AMD XP+ vs. Intel P4

Originally Posted by DMOS

When an instruction is broken down, it's actually composed of a bunch of littler instructions. In a modern, out of order (OOO) execution processor, like the P4's and K8's, take any number of instructions, break them up, check for dependancies, then try and execute as many of them as possible at once. The K8 takes a few of these in one clock, and tries to spread them wide across a large number of execution units. The P4 is "narrower" and while it is able to handle more individual instructions at once (HT, and a very large "window"), instead of spreading them wide and doing them all at once, it lines them up and just keeps track of them in various stages of execution, trying to get each stage done very quickly.

It might help you to think about these two approaches in terms of a McDonald's analogy. At McDonald's, you can either walk in or drive through. If you walk in, there are five or six short lines that you can get in and wait to have your order processed by a single server in one, long step. If you choose to drive through, you'll wind up on a single, long line, but that line is geared to move faster because more servers process your order in more, quicker steps: a) you pull up to the speaker and tell them what you want; and b) you drive around and pick up your order. And since the drive-through approach splits the ordering process up into multiple, shorter stages, more customers can be waited on in a single line because there are more stages of the ordering process for different customers to find themselves in. So the K8 takes the multi-line, walk-in approach, while the P4 takes the single-line, drive-through approach.

Each can be fast, it just depends on the application. I figured the P4 would be quicker on the WMV thing because it's not code that is hard to predict, and media encoding/decoding traditionally has been a P4 strength thanks to it usually not being something that goes "wide" no matter what you try to do to it.