I've seen plenty of software (especially systems software) that does spend much of it's time in tight inner loops. Pulling out all the optimization stops there can give measurable gains. I've personally seen measurable gains on real applications from tricks like reordering branches so that the more predictable branches go first.
So it's situational, but IME it's pretty predictable where you'll see this kind of optimization help. By all means profile and use whatever tools at hand to help you along, and don't apply the optimization blindly - but despite the whole "black art" label optimization sometimes gets this kind of thing really is pretty straightforward.
The danger is that benchmarks like this encourage naïve programmers to use complex constructs as a matter of course, when simpler would usually be better. "Premature optimisation is the root of all evil" and all that...
Are there any open source projects amongst your examples?
In the end, it's just another tool which is the right one in particular circumstances, and the wrong one in all others.
The author is clearly aware that the real world of performance is much bigger & more complex than his simple Petri dish. Credit to him for mentioning that. It's also really refreshing to see him analysing the optimised assembly.
The trouble with this approach is that it's tempting to draw simple conclusions. In this case, you might be tempted to conclude "CRTP always faster than virtual dispatch", when the truth is likely to be much more situation dependent.
I have seen a biggish project go though a lot of effort to switch to CRTP, only to see a negligible performance impact.