An interactive study companion

A Primer on Memory Consistency and Cache Coherence

Every concept, protocol table, and worked example of the textbook — rebuilt as explorable pages: clickable state-transition tables, litmus-test enumerators, step-through animations, and quizzes with explanations.

Based on the book by Vijay Nagarajan, Daniel J. Sorin, Mark D. Hill, and David A. Wood — A Primer on Memory Consistency and Cache Coherence, Second Edition, Synthesis Lectures on Computer Architecture, Morgan & Claypool, 2020. All credit for the material belongs to the authors; this site is a personal study rendering.

Your progress

0/69 sections read

Progress is stored in this browser (localStorage) — sections are marked read when you visit them.

The learning path

After the foundations, the consistency and coherence tracks are largely independent — read them in either order (or interleaved). The advanced chapters draw on both.

Foundations — start here

What consistency and coherence each mean, and the baseline system model + invariants everything else builds on.

Consistency track

What value may a load return? SC, then TSO/x86, then the relaxed models — each with formalism and implementations.

Coherence track

How caches stay invisible: the protocol design space, snooping, directories, and the advanced corners.

Advanced — where both tracks meet

GPUs and heterogeneous systems bend the rules; specification and validation make all the rules precise.

Glossary

Every term the book defines — searchable, with the chapter that introduced it. (The same definitions behind the dotted-underline tooltips on every page.)

How to read this site

Use ←/→ to move between sections. Protocol tables are clickable — every cell explains itself, including the impossible ones. Each section ends with a quiz; missed questions can be retried alone.