Intel and Mikko Lipasti of the University of Wisconsin--Madison. This book brings together the numerous microarchitectural techniques for harvesting more instruction-level parallelism (ILP) to achieve better processor performance that have been proposed and implemented in real machines. Other advanced techniques from recent research efforts that extend beyond ILP to exploit thread-level parallelism (TLP) are also compiled in this book. All of these techniques, as well as the foundational principles behind them, are organized and presented within a clear framework that allows for ease of comprehension. This text is intended for an advanced computer architecture course or a course in superscalar processor design. It is written at a level appropriate for senior or first year graduate level students, and can be used by professionals as well.

Hide more