Computer Architecture: A Quantitative Approach - 7th Editon

by John L. Hennessy, David A. Patterson, Christos Kozyrakis

For nearly 30 years, Computer Architecture: A Quantitative Approach has been considered essential reading by instructors, students, and practitioners of computer design. The seventh edition of this classic textbook is fully revised with the latest developments in processor and system architecture. Joined by new co-author Christos Kozyrakis, Turing Award-winning authors John Hennessy and David Patterson continue their longstanding tradition of focusing on areas where the most exciting computing innovations are happening, with a strict emphasis on good engineering design. This edition covers new developments in GPU and CPU architectures, domain-specific architectures, and features more comprehensive coverage of systems on a chip (SoC) and heterogeneity.

936 pages, Paperback

First published October 24, 2025

Reviews

[Rahul Chandra]

I think in the context of the fact it’s a grad level textbook, it’s probably 5 stars, but in terms of ease of reading, it’s a little annoying for chapters 2 and 3.

They tell the reader without a strong background to read the appendices for info about caches and pipelining, and true, it’s actually necessary background material, but the appendix goes way more in-depth than one needs for the chapters. It’s pretty annoying because it takes much longer to read the book, and a lot of the material isn’t strictly necessary(to me anyway).

However, the appendix and chapter on pipelining, as well as the chapter on Data level parallelism are extremely good. Initially I read the fifth edition, which had nothing about Domain Specific Architectures, but this chapter in the sixth edition was probably the best chapter by a long shot(but maybe that’s because I’m just closer to that area so it made more sense to me).

Pretty good book, and I think now I can reason about hardware a lot better.