 Okay, so this first example is about as simple as you can get, and it's in part just designed to get you familiar with the idea and see how it's working, what the equation is telling you. So we have an example of a given machine can complete a task in 30 seconds. So what's its performance on this task? So we have an execution time, 30 seconds. We want to solve for performance. So we've got the nice equation. So p equals 1 divided by 30 seconds. So, okay, I can reduce this. It says 0.03. And because I have 1 divided by seconds, that's then in hertz. So, well, I'm getting a small number because 30 is much, much bigger than 1. And so what is this telling me? Well, one thing it tells me is that, okay, it's not terribly high performance. I'd probably like something much greater than 1. It's telling me that I can finish 0.03 of these tasks every second as well. So if I've got a whole bunch of tasks that I'd like to run, and I'm interested in finding out how long it's going to take, or how much work I can get done every second, this will tell me something about how much work I can compute in every second. Again, really, really simple example, but it illustrates the point well enough. For a slightly more complex example, we can look at, well, what's the case if instead of 30 seconds, our computer completes a different task in 2 milliseconds. So, again, have performance equals 1 divided by 2 milliseconds. So 2 milliseconds is much, much smaller than 1. So that will be 1 divided by 2 times 10 to the minus third seconds. So that's 0.5 times 10 to the third, or 500 hertz. So this time it's telling me I can complete 500 of this task every second, which is obviously much more in the previous example, because 2 milliseconds is obviously much, much smaller than 30 seconds. So this one takes far less time to compute than this one, so I can obviously finish far more of them in the same amount of time.