Source?

Here’s mine

That article may be out of date though. From the article:

What limits computer performance today is predictability, and the two big ones are instruction/branch predictability, and data locality.

This is true, and it points out one of the ways Intel has made their architecture so competitive, Intel has bet very heavily on branch prediction and they’ve done a lot of optimisation around it.

But more recently branch prediction has proven to be quite problematic in terms of security. Branch prediction was the root of the problem that led to the meltdown and spectre vulnerabilities. And the only real mitigation for this problem was to completely redesign how branch prediction was done, and significantly reducing the performance gains.

So yeah to sum up, one of the big differences between ARM and intel’s X86 architecture is branch prediction, except branch prediction just got nerfed big time.