I remember when the first edition came out---back in the early 90's!!!! I was young, slim, had a full head of hair---and this new textbook was the bomb. Vastly better than any previous textbook on computer architecture.

I can't believe it is still the best. it's been like 30 years. During that time, so much has happened--the death of supercomputer companies like Convex and Cray, SIMD going from expensive computers like the MASPAR MP-1 to being on virtually every processor, the dot com boom, the rise of google-style server farms, etc etc.

And now the transition to neural net processing.

I mean, it is a testament to the authors that they could keep their competitors from even thinking about trying to write a competing book for so long. It is a great case study in how to stay relevant in tech for the long term.

But man, before it came out, every year 2 or 3 new textbooks in computer architecture came out, each one detailing the next cool thing which computer architectures were being called upon to do.

It's exhibit A of Peter Thiel's case that we are living in an era of very low innovation. If Computer Architecture were a really healthy field, classes would have to be taught from recently-published papers, because it was moving faster than a textbook could be published.

Hat's off to the authors, but man, this is really depressing.