I enjoyed that it was a simpler read then a lot of the circuits-type of books that are part of a EE/CE curriculum, but I always felt there was this lack of "hard science"/physics in the book.
And perhaps it was just not a topic they felt fit with the vision of what this book is suppose to be, and it likely came to be a better decision to abstract that part away for readability.
I would recommend COaD to any beginner who wants to learn some basic concepts of computer design (and if working with FPGAs why not build one).
CA deals with more advanced concepts but doesn't overwhelm you with math and circuit theory (as you noted) so it's a natural progression (from COaD). I think something more advanced and "hard science" should be part of a post-graduate curriculum
It's a long time since I read it, but from my memory that's the kind of thing the book is about. I'm not sure how you'd determine those kinds of things in a more "hard science"/physics fashion.
Given that most of my career has been pretty far removed from the compiler/assembly instructions, much of the content wasn't directly relevant to what I've been doing, but I still find myself using many of the tools that are outlined in the first chapter ("Quantitative Principles of Computer Design") when dealing with performance problems or analysis in high-level-language-world, which happens pretty often.
But man, 6 months out and I retained nearly nothing. It's just so esoteric and not very relevant to my every day schoolwork(then) and career(now) that it's slowly seeped out of my brain.