Welcome to Computer Architecture, taught by Prof. Luis Ceze with Brandon Holt.

This website will be updated throughout the quarter, so check back for the latest.

Course Overview


This is the planned lecture schedule. It will get filled in as we go, so please check back.

Each week there will be several suggested readings, including some textbook chapters and influential research papers. Some lectures there will be a required reading (bolded), which you will need to submit a commentary on. This should be just a paragraph describing what you found most interesting, surprising, or asking questions that you have. These commentaries should be submitted to the Catalyst dropbox before the following lecture.

(subject to change)

Date Topic & Readings HW
Sept 24 (W)

Intro / Metrics / Project ideas

Sep 26 (F)


Oct 1 (W)

ISA/Pipelining Review

Oct 3 (F)

Branch prediction

Oct 8 (W)

Superscalar / Dynamic Scheduling

Oct 10 (F)

Dynamic Scheduling/Short Project Pitches

  • Chapter 3.9-3.16 of HP

Oct 15 (W)

Multithreading/Memory Hierarchy

Oct 17 (F)

Memory hierarchy

Oct 22 (W)

Virtual Memory/NVRAM/Cache coherence

Oct 24 (F)

No lecture (Luis gone, Brandon @ OOPSLA).

Oct 29 (W)

Cache Coherence/Memory Consistency models

  • Chapter 5.5-5.9 of HP

Oct 31 (F)

Doug Carmean on Larrabee

Nov 5 (W)

Memory Consistency models

Nov 7 (F)

Brad Beckman on GPUs

Nov 10 (M)
Nov 12 (W)

No class (Luis out of town)

Nov 14 (F)

Gabe Loh on 3D Stacking

Nov 19 (W)

Transactional Memory/Warehouse-scale Computing

Nov 21 (F)

No class (Luis out of town)

Nov 26 (W)

Denard Scaling/Dark Silicon/specialization

Nov 28 (F)

UW Holiday (Thanksgiving)

Dec 3 (W)


Dec 5 (F)

Visit to the Living Computer Museum

Dec 8 (M)

no class


This calendar just has the lectures, office hours, and special activities/meetings to help you keep up. We'll always let you know about changes via email, but feel free to subscribe to this if you like.

Reading suggestions mentioned in class in passing

Architecture Support for Disciplined Approximate Programming

HardBound: Architectural Support for Spatial Safety of the C Programming Language

Improving Direct-Mapped Cache Performance by the Addition of a Small Fully-Associative Cache and Prefetch Buffers