. If you wish to use this as a reference work, be warned. The style is strange, and upside down in places. For example, "examples" are given with wrong usage of Assembly "instructions", because the book has not "got there yet". Later, you are given the "correct version". Some people might like this, some may not. 3. If you are a professional and want a refresher, be warned again. The book labours through pages and pages of simple worked exercises, involving nothing more complicated than a times b divided by c, and then jumps into implementational details. 4. One thing the book must be praised for is its thoroughness. 5. Essentially, the authors have intended that ANYONE not even remotely familiar with the subject should be able to tackle it from the ground up. Thus you have concepts introduced in an EXTREMELY step by step fashion, and no one will complain that the book is "difficult to read", per se. But the authors carry it a little too far, and those readers used to traditional textbook techniques of explanation, will be lost in many places. Those who have no problems with this might complain that the book is too long in places. The most satisfied reader will be one who has no idea of what computers are, and was thrown into this course all of a sudden, and who has a lot of free time, and who has an instructor to guide him through the book and the course.

Rather than being a boring, bland and dry text, COMPUTER ORGANIZATION & DESIGN is a well-written and very informative introduction to many hardware and software fundamentals that should be known by anyone with interest in this field. It's a little wordier than it probably could be, but I found the style of the writing to be a great help at teaching myself these sometimes obscure topics. It succeeds at being both a teacher and a reference book.

The authors had the clever idea of introducing many of the concepts from a historical perspective, tracing the beginnings of ideas up to their current implementations. This makes the narrative much less dry than it could have been (let's face it, hardware design isn't exactly riveting material) but makes for a great introduction. The reader gets to see the concepts develop from simpler ideas into the more complicated set-ups of today. Putting the models into that context makes the more difficult concepts easier to grasp.

Some discussion concerning this text has revolved around its wordiness. Certainly the book goes into more detail than it probably needs to, and takes longer than necessary to explain certain topics. But to the student or reader encountering these details for the first time, this approach can be extremely rewarding. I found this book to be an excellent teacher. While it took a little bit of time for me to read, it was quite up to the task of clearly and simply explaining the concepts at hand. Each chapter has a section on Fallacies and Pitfalls, which I found particularly helpful. They take a number of the most commonly held misconceptions about the material in that chapter, and clearly and carefully explain why such things aren't true. I found that a lot of what they covered were things that I had either misconstrued or was unclear about so this section was invaluable for me.

As reference material, the book covers Processor Performance, Microinstructions, Arithmetic (covers binary and floating-point operations done on the MIPS processor), Processor Pipelining, I/O Interfaces, Multiprocessing, and various other MIPS related subjects. If you looking for something that's primarily reference material, you could probably find a text out there that's a bit more concise. But if you're a little rusty on some of these concepts or are encountering them for the first time, then you could do a lot worse than to teach yourself from this book.

Some may wonder why so many teachers, in Universities, Colleges and elsewhere, have selected this textbook among so many other choices.

First, this book presents an authoritative introduction on a popular type of architecture: the MIPS architecture. As the basis for the Pentium class of systems, one can hardly avoid a good coverage of MIPS in a Computer Architecture and Design class. Secondly, the authors have taken great pains to indicate common fallacies and pitfalls as well as "real-world" examples (even though they may be slightly outdated since the writing of this book in 1995). Thirdly the book is fairly comprehensive in breadth, if not always in depth.

This brings us to the real reason this textbook enjoys popularity among teachers: flexibility. Teachers often use a textbook not as a reference, but as an aide in teaching. Usually this means that the exercises, presentation and diagrams are helpful in covering a particular topic. Patterson and Hennessy provide the essentials of MIPS architecture while leaving enough room for teachers to use their own methods of presentation and emphasis. Since the book makes use of logic design but does not require it as a prerequisite (while giving a very good high-level overview in Appendix B), students from a variety of background (hardware or software) can make use of this book without being held back. A teacher may choose to cover logic design in parallel, or seperately, put more emphasis on pipelining or glossing over it, and either offer an extensive coverage of MIPS assembly or ignore it altogether This effectively allows for a wide berth in teaching possibilities.

What's in it for the student? Pay careful attention to your teacher's lecture! (But you know this already) Use this book for its excellent diagrams and for its explanations if you need to understand a particular concept in more details. Use it to do the exercises of course. In the rare event that you understood completely the lecture the first time, do not hesitate to skip ahead to find "Final" diagrams and summary tables.

A note on P&H's incremental method: while it may initially present some difficulty for a reader accustomed to receiving ready-made answers, it is an excellent way of understanding the design process which is inherently incremental in scope and functionality. When studying a series of diagrams (such as 5.19-5.24 or 6.31-6.35), visualize the intermediary figures as stills of a picture. The entire sequence of figures may be played in "fast-forward" to see the evolution of a design or the activities along the instruction datapath. The last figure in such a sequence may then better understood and appreciated.

Last but not least, do not hesitate to read and consult other references such as Tanenbaum's Structured Computer Organization, MIPS reference docs available online and MIPS design companies websites. Do not forget what a Computer Architecture and Design class is all about: learning to design your own architecture one day in the real world!

I am a CS major and recently studied this book in the computer architecture course. The book does not presume prior logic design or assembly language experience. The writing style is quite lively, unlike the dry tone of most science authors. The book is a good mix of theory and history, and has a distinctive 'Fallacies and Pitfalls' section at the end of each chapter that lays to rest the common misconceptions and ill-practices pertaining to the topic of that chapter. The authors are quite well known in the computer design field and anything they say is authoritative and current. Unlike many other books on computer design and architecture, the authors follow a unified approach and build a RISC machine chapter by chapter, introducing new concepts gradually and thoroughly. The detail is remarkable, and the authors have favoured explaining in depth a particular, simple architecture rather than going for a sort of a survey of all the prevalent famous architectures. I found this to be very useful in understanding the basic concepts. Nevertheless, there is a 'Real Stuff' section at the end of most chapters to give one a flavour of full-blown, real-world computer architectures. The diagrams in the book progress from simple to very detailed for a particular portion of the architecture. The chapter on assembly language of MIPS is also very good. Some reviewers have complained about the progressive style of the book, whereby the authors continuously refine an idea. I found it helpful on the first read, as it takes you gradually to the final design. I am sure if they had not done this, students would then have complained about the book being too difficult. However, the book *is* verbose in places. Also, it would have been better to use more headings and other visual aids to categorise and demarcate topics. The exercises are pretty good and the complaint about the examples not having enough mathematics is really not valid, as that is the level of *mathematics* applicable to computer architecture. Overall, an interesting book that I enjoyed and benefitted from a lot.

If you want to understand how modern computers really work, this book is an excellent choice. The book focuses on the MIPS architecture. This is unusual, in this Intel-oriented world, but in the end, the Pentium is nothing but a RISC-computer with a complicated instruction decoder. And with the understanding you get, it will be easy to transfer your knowledge to other architectures and computers.

The book makes a fantastic job of explaining how micro-processors work, how virtual memory, cache-hierarchies, and pipelining affect your programs performance, how to optimize assembly code, how circuits combine to build the arithmetical logic units inside the CPU, and the issues involved in designing and programming for multiprocessor computers and clusters. If you are a computer programmer, or beginning hardware engineer student, this book is for you. A basic course in programming would be advantageous.

This book was not an easy read for me, but if enough time is spent this book is written well enough for an assembly/hardware beginner to grasp it. I had no assembly experience and very little hardware design experience comming into this class, and using this book I was able to do very well in the class, and most importantly understand these concepts. Many people struggled(this is a CS class not EE), but most of these people simply did not put the time into reading the 100+ page chapters. Simply put the book does what its supposed to do very well if you put in the time.

I used this book to learn about computer hardware and architecture. One must realize that the subject matter (that the book discusses) is quite difficult and requires much thought. In spite of the difficulty of the material, the book explains topics quite well. It focuses on specific computer architecture implementations. Thus, it is mainly up to the readers to understand the implementations by reading the book carefully, and ask themselves if there are better ways to implement the computer design.

The book is a bit verbose. I wish it were more succinct. Also, the book could have done a better job explaining the esoteric topics in even more detail such as virtual memory. It also could have provided more examples to help the reader understand why the various designs work.

Overall, not a bad book, but it is certainly not for beginners that have no previous knowledge of basic digital design (such as MUXes, decoders, encoders, gates, flip-flops, state diagrams, state tables, K-maps, etc.).

I was required to read this text for a Computer Design Class, and must say it was anything but an easy read. The book could be commended for being very comprehensive and thorough, but don't expect to speed-read through this one. The author for some reason decided that it would be a good idea to teach you the concepts presented in the book backwards, tell you "oops, just kidding", then explain how you really do it. This can lead to hours of confusion and frustration, trust me. Also, my instructor (thank god for him), often times told the class to skip over relatively large sections of the book on a normal basis, because true to form, it tends to be entirely thorough with information that is not entirely pertinent. Often times even when very clear about what was presented in the chapter, you'll find yourself confused after reading 15 pages, in which a simple idea was presented. If you can avoid this book, you'd be well advised to do so. I'd like to burn my copy. Oh, only if.

This book is quite a strange case. For sure, it is the most widely used around the world for intro courses on Computer Architecturs (CAs). Could it be because Hennessy and Patterson are, at present and since a long time, two of the most prominent researchers in the field, Hennessy being now also President of Stanford University, Patterson a professor at Berkeley. But it would be too reductive to limit the view to this only. So we should move inside the book and try to understand the real (or other) reasons.

As an introductory text on CA, the approach is different than the somewhat classical one.

Those who'd expect a few introductory chapters on logic design (as, e.g., Mano & Kime's chapters or Murdocca's long appendixes) will find instead a short appendix that describes basic components (gates, registers, clocks and so on) at a high level (never mention digital abstracion & co.).

The path then is not a survey of general concepts & principles of CA with eventually some real examples as application. Instead, the process is a strictly step-by-step constructive one: they build from scratch a new system funding the design with plenty of considerations and tips, even with warnings on most common "fallacies and pitfalls". All this done through a very straightforward and clear language and with lots of figures, well paced and presented. As a result, coping with the topics is pretty an easy task, and the most likely result is a thourough understanding of what they present.

So what they present ? Substantially, the MIPS, a well known (thanks to this book and their authors too, of course) and widely sold (thanks to its true qualities) RISC processor. The authors have been leaders in the development of the RISC architecture, which admittedly is by now the only good choice for CPU designs since even Intel in its newest architectures reduce all down to the execution of RISC instructions. Anyway, the attention is not only on RISC (and MIPS) architectures: it's "mostly" on these, but there's space for short disgressions in the PowerPC, 80x86 and Pentium Pro (the book is dated 1997) field. This is done through a section named "Real stuff" in each chapter, where after they've extensively developed the subpart of the MIPS (be it the ISA, the ALU or Datapath & Control, the Pipeline and so on), they summarily look at how the same concepts have been developed by PowerPC and 80x86 or Pentium.

All in all, if the book has been assigned as a textbook for a course, little integration is needed to understand it and made it useful for the course; or if it is used a self first introduction to computer architectures and especially RISC architecture, the book will prove a very good choice. And this happens simply because the transfer of knowledge is effective as probably the authors have intended it to be.
If what is needed is a reference, then perhaps the step-by-step approach would suggest other choices (e.g. Tanenbaum, Murdocca, Stallings or Mano & Kime).

I am an aspiring programmer doing an MSc CS during the evening. I have a background in Finance/Economics. The book would suit a full-time student of CS but for those who are already working it is too long and laborious to read. Always clear but very time consuming. Not simplistic at all - the books goes into subjects that more introductory books leave out. Overall a SUPERB book if you don't have anything else to do for the next 6 months and want to learn things you don't need to know.