In this conference, we spend a great deal of time addressing new and innovative microarchitecture techniques as a theoretical exercise. In our zeal to build faster, smarter, and cooler designs, we typically assemble a most appealing collections of features, measure their performance with simulators, and pontificate eloquently upon their relative merits.

But there is an enormous amount of engineering that has to cover the gulf between these theoretical exercises and an actual working microprocessor.

This talk will focus on how the architectural concepts in the Pentium(R) 4 microprocessor were refined and revised in the face of real-life design constraints, and describe some of the toils and travails required to bring it (or any other processor) from the drawing board to reality.

Darrell Boggs is a Principle Engineer with Intel Corporation and has been working as a microarchitect for nearly 10 years. He graduated from Brigham Young University with a MS in Electrical Engineering. Darrell has worked on Pentium(R) Pro Processor, Pentium(R) II Processor, and the Pentium(R) 4 Processor. Darrell holds 13 microarchitectural patents in the areas of register renaming; instruction decoding; event and state recovery mechanisms and out-of-oder core architectures. But there is an enormous amount of engineering that has to cover the gulf between these theoretical exercises and an actual working microprocessor.