AnyBook4Less.com | Order from a Major Online Bookstore |
![]() |
Home |  Store List |  FAQ |  Contact Us |   | ||
Ultimate Book Price Comparison Engine Save Your Time And Money |
![]() |
Title: Software Optimization Cookbook: High-Performance Recipes for the Intel Architecture by Richard Gerber ISBN: 0-9712887-1-2 Publisher: Intel Press Pub. Date: 20 March, 2002 Format: Paperback Volumes: 1 List Price(USD): $49.95 |
Average Customer Rating: 4.2 (5 reviews)
Rating: 3
Summary: Great book - lousy publishing
Comment: I really like the book. The author did an amazing job explaining the material in such a way that it's not only easy to understand but also easy to remember.
The only big problem I had with my copy was that pages 139-162 were missing and pages 115-138 were duplicated instead. Obviously the publisher didn't do a very good job. I don't know if all copies have this problem or only mine. Be careful when you buy the book, check for duplicated/missing pages.
Rating: 5
Summary: Great book for software guys
Comment: I am happy to have found this book! I am a software guy who was faced with the need to optimize my applications on the Intel platforms. This book helped me to make a start in meeting my needs without necessarily having to become a hardware guru. The content is presented in an easy-to-read style.
Rating: 4
Summary: Simplistic but enjoyable
Comment: It is initially disconcerting to read this book if you don't own a copy of VTune; it seems like an advertisement for the first few chapters.
By the end of the book, it seems natural to use Vtune as an example; other profilers won't cut it for some of the problems (eg. register stalls, cache misses) that Gerber discusses. Vtune is pretty much essential to reap maximum benefit from this book.
The book is excellent in its coverage of the IA32 family, Pentium 4 included. It is simplistic in its approach, suitable most for the novice who hasn't browsed the depths of the (free) Intel manuals.
Metrics are lacking, sometimes worringly so - my trials show that conditional jumps on random data outperform conditional moves, contradicting his advice on branch prediction. This is probably the result of gross oversimplification on the book's part.
There could be more technical detail here, but for the first step on a complex voyage, it's not bad.
Thank you for visiting www.AnyBook4Less.com and enjoy your savings!
Copyright� 2001-2021 Send your comments