The point is that in benchmarks these things don’t really show up at all and Apple still leads. The things I mentioned are only useful because of specific usecases, and saying that Apple is ahead because of those is inaccurate. The point is that the tricks are extremely important for Apple, but not in an argument of “why is Apple making fast processors”.
Regarding a comparison with AMD: I think we’ll have to see what Apple’s professional chips can do. My guess is they’re pulling ahead already.
So JavaScript is not benchmarked, fast ref counting does not improve native application benchmark results, and the memory model trick does nothing to improve benchmark results of x86 applications?
Yeah, you can of course say that each of these is a "specific use case". But which
use cases other than running native MacOS apps built on Apple's frameworks, x86 MacOS apps and web applications do you have in mind? I see those covering a lot of what people tend to do with their MacBooks.
Regarding a comparison with AMD: I think we’ll have to see what Apple’s professional chips can do. My guess is they’re pulling ahead already.